Vehicle driving route selection method and device based on mine scene

Abstract

The embodiment of the invention provides a vehicle driving route selection method and device based on a mine scene, and relates to the technical field of vehicles. The method comprises the following steps: acquiring a pavement image of a to-be-measured mine scene through an image acquisition sensor on a target mine car, and acquiring pavement temperature information of the to-be-measured mine scene through a temperature acquisition sensor on the target mine car; determining pavement state information based on the pavement image and the pavement temperature information; and adopting a route planning algorithm to obtain a target driving route of the target mine car based on the pavement state information. According to the embodiment of the invention, data of different sensors are fused, so that the accuracy of pavement state information is improved; according to the invention, the route planning algorithm is adopted to perform route selection on the target mine car based on the road surface state information to obtain the optimal target driving route, so that the mine car is prevented from driving to an area with relatively high slip risk, the selected target driving route is relatively high in safety, and the driving safety of the mine car is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle technology, and in particular to a method and device for selecting a vehicle driving route based on a mining scenario. Background Art

[0002] Mining areas are often located in mountainous and hilly areas with complex terrain and harsh climate. Under rainy, snowy and freezing weather conditions, mining vehicles (such as unmanned mining vehicles) often have the risk of slipping when driving in mining areas. Therefore, a vehicle route selection method for mining scenarios is urgently needed to ensure the safe driving of mining vehicles in mining areas. Summary of the invention

[0003] The embodiment of the present disclosure provides a method and device for selecting a vehicle driving route based on a mine scenario, which is used to provide a driving route with a lower risk of skidding for vehicles driving in a mine environment. The technical solution provided by the present disclosure is as follows: According to one aspect of an embodiment of the present disclosure, a method for selecting a vehicle driving route based on a mine scenario is provided, the method comprising: Acquire a road surface image of the mine scene to be tested through an image acquisition sensor on the target mine car, and acquire road surface temperature information of the mine scene to be tested through a temperature acquisition sensor on the target mine car; Determining road surface state information based on the road surface image and the road surface temperature information; A route planning algorithm is used to obtain a target driving route of the target mining vehicle based on the road surface state information.

[0004] Optionally, determining the road surface state information based on the road surface image and the road surface temperature information includes: Determining road surface roughness based on the road surface image; Based on the road surface roughness and the road surface temperature information, road surface state information is determined.

[0005] Optionally, the method further comprises: Acquire a real-time friction coefficient between the target mine car and the road surface through a road surface condition sensor on the target mine car; Based on the road surface image, the road surface temperature information and the real-time friction coefficient, skidding risk information is determined.

[0006] Optionally, the determining the skidding risk information based on the road surface image, the road surface temperature information and the real-time friction coefficient includes: If a skidding risk is detected based on the road surface state information, the road surface roughness, the road surface temperature information and the real-time friction coefficient are input into a pre-trained skidding risk prediction model to obtain a skidding risk coefficient output by the skidding risk prediction model.

[0007] Optionally, the detecting the existence of a skidding risk based on the road surface state information includes: According to the road surface state information and the tire model of the target mine car, query the anti-skid coefficient corresponding to the target mine car; If the anti-skid coefficient is greater than the real-time friction coefficient, it is determined that there is a risk of skidding.

[0008] Optionally, determining the road surface roughness based on the road surface image includes: grayscale the road surface image to obtain a grayscale image corresponding to the road surface image; Performing two-dimensional sampling on the grayscale image to obtain at least two two-dimensional sampling points; Based on the grayscale image and the at least two two-dimensional sampling points, obtaining a three-dimensional grid image corresponding to the road surface image; Based on the three-dimensional grid image, a road surface roughness corresponding to the road surface image is calculated.

[0009] Optionally, the method further comprises: If the skidding risk coefficient is less than a first threshold value, determining the skidding risk level as slight skidding; If the skidding risk coefficient is not less than the first threshold value and less than the second threshold value, the skidding risk level is determined to be moderate skidding; Otherwise, the skidding risk level is determined to be severe skidding.

[0010] Optionally, the method further comprises: Based on the skidding risk level, determining a vehicle control strategy corresponding to the skidding risk level; The vehicle control strategy is sent to a vehicle control module so that the vehicle control module executes the vehicle control strategy on the target mining vehicle.

[0011] Optionally, each sensor on the target mine car is arranged on the target mine car based on a target arrangement; The target sensor arrangement is determined based on the following steps: Determine an initial arrangement; the initial arrangement includes position information corresponding to a plurality of sensors; Based on deep reinforcement learning, the initial arrangement is adjusted at least once until a preset condition is satisfied, and the initial arrangement that satisfies the preset condition is used as a target arrangement; The preset condition includes that the sensor arrangement performance index is maximum.

[0012] According to another aspect of an embodiment of the present disclosure, a vehicle driving route selection device based on a mine scene is provided, the device comprising: A data acquisition module, used to acquire a road surface image of the mine scene to be tested through an image acquisition sensor on the target mine car, and to acquire road surface temperature information of the mine scene to be tested through a temperature acquisition sensor on the target mine car; A road surface state information determination module, used to determine road surface state information based on the road surface image and the road surface temperature information; The route selection module is used to obtain the target driving route of the target mining vehicle based on the road surface state information by using a route planning algorithm.

[0013] According to another aspect of an embodiment of the present disclosure, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the steps of any one of the above-mentioned methods for selecting a vehicle route based on a mining scenario are implemented.

[0014] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned vehicle route selection methods based on a mine scenario are implemented.

[0015] According to one aspect of an embodiment of the present disclosure, a computer program product is provided, which includes a computer program. When the computer program is executed by a processor, the steps of any of the above-mentioned vehicle driving route selection methods based on a mine scenario are implemented.

[0016] The technical solution provided by the embodiments of the present disclosure has the following beneficial effects: By setting up a variety of different types of sensors on the target mine car, obtaining road surface images and road surface temperature information, fusing data from different sensors, and analyzing road surface status information in multiple dimensions such as road surface characteristics and road surface temperature, the accuracy of road surface status information is improved; a route planning algorithm is used to select the route of the target mine car based on the road surface status information to obtain the optimal target driving route, fully considering the skidding risks caused by different road surface conditions, avoiding driving to areas with higher skidding risks, making the selected target driving route safer, and improving the safety of vehicle driving. At the same time, it can also avoid interruptions to vehicle driving caused by road slippage, improve the continuity of vehicle driving, and improve the work efficiency of the target mine car. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for describing the embodiments of the present disclosure are briefly introduced below.

[0018] Figure 1 A schematic diagram of a process flow of a vehicle driving route selection method based on a mine scenario provided by an embodiment of the present disclosure; Figure 2 A schematic diagram of a flow chart of a method for determining a skidding risk level provided in an embodiment of the present disclosure; Figure 3 A system architecture diagram of a vehicle safety system provided by an embodiment of the present disclosure; Figure 4 A schematic diagram of the structure of a vehicle driving route selection device based on a mine scene provided by an embodiment of the present disclosure; Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] The embodiments of the present disclosure are described below in conjunction with the drawings in the present disclosure. It should be understood that the implementation methods described below in conjunction with the drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present disclosure and do not constitute a limitation on the technical solutions of the embodiments of the present disclosure.

[0020] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present disclosure refer to that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude the implementation as other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the technical field. It should be understood that when we say that an element is "connected" or "coupled" to another element, the one element may be directly connected or coupled to the other element, or it may refer to that the one element and the other element establish a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein indicates at least one of the items defined by the term, for example, "A and / or B" or "A, B" indicates that it is implemented as "A", or implemented as "B", or implemented as "A and B".

[0021] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0022] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present disclosure and the technical effects produced by the technical solutions of the present disclosure. It should be noted that the following embodiments can refer to, draw on or combine with each other, and the same terms, similar features and similar implementation steps in different embodiments will not be described repeatedly.

[0023] Figure 1 A flowchart of a method for selecting a vehicle driving route based on a mining scenario provided by an embodiment of the present disclosure is shown in FIG. Figure 1 As shown, the method includes: Step S110, acquiring a road surface image of the mine scene to be tested through an image acquisition sensor on the target mine car, and acquiring road surface temperature information of the mine scene to be tested through a temperature acquisition sensor on the target mine car.

[0024] Specifically, the vehicle route selection method based on the mining scene provided in the embodiment of the present disclosure can be applied to the vehicle safety system. The vehicle safety system can be set on the target mine car. The target mine car travels in the mining scene to be tested. The target mine car can include unmanned mine cars and manually driven mine cars, etc. The embodiment of the present disclosure does not limit the specific type of the target mine car.

[0025] The target mine car can be equipped with multiple sensors, including image acquisition sensors and infrared thermal imaging sensors. Among them, the image acquisition sensor can use a high-definition camera to capture real-time images of the road surface, focusing on monitoring factors such as road color, brightness and texture changes that affect the slipperiness of the road surface in rainy and snowy weather. The camera should have good low-light performance and be able to work at night or in bad weather conditions. For example, a shutter camera can be used to avoid motion blur and support high dynamic range (HDR) to capture wider brightness details. The temperature acquisition sensor can be an infrared thermal imaging sensor, which can effectively detect the road surface temperature at night or in low visibility conditions through infrared thermal imaging technology.

[0026] Step S120, determining road surface state information based on the road surface image and road surface temperature information.

[0027] Specifically, the road surface image can be used to reflect the road surface characteristics such as color, texture and brightness of the road surface of the mine scene to be tested, and the road surface temperature information can be used to reflect whether the road surface of the mine scene to be tested is likely to be frozen. Therefore, after obtaining the road surface image and the road surface temperature information, the road surface state information of the target mine car can be determined by combining the road surface image and the road surface temperature information.

[0028] The road surface condition information may be used to reflect the surface condition of the road surface, and the road surface condition information may include dryness, wetness, slipperyness, and ice.

[0029] As an optional embodiment, determining the road surface state information based on the road surface image and the road surface temperature information includes: Based on the road surface image, determine the road surface roughness; Determine road surface condition information based on road surface roughness and road surface temperature information Specifically, after the road surface image is obtained, the road surface roughness can be analyzed by performing image processing on the road surface image, and the road surface state information can be obtained by combining the road surface roughness and road surface temperature information.

[0030] Optionally, the road surface roughness and road surface temperature information can be combined to classify the road surface state using machine learning algorithms (such as random forest or support vector machine) to obtain road surface state information. In addition, deep learning algorithms such as convolutional neural network (CNN) can be introduced to process image data; reinforcement learning algorithms can be used to optimize the data processing process and improve the accuracy of road surface state classification.

[0031] Step S130, using a route planning algorithm to obtain a target driving route of the target mining vehicle based on the road surface status information.

[0032] Specifically, after obtaining the road surface status information, the route selection can be performed through a route planning algorithm in combination with the road surface status information and the real-time traffic information to obtain a target driving route of the target mining vehicle.

[0033] The target driving route may be an optimal driving route, for example, a driving route with the lowest risk of skidding.

[0034] Optionally, specific road surface points in the mine scene can be used as nodes based on real-time traffic information, such as intersections and turning points. The edges connecting the nodes are constructed based on the drivable paths between the nodes, and the weights corresponding to the edges are set based on the obtained road surface status information. After setting the starting point and the end point, the nodes can be traversed by an algorithm (such as A* or Dijkstra algorithm), and the path cost can be calculated according to the weight of the edge. Assuming that a larger weight is set for the edge corresponding to the road surface state of "icy", and a smaller weight is set for the edge corresponding to the road surface state of "dry", the route with the smallest path cost (that is, the route with the lowest risk of slipping) can be used as the target driving route.

[0035] Optionally, route selection can be performed based on a multi-objective optimization algorithm. For example, driving time, energy consumption, skidding risk, etc. can be used as multiple objectives to be optimized, and a driving route with the shortest time, the lowest energy consumption and the lowest skidding risk can be determined based on an algorithm (such as a genetic algorithm or a particle swarm optimization algorithm) as the target driving route.

[0036] The vehicle driving route selection method based on the mining scene provided by the embodiment of the present disclosure, by setting a plurality of different types of sensors on the target mining car, obtaining the road surface image and road surface temperature information, fusing the data of different sensors, and analyzing the road surface state information in combination with multiple dimensions such as road surface characteristics and road surface temperature, thereby improving the accuracy of the road surface state information; using a route planning algorithm to select the route of the target mining car based on the road surface state information, obtaining the optimal target driving route, fully considering the skidding risks caused by different road surface conditions, avoiding driving to areas with higher skidding risks, making the selected target driving route safer, and improving the safety of vehicle driving. At the same time, it can also avoid the interruption of vehicle driving caused by road slippage, improve the continuity of vehicle driving, and improve the working efficiency of the target mining car.

[0037] As an optional embodiment, the method further includes: The real-time friction coefficient between the target mine car and the road surface is obtained through the road surface condition sensor on the target mine car; Determine skidding risk information based on road surface images, road surface temperature information and real-time friction coefficient.

[0038] Specifically, a road condition sensor may be provided on the target mine car, and the road condition sensor may be installed on the tire or chassis of the target mine car. The road condition sensor is used to monitor the contact condition between the tire of the target mine car and the road surface in real time, so as to calculate the real-time friction coefficient between the tire of the target mine car and the road surface. The real-time friction coefficient may be used to reflect the contact condition between the tire of the target mine car and the road surface.

[0039] Optionally, a laser radar sensor may be provided on the target mining vehicle to detect obstacles or depressions on the road surface to improve driving safety. A wheel slip sensor may also be provided on the target mining vehicle, for example, a wheel slip sensor may be installed on each tire to monitor the slip state of the tire in real time, and when it is detected that the slip threshold is approaching, timely feedback is given to the vehicle control unit to control the vehicle to perform a braking operation.

[0040] It should be noted that one or more sensors of each type may be provided, and the number of sensors of each type may be specifically set according to actual application requirements, which is not limited in the embodiments of the present disclosure. The installation position of each sensor on the target mining vehicle may also be specifically set according to actual application requirements, which is not limited in the embodiments of the present disclosure.

[0041] When the target mine car is traveling on the road, the road surface image can be acquired through the image acquisition sensor on the target mine car, the road surface temperature information can be acquired through the temperature acquisition sensor on the target mine car, and the real-time friction coefficient between the tires of the target mine car and the road surface can be acquired through the road condition sensor on the target mine car.

[0042] After obtaining the road surface image, road surface temperature information and real-time friction coefficient, the skidding risk information of the target mining vehicle traveling on the road surface can be determined by combining the road surface image, road surface temperature information and real-time friction coefficient. The skidding risk information can be used to reflect whether there is a skidding risk on the road surface, and can also be used to reflect the degree of the skidding risk.

[0043] Optionally, the slip risk information can be determined based on a machine learning algorithm. For example, the road surface image, road surface temperature information and real-time friction coefficient can be input into a pre-trained model to obtain the slip risk information output by the model. The road surface image and road surface temperature information can also be combined to determine the type of road surface condition, and then the anti-skid information of the tires of the target mining car under the corresponding road surface condition can be queried. Finally, the slip risk information can be determined by combining the anti-skid information and the real-time friction coefficient. The specific method for determining the slip risk information is not limited in the embodiments of the present disclosure.

[0044] In the disclosed embodiment, a variety of different types of sensors are arranged on the target mine car to obtain multi-source data such as road surface images, road surface temperature information and real-time friction coefficient. By fusing the data from different sensors and combining road surface characteristics, road surface temperature and the contact conditions between the tires of the target mine car and the road surface, the slip risk information is analyzed from multiple dimensions. The information is utilized more comprehensively, which improves the accuracy of slip risk detection, thereby reducing traffic accidents caused by road slippage and further improving the safety of vehicle driving.

[0045] As an optional embodiment, the skidding risk information is determined based on the road surface image, road surface temperature information and real-time friction coefficient, including: If a skidding risk is detected based on the road surface condition information, the road surface roughness, road surface temperature information and real-time friction coefficient are input into a pre-trained skidding risk prediction model to obtain a skidding risk coefficient output by the skidding risk prediction model.

[0046] Specifically, after obtaining the road surface image, the road surface roughness can be analyzed by performing image processing on the road surface image, and the road surface state information can be obtained by combining the road surface roughness and road surface temperature information. The road surface state information can be used to reflect the surface state of the road surface, and the road surface state information can include dryness, wetness, and ice.

[0047] Optionally, the road surface roughness and temperature information can be combined to classify the road surface state using machine learning algorithms (such as random forest or support vector machine) to obtain road surface state information. In addition, deep learning algorithms such as convolutional neural network (CNN) can be introduced to process image data; reinforcement learning algorithms can be used to optimize the data processing process and improve the accuracy of road surface state classification.

[0048] After analyzing the road surface condition information, it can be determined whether there is a risk of skidding on the road surface based on the road surface condition information. For example, when the road surface condition information is dry, it is determined that there is no risk of skidding; when the road surface condition information is wet or icy, it is determined that there is a risk of skidding.

[0049] When a risk of skidding is detected on the road surface, the road surface roughness, road surface temperature information and real-time friction coefficient can be input into a pre-trained skidding risk prediction model. The skidding risk model is combined with the road surface roughness, road surface temperature information and real-time friction coefficient for analysis to predict the degree of skidding risk of the road surface on which the target mine car is traveling, and output the skidding risk coefficient. The skidding risk coefficient can be used to reflect the level of the risk of skidding on the road surface. For example, the larger the value of the skidding risk coefficient, the higher the risk of skidding on the road surface.

[0050] Optionally, the skidding risk prediction model may also be trained, and the training process may include: determining an initial skidding risk prediction model; inputting multiple training samples into the initial skidding risk prediction model, each training sample may include sample road surface roughness, sample road surface temperature information, sample real-time friction coefficient and sample skidding risk coefficient; by continuously adjusting the model parameters of the initial skidding risk prediction model, the difference between the predicted skidding risk coefficient of each training sample output by the initial skidding risk prediction model and the sample skidding risk coefficient becomes smaller and smaller, and the trained initial skidding risk prediction model is used as a skidding risk detection model.

[0051] Optionally, after obtaining the slip risk coefficient, the slip risk coefficient may be analyzed, and when the slip risk coefficient is large, the driving strategy or driving route of the target mining vehicle may be adjusted to ensure the safety of vehicle driving.

[0052] In the disclosed embodiment, the road surface state information is determined by combining the road surface roughness and road surface temperature information, and a preliminary judgment is made on whether there is a risk of skidding based on the road surface state information; when the risk of skidding is detected, a skidding risk coefficient is determined based on the road surface roughness, road surface temperature information and the real-time friction coefficient, and a corresponding skidding risk level is determined based on the skidding risk coefficient. There is no need to conduct further analysis on the situation where there is no risk of skidding, thereby improving the efficiency of data processing and the response speed of skidding risk detection. For the situation where there is a risk of skidding, a more accurate skidding risk coefficient can be obtained, further improving the accuracy of skidding risk detection.

[0053] As an optional embodiment, detecting the risk of skidding based on road surface status information includes: According to the road condition information and the tire model of the target mine car, the anti-skid coefficient corresponding to the target mine car is queried; If the anti-skid coefficient is greater than the real-time friction coefficient, it is determined that there is a risk of skidding.

[0054] Specifically, after obtaining the road surface condition information, the tire model of the target mine car can be obtained, and based on the road surface condition information and the tire model of the target mine car, the anti-skid coefficient of the target mine car under the current road surface condition can be queried from the vehicle database, and then the relationship between the anti-skid coefficient and the real-time friction coefficient can be determined.

[0055] If the anti-skid coefficient is greater than the real-time friction coefficient, it is determined that there is a skidding risk, and the degree of the skidding risk can be further determined; otherwise, it is determined that there is no skidding risk, and the target mine car can maintain the original route and continue to monitor the road skidding situation.

[0056] In the disclosed embodiment, compared with directly judging whether there is a risk of slipping on the road surface through road surface status information, the anti-skid characteristics of the tires of the target mining vehicle are fully considered, thereby improving the accuracy of slip risk detection.

[0057] As an optional embodiment, determining the road surface roughness based on the road surface image includes: Grayscale processing is performed on the road surface image to obtain a grayscale image corresponding to the road surface image; Perform two-dimensional sampling on the grayscale image to obtain at least two two-dimensional sampling points; Based on the grayscale image and at least two two-dimensional sampling points, a three-dimensional grid image corresponding to the road surface image is obtained; Based on the three-dimensional grid image, the road surface roughness corresponding to the road surface image is calculated.

[0058] Specifically, in order to obtain the road surface roughness, the road surface image can be grayed and the color road surface image can be converted into a corresponding grayscale image to improve the efficiency of image processing. After obtaining the grayscale image, at least two two-dimensional sampling points in the grayscale image can be obtained by performing two-dimensional sampling on the grayscale image. At the same time, the grayscale data corresponding to the grayscale image is obtained, and a three-dimensional grid image corresponding to the road surface image can be constructed according to the two-dimensional sampling points and grayscale data of the grayscale image, and the corresponding road surface roughness can be calculated based on the three-dimensional grid image.

[0059] Optionally, for a three-dimensional network image, the maximum grayscale value can be determined from the grayscale values ​​corresponding to each pixel in the image, and the difference between the grayscale value of each pixel and the maximum grayscale value can be calculated to obtain multiple differences. The multiple differences are summed and averaged, and the average value of the calculated differences is used as the road roughness.

[0060] In addition, the road surface image can also be preprocessed. For example, the road surface image can be preprocessed by denoising, contrast enhancement, and edge detection to highlight the road surface features and provide clear image data for subsequent analysis.

[0061] As an optional embodiment, when the temperature acquisition sensor is an infrared thermal imaging sensor, thermal imaging data is acquired through the temperature acquisition sensor, and the thermal imaging data is preprocessed, including radiation correction, temperature calibration, etc., to ensure the accuracy of the thermal imaging data. After preprocessing, the acquired thermal imaging data can be analyzed by infrared analysis software, including emissivity adjustment, critical temperature setting, and temperature value marking of measurement points and areas, to obtain corresponding road surface temperature information.

[0062] As an optional embodiment, Figure 2 A schematic diagram of a method for determining a skidding risk level provided by an embodiment of the present disclosure is shown in FIG. Figure 2 As shown, the method also includes: If the skidding risk coefficient is less than the first threshold, the skidding risk level is determined to be slight skidding; If the skidding risk coefficient is not less than the first threshold value and less than the second threshold value, the skidding risk level is determined to be moderate skidding; Otherwise, the skidding risk level is determined to be severe skidding.

[0063] Specifically, after obtaining the skidding risk coefficient, the skidding risk level can be determined by comparing the skidding risk coefficient with the first threshold and the second threshold, wherein the first threshold and the second threshold can be determined based on limited experiments, and the first threshold is smaller than the second threshold.

[0064] When the slip risk coefficient is less than the first threshold, the corresponding slip risk level is determined to be mild slip; when the slip risk coefficient is not less than the first threshold and less than the second threshold, the corresponding slip risk level is determined to be moderate slip; when the slip risk coefficient is not less than the second threshold, the corresponding slip risk level is determined to be severe slip.

[0065] Optionally, after determining the skidding risk level, the method further includes: Based on the skidding risk level, determining a vehicle control strategy corresponding to the skidding risk level; The vehicle control strategy is sent to the vehicle control module so that the vehicle control module executes the vehicle control strategy on the target mining vehicle.

[0066] Specifically, corresponding vehicle control strategies can be set for different skidding risk levels. For example, for mild skidding, the corresponding vehicle control strategy may include adjusting the vehicle speed, reducing power output, and fine-tuning the vehicle's driving route to avoid potential skidding areas; for moderate skidding, the corresponding vehicle control strategy may include adjusting the vehicle speed, reducing power output, and activating the vehicle's Electronic Stability Program (ESP) to help the vehicle maintain stability by braking individual wheels of the braking system; for severe skidding, the corresponding vehicle control strategy may include immediately activating the emergency braking system and using the vehicle's dynamic control technology (such as torque vectoring) to stabilize the vehicle and prevent it from losing control.

[0067] After determining the skidding risk level, a vehicle control strategy corresponding to the skidding risk level can be determined and sent to a vehicle control module. After receiving the vehicle control strategy, the vehicle control module can control the vehicle's driving according to the vehicle control strategy to ensure safe driving of the vehicle.

[0068] In the disclosed embodiment, based on the skidding risk level corresponding to the skidding risk coefficient, corresponding vehicle control strategies are designed for different skidding risk levels, thereby improving the safety of vehicle driving.

[0069] As an optional embodiment, each sensor on the target mine car is arranged on the target mine car based on the target arrangement; The target sensor layout is determined based on the following steps: Determine an initial arrangement; the initial arrangement includes position information corresponding to each of the plurality of sensors; Based on deep reinforcement learning, the initial arrangement is adjusted at least once until a preset condition is satisfied, and the initial arrangement that satisfies the preset condition is used as a target arrangement; The preset conditions include the maximum sensor arrangement performance index.

[0070] Specifically, the optimal arrangement of multiple sensors on the target mine car, ie, the target arrangement, can be obtained, and each sensor is arranged on the target mine car according to the target arrangement, thereby achieving the optimization of the sensor layout.

[0071] The target layout can be determined based on deep reinforcement learning. The specific process includes setting initial position information corresponding to multiple sensors on the target mine car to obtain an initial layout, wherein the initial position information corresponding to each sensor is in the same coordinate system, for example, it can be a world coordinate system, or it can be a coordinate system established with the target mine car as a reference, and the initial position information can be expressed as a three-dimensional coordinate.

[0072] Sensor placement performance indicators may be set to reflect the benefits corresponding to different placement methods. The sensor placement performance indicators may include the coverage range corresponding to each sensor as a whole and the information gain corresponding to each sensor as a whole, etc. The sensor placement performance indicators may be specifically set according to actual application requirements.

[0073] Based on the deep reinforcement learning algorithm, the position information corresponding to each sensor in the initial layout is continuously adjusted, and the initial layout that achieves the maximum sensor performance index is taken as the target layout to achieve the optimal layout of multiple sensors.

[0074] In the disclosed embodiment, the optimal target layout is determined based on a deep reinforcement learning algorithm, and multiple sensors are set on the target mining car according to the target layout, thereby achieving the optimal layout of multiple sensors, improving the complementarity between the sensors, and further improving the reliability of data collection.

[0075] Figure 3 A system architecture diagram of a vehicle safety system provided by an embodiment of the present disclosure, such as Figure 3As shown in the figure, the vehicle safety system includes a user interaction module, a vehicle control module, a data processing module, a data acquisition module, a communication module and a safety and redundancy module. Among them, the user interaction module includes an AR (Augmented Reality) display unit, a tactile feedback unit and a cockpit display unit, which are used to provide users with intuitive road conditions and driving suggestions. The vehicle control module includes a driving assistance unit, an emergency response unit and a control strategy adjustment unit, which are used to adjust the vehicle driving parameters according to the output of the data processing module. The data processing module includes an image processing unit, a thermal imaging processing unit and a data analysis unit, which are responsible for processing the data collected by the sensor and extracting useful information. The data acquisition module includes an image acquisition sensor, an infrared thermal imaging sensor and a road condition sensor, which are used to monitor the road condition in real time. The communication module includes a vehicle network communication unit and a data transmission unit, which are used to share road condition information with other vehicles or infrastructure. The safety and redundancy module includes a redundant sensor unit, a system self-test unit and a data verification and validation unit, which are used to ensure the stability of the system and the accuracy of the data.

[0076] In the user interaction module, the AR display unit can be used to introduce augmented reality technology to directly display the road conditions and recommended routes in the form of graphics and color coding in the driver's field of view. The cockpit display unit can be used to display the road conditions and recommended routes in the form of graphics and color coding on the vehicle's dashboard or central control screen.

[0077] The data acquisition module can use a high-speed data acquisition module (such as an embedded microprocessor) to ensure real-time data acquisition and processing. The module should support a high sampling rate and have sufficient storage space to save the collected data. Since the data acquisition equipment will work in a harsh outdoor environment, it is necessary to ensure that all equipment has sufficient protection level, such as IP67 (a protection safety level) or higher, to prevent dust and water.

[0078] In the data processing module, the data of the image sensor and the infrared sensor can also be integrated into a processing unit, and a multi-tasking real-time operating system can be used to manage data flow and processing tasks to ensure the real-time and stability of the system.

[0079] In the vehicle control module, the driving assistance unit can be used to automatically adjust vehicle driving parameters such as speed and power output based on the output of the data analysis unit; it can also provide the driver with real-time information on road conditions and recommended driving routes. The emergency response unit can be used to automatically activate emergency braking or stability control systems when a high risk of skidding is detected. The control strategy adjustment unit can be used to adaptively adjust vehicle driving parameters such as automatic gear shifting and torque distribution in real time based on road conditions.

[0080] In the communication module, the IoV communication unit can be used to communicate with other vehicles or road infrastructure, share road status information, and improve the safety of the overall traffic system. For example, 5G technology can be used to achieve high-speed, low-latency communication between vehicles (V2V) and vehicles and infrastructure (V2I).

[0081] The safety and redundancy module can be used in any slipping situation. If the main control system cannot respond effectively, the redundant sensor system and control unit should intervene immediately to provide backup control strategies to ensure vehicle safety. The redundant sensor unit is used to design key sensors and processing units as redundant configurations to prevent single point failures from causing system failure. The system self-check unit is used to regularly check the working status of sensors and processing units to ensure the normal operation of the system. The data verification and validation unit is used to regularly verify sensor data to ensure the accuracy and reliability of the data. In addition, the cockpit display system should promptly provide feedback to the driver on the current skidding status and measures taken through the user interface feedback strategy, so that the driver can understand the vehicle status and take over control when necessary. It is also possible to provide a remote monitoring interface for the safety officer through the remote monitoring strategy, so that the safety officer can understand the vehicle status and road conditions in real time even if he is not in the car. It is also possible to use the through-hole emergency intervention strategy to allow the safety officer to remotely control the vehicle when necessary. Through these strategies, the vehicle control module can respond quickly and effectively to different skidding situations, thereby improving the driving safety of the vehicle in rainy and snowy weather.

[0082] Figure 4 A schematic diagram of a vehicle route selection device based on a mine scene provided by an embodiment of the present disclosure is shown in FIG. Figure 4 As shown, the device of this embodiment may include: The data acquisition module 210 is used to acquire the road surface image of the mine scene to be tested through the image acquisition sensor on the target mine car, and acquire the road surface temperature information of the mine scene to be tested through the temperature acquisition sensor on the target mine car; A road surface state information determination module 220, configured to determine road surface state information based on the road surface image and the road surface temperature information; The route selection module 230 is used to obtain a target driving route of the target mining vehicle based on the road surface state information by using a route planning algorithm.

[0083] As an optional embodiment, the road surface state information determination module is specifically used for: Determining road surface roughness based on the road surface image; Based on the road surface roughness and the road surface temperature information, road surface state information is determined.

[0084] As an optional embodiment, the device further includes a skidding risk detection module, which is used to: Acquire a real-time friction coefficient between the target mine car and the road surface through a road surface condition sensor on the target mine car; Based on the road surface image, the road surface temperature information and the real-time friction coefficient, skidding risk information is determined.

[0085] As an optional embodiment, the skid risk detection module is specifically used for: If a skidding risk is detected based on the road surface state information, the road surface roughness, the road surface temperature information and the real-time friction coefficient are input into a pre-trained skidding risk prediction model to obtain a skidding risk coefficient output by the skidding risk prediction model.

[0086] As an optional embodiment, when the skidding risk detection module detects the existence of the skidding risk based on the road surface state information, it is specifically used to: According to the road surface state information and the tire model of the target mine car, query the anti-skid coefficient corresponding to the target mine car; If the anti-skid coefficient is greater than the real-time friction coefficient, it is determined that there is a risk of skidding.

[0087] As an optional embodiment, when the road surface state information determination module determines the road surface roughness based on the road surface image, it is specifically used to: grayscale the road surface image to obtain a grayscale image corresponding to the road surface image; Performing two-dimensional sampling on the grayscale image to obtain at least two two-dimensional sampling points; Based on the grayscale image and the at least two two-dimensional sampling points, obtaining a three-dimensional grid image corresponding to the road surface image; Based on the three-dimensional grid image, a road surface roughness corresponding to the road surface image is calculated.

[0088] As an optional embodiment, the device further includes a skidding risk level determination module, which is used to: If the skidding risk coefficient is less than a first threshold value, determining the skidding risk level as slight skidding; If the skidding risk coefficient is not less than the first threshold value and less than the second threshold value, the skidding risk level is determined to be moderate skidding; Otherwise, the skidding risk level is determined to be severe skidding.

[0089] As an optional embodiment, the device further includes a slip control module, which is used to: Based on the skidding risk level, determining a vehicle control strategy corresponding to the skidding risk level; The vehicle control strategy is sent to a vehicle control module so that the vehicle control module executes the vehicle control strategy on the target mining vehicle.

[0090] As an optional embodiment, each sensor on the target mine car is arranged on the target mine car based on a target arrangement; The target sensor arrangement is determined based on the following steps: Determine an initial arrangement; the initial arrangement includes position information corresponding to a plurality of sensors; Based on deep reinforcement learning, the initial arrangement is adjusted at least once until a preset condition is satisfied, and the initial arrangement that satisfies the preset condition is used as a target arrangement; The preset condition includes that the sensor arrangement performance index is maximum.

[0091] The device of the embodiment of the present disclosure can execute the method provided by the embodiment of the present disclosure, and its implementation principle is similar and has corresponding technical effects. The actions performed by each module in the device of each embodiment of the present disclosure correspond to the steps in the method of each embodiment of the present disclosure. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0092] In the embodiments of the present disclosure, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0093] In an embodiment of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, and the processor executes the above-mentioned computer program to implement the steps of the method provided by any optional embodiment of the present disclosure. Compared with the prior art, it can be achieved that: by setting a plurality of different types of sensors on the target mine car, obtaining road surface images and road surface temperature information, fusing the data of different sensors, and analyzing the road surface state information in combination with multiple dimensions such as road surface characteristics and road surface temperature, the accuracy of the road surface state information is improved; a route planning algorithm is used to select the route of the target mine car based on the road surface state information to obtain the optimal target driving route, fully considering the skidding risks caused by different road surface conditions, avoiding driving to areas with higher skidding risks, making the selected target driving route safer, and improving the safety of vehicle driving. At the same time, it can also avoid the interruption of vehicle driving caused by road slippage, improve the continuity of vehicle driving, and improve the working efficiency of the target mine car.

[0094] In an alternative embodiment, an electronic device is provided, such as Figure 5 As shown, Figure 5 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present disclosure.

[0095] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0096] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0097] The memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation herein.

[0098] The memory 4003 is used to store the computer program for executing the embodiment of the present disclosure, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the computer program stored in the memory 4003 to implement the steps shown in the above method embodiment.

[0099] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable devices, etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0100] An embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0101] The embodiments of the present disclosure also provide a computer program product, including a computer program, which can implement the steps and corresponding contents of the aforementioned method embodiments when executed by a processor.

[0102] It should be understood that, although the flowchart of the embodiment of the present disclosure indicates each operation step by arrows, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated herein, in some implementation scenarios of the embodiment of the present disclosure, the implementation steps in each flowchart can be executed in other orders according to demand. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on the actual implementation scenario. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage in these sub-steps or stages can also be executed at different times. In scenarios with different execution times, the execution order of these sub-steps or stages can be flexibly configured according to demand, and the embodiment of the present disclosure does not limit this.

[0103] The above is only an optional implementation method for some implementation scenarios of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the scheme of the present disclosure, other similar implementation methods based on the technical ideas of the present disclosure are also within the protection scope of the embodiments of the present disclosure.

Claims

1. A vehicle route selection method based on a mine scene, characterized in that: include: Acquire a road surface image of the mine scene to be tested through an image acquisition sensor on the target mine car, and acquire road surface temperature information of the mine scene to be tested through a temperature acquisition sensor on the target mine car; Determining road surface state information based on the road surface image and the road surface temperature information; A route planning algorithm is used to obtain a target driving route of the target mining vehicle based on the road surface state information.

2. The method according to claim 1, characterized in that The determining of the road surface state information based on the road surface image and the road surface temperature information includes: Determining road surface roughness based on the road surface image; Based on the road surface roughness and the road surface temperature information, road surface state information is determined.

3. The method according to claim 2, characterized in that The method further comprises: Acquire a real-time friction coefficient between the target mine car and the road surface through a road surface condition sensor on the target mine car; Based on the road surface image, the road surface temperature information and the real-time friction coefficient, skidding risk information is determined.

4. The method according to claim 3, characterized in that The determining of skidding risk information based on the road surface image, the road surface temperature information and the real-time friction coefficient includes: If a skidding risk is detected based on the road surface state information, the road surface roughness, the road surface temperature information and the real-time friction coefficient are input into a pre-trained skidding risk prediction model to obtain a skidding risk coefficient output by the skidding risk prediction model.

5. The method according to claim 4, characterized in that The detecting the existence of a skidding risk based on the road surface state information includes: According to the road surface state information and the tire model of the target mine car, query the anti-skid coefficient corresponding to the target mine car; If the anti-skid coefficient is greater than the real-time friction coefficient, it is determined that there is a risk of skidding.

6. The method according to claim 2, characterized in that The determining of the road surface roughness based on the road surface image includes: grayscale the road surface image to obtain a grayscale image corresponding to the road surface image; Performing two-dimensional sampling on the grayscale image to obtain at least two two-dimensional sampling points; Based on the grayscale image and the at least two two-dimensional sampling points, obtaining a three-dimensional grid image corresponding to the road surface image; Based on the three-dimensional grid image, a road surface roughness corresponding to the road surface image is calculated.

7. The method according to claim 4, characterized in that The method further comprises: If the skidding risk coefficient is less than a first threshold value, determining the skidding risk level as slight skidding; If the skidding risk coefficient is not less than the first threshold value and less than the second threshold value, the skidding risk level is determined to be moderate skidding; Otherwise, the skidding risk level is determined to be severe skidding.

8. The method according to claim 7, characterized in that The method further comprises: Based on the skidding risk level, determining a vehicle control strategy corresponding to the skidding risk level; The vehicle control strategy is sent to a vehicle control module so that the vehicle control module executes the vehicle control strategy on the target mining vehicle.

9. The method according to any one of claims 1 to 6, characterized in that: Each sensor on the target mine car is arranged on the target mine car based on a target arrangement; The target sensor arrangement is determined based on the following steps: Determine an initial arrangement; the initial arrangement includes position information corresponding to a plurality of sensors; Based on deep reinforcement learning, the initial arrangement is adjusted at least once until a preset condition is satisfied, and the initial arrangement that satisfies the preset condition is used as a target arrangement; The preset condition includes that the sensor arrangement performance index is maximum.

10. A vehicle route selection device based on a mine scene, characterized in that: include: A data acquisition module, used to acquire a road surface image of the mine scene to be tested through an image acquisition sensor on the target mine car, and to acquire road surface temperature information of the mine scene to be tested through a temperature acquisition sensor on the target mine car; A road surface state information determination module, used to determine road surface state information based on the road surface image and the road surface temperature information; The route selection module is used to obtain the target driving route of the target mining vehicle based on the road surface state information by using a route planning algorithm.

11. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images