Suspension adjusting method, device and equipment in crosswind environment and storage medium

Abstract

The embodiment of the invention provides a suspension adjusting method and device in a crosswind environment, equipment and a storage medium. The method comprises the steps that in the vehicle driving process, visual environment information and vehicle dynamic information are obtained, and the vehicle dynamic information comprises vehicle body deviation information and vehicle position information; determining a current crosswind level based on the visual environment information, the vehicle body deviation information and a pre-trained wind field feature model; obtaining weather forecast information; a crosswind environment prediction result is generated based on the current crosswind level, the weather forecast information and a crosswind database, and the crosswind database is used for storing historical crosswind information; and adjusting suspension parameters of the vehicle according to the crosswind environment prediction result and the vehicle position information. According to the method, the vehicle suspension parameters are adaptively adjusted according to the front crosswind pre-estimation result, and the safety and stability of vehicle driving are improved.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a suspension adjustment method, device, equipment and storage medium in crosswind conditions. Background Technology

[0002] When airflow is disturbed or accelerated, it will exert a significant lateral force on the vehicle, resulting in crosswinds. Crosswinds may cause the vehicle to deviate laterally, tilt, or even lose control due to lateral forces, thus affecting the vehicle's driving safety and stability.

[0003] In existing technologies, vehicle control systems mainly rely on onboard sensors to monitor the vehicle in real time, and then combine control algorithms to adjust the vehicle's dynamic parameters (such as suspension parameters). However, this control method is based on the premise that the vehicle is already in a crosswind environment, which has a certain lag and cannot actively intervene before the crosswind occurs.

[0004] Therefore, there is an urgent need for an active intervention method in crosswind environments, which can improve the driving safety and stability of vehicles in crosswind environments by identifying crosswind scenarios in advance. Summary of the Invention

[0005] The suspension adjustment method, apparatus, equipment, and storage medium provided in this application under crosswind conditions improve vehicle driving safety and stability.

[0006] In a first aspect, embodiments of this application provide a suspension adjustment method under crosswind conditions, comprising: acquiring visual environment information and vehicle dynamic information during vehicle operation, wherein the vehicle dynamic information includes vehicle body offset information and vehicle position information; determining the current crosswind level based on the visual environment information and vehicle body offset information, as well as a pre-trained wind field feature model; acquiring weather forecast information; generating a crosswind environment prediction result based on the current crosswind level, weather forecast information, and a crosswind database, wherein the crosswind database is used to store historical crosswind information; and adjusting the vehicle's suspension parameters according to the crosswind environment prediction result and vehicle position information.

[0007] In one possible implementation, the crosswind environment prediction results include: predicted crosswind occurrence sections and predicted crosswind levels. The above-mentioned adjustment of vehicle suspension parameters based on crosswind environment prediction results and vehicle location information includes: adjusting vehicle suspension parameters based on predicted crosswind levels before the vehicle travels to the predicted crosswind occurrence section, taking into account vehicle location information.

[0008] In one possible implementation, the vehicle's suspension parameters are adjusted based on the predicted crosswind level, including: determining the target damping force corresponding to the predicted crosswind level according to a preset mapping relationship between crosswind level and damping force; and generating and sending a damping force adjustment command to the suspension control system based on the target damping force to adjust the vehicle's suspension parameters.

[0009] In one possible implementation, the current crosswind level is determined based on visual environment information, vehicle offset information, and a pre-trained wind field feature model. This includes: performing image processing on the visual environment information to obtain road geometry features and road segment environment information; fusing the road geometry features, road segment environment information, and vehicle offset information to obtain fused features; and modeling the mapping relationship between the fused features and the crosswind level using the wind field feature model to generate the current crosswind level.

[0010] In one possible implementation, the crosswind database includes a crosswind annotation map and a crosswind risk map. The crosswind annotation map stores standard information about road segments, and the crosswind risk map stores crosswind levels. Based on the current crosswind level, weather forecast information, and the crosswind database, a crosswind environment prediction result is generated, including: querying the crosswind level in the crosswind risk map based on vehicle location information to determine the stored crosswind level corresponding to the vehicle location information; performing a weighted fusion of the current crosswind level and the stored crosswind level to obtain a fused crosswind level; obtaining the annotation information of each segment of the vehicle's travel route from the crosswind annotation map; and generating a crosswind environment prediction result based on the fused crosswind level, combined with wind speed and direction data from the weather forecast information and the annotation information of each segment of the vehicle's travel route.

[0011] In one possible implementation, before generating a crosswind environment prediction result based on the current crosswind level, meteorological forecast information, and a crosswind database, the method further includes: acquiring a base map of the target area and first vehicle driving data of multiple vehicles; based on the first vehicle driving data, identifying road segments in the base map whose crosswind frequency reaches a preset threshold as crosswind-prone road segments, and determining the crosswind labeling level of the crosswind-prone road segments; extracting characteristic information of the crosswind-prone road segments to form a target feature set; comparing and analyzing the target feature set with the feature information of other road segments in the base map to determine the crosswind labeling level of other road segments; and labeling the base map based on the crosswind labeling level and other labeling information to obtain a crosswind-labeled map, wherein the other labeling information includes at least one of: road segment location information, road segment type, and road attributes.

[0012] In one possible implementation, before generating a crosswind environment prediction result based on the current crosswind level, meteorological forecast information, and crosswind database, the method further includes: acquiring second vehicle driving data of multiple vehicles on different target road segments; for any target road segment among the different target road segments, extracting the crosswind situation information of the target road segment from the second vehicle driving data of the target road segment, the crosswind situation information including the presence of crosswinds on the target road segment and the crosswind level when crosswinds are present; constructing the correlation between the road segment location information and the crosswind situation information of the target road segment; and obtaining a crosswind risk map based on the correlation between the road segment location information and the crosswind situation information of different target road segments.

[0013] Secondly, embodiments of this application provide a suspension adjustment device for crosswind environments, comprising: an on-board acquisition module, used to acquire visual environment information and vehicle dynamic information during vehicle operation, the vehicle dynamic information including vehicle body offset information and vehicle position information; a processing module, used to determine the current crosswind level based on the visual environment information, vehicle body offset information, and a pre-trained wind field feature model; a meteorological acquisition module, used to acquire meteorological forecast information; a prediction module, used to generate a crosswind environment prediction result based on the current crosswind level, meteorological forecast information, and a crosswind database, the crosswind database being used to store historical crosswind information; and an adjustment module, used to adjust the vehicle's suspension parameters according to the crosswind environment prediction result and vehicle position information.

[0014] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0016] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0017] The suspension adjustment method, device, equipment, and storage medium provided in this application for crosswind environments acquire visual environment information and vehicle dynamic information during vehicle operation. Based on the visual environment information, vehicle body offset information, and a pre-trained wind field feature model, the current crosswind level is accurately determined. Furthermore, crosswind modeling is completed by combining the current crosswind level, weather forecast information, and a crosswind database storing historical crosswind information. Multi-dimensional data complements and supplements the input features, significantly improving the accuracy and precision of crosswind environment prediction results. Then, using this accurate crosswind environment prediction result and vehicle position information, the vehicle's suspension parameters are specifically adjusted before the vehicle enters the crosswind area. This truly achieves proactive prediction of key parameters such as crosswind level and impact, and proactive intervention before crosswinds occur. It effectively optimizes the vehicle's driving stability in crosswind scenarios, avoiding the risk of lateral deviation, body roll, or even loss of control due to lateral forces, and significantly improves the safety and stability of vehicle operation. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] Figure 1 A schematic diagram illustrating a scenario where a vehicle is subjected to crosswinds, provided as an embodiment of this application;

[0020] Figure 2 A flowchart illustrating a suspension adjustment method under crosswind conditions provided in this application embodiment. Figure 1 ;

[0021] Figure 3 A flowchart illustrating a suspension adjustment method under crosswind conditions provided in this application embodiment. Figure 2 ;

[0022] Figure 4 A schematic diagram illustrating a suspension adjustment method under crosswind conditions provided in an embodiment of this application;

[0023] Figure 5 This is a schematic diagram of the structure of a suspension adjustment device in a crosswind environment provided in an embodiment of this application;

[0024] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0025] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0026] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0027] "Multiple" refers to two or more, and other quantifiers are similar. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following objects have an "or" relationship.

[0028] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, products, or apparatus.

[0029] It should be noted that, in the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0030] First, let me explain the terms used in this application:

[0031] Crosswind: refers to the natural airflow blowing perpendicular to the direction of the vehicle body.

[0032] Figure 1 This is a schematic diagram illustrating a scenario where a vehicle is subjected to crosswinds, as provided in an embodiment of this application. Figure 1 As shown, when airflow passes through open road sections or areas of abrupt terrain changes, it generates a lateral force perpendicular to the vehicle's trajectory; this force is called crosswind force (e.g., ...). Figure 1As shown by the middle arrow, the vehicle will be directly affected by this lateral force during its movement.

[0033] Crosswinds are commonly found in open areas or areas with abrupt changes in terrain, such as bridges, tunnel entrances, valleys, and seashores. Their formation is due to multiple factors, including the wind gap effect, the pressure gradient force, and the lack of airflow shielding. Because crosswinds are characterized by their sudden onset and unstable speed, vehicles encountering crosswinds are highly susceptible to lateral deviation, body roll, or even loss of control due to lateral forces, thus affecting the safety and stability of vehicle operation.

[0034] In existing technologies, vehicle crosswind response control systems primarily rely on onboard sensors to monitor the vehicle's driving status in real time. Control strategies are only triggered and dynamic parameters adjusted when the sensors detect the vehicle is in a crosswind environment and its posture becomes abnormal. This passive response mode has a certain lag, failing to proactively predict and intervene before the vehicle enters a crosswind area. This leads to problems such as decreased driving stability and a sudden increase in driver workload in the initial stages of entering a crosswind zone.

[0035] Based on this, this application provides a suspension adjustment method for crosswind environments. By integrating visual environmental information, vehicle dynamic information, weather forecast information, and crosswind database, a crosswind environment prediction result is generated. Before entering the crosswind area, the suspension parameters of the vehicle are proactively and adaptively adjusted to optimize the vehicle body support performance and anti-roll capability in advance, thereby reducing the impact of crosswinds on vehicle driving stability from the source, reducing the driver's operating load, and ensuring driving safety and comfort.

[0036] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0037] Figure 2 A flowchart illustrating a suspension adjustment method under crosswind conditions provided in this application embodiment. Figure 1 ,like Figure 2 As shown, the method includes:

[0038] Step S201: During vehicle operation, visual environment information and vehicle dynamic information are acquired. The vehicle dynamic information includes vehicle body offset information and vehicle position information.

[0039] The visual environment information refers to the surrounding environment image data acquired through an onboard vision unit, which may include, for example, roads, traffic signs, buildings, and obstacles. The onboard vision unit can be, for example, an onboard camera. Image processing algorithms can be used to process the image data of the foreground and surrounding environment to obtain visual environment information such as roads, traffic signs, buildings, and obstacles. Image processing algorithms may include, for example, edge detection, feature extraction, and object recognition.

[0040] Vehicle dynamic information refers to the dynamic data of a vehicle during its driving process obtained through onboard sensors, including vehicle offset information and vehicle position information.

[0041] Vehicle offset information refers to data caused by crosswinds, such as lateral acceleration and angular velocity, which can be obtained through an inertial measurement unit (IMU).

[0042] Vehicle location information refers to the vehicle's geographic coordinates, which can be obtained through the Global Positioning System (GPS).

[0043] In this step, visual environment information and vehicle dynamic information are acquired through an onboard acquisition module while the vehicle is in motion. The onboard acquisition module can be, for example, an onboard camera, IMU, GPS, etc.

[0044] For example, the vehicle is equipped with multiple high-resolution cameras, covering a 360-degree field of view. During vehicle operation, the onboard cameras continuously monitor the environment ahead and around the vehicle, collecting image data of the surrounding environment. Image processing algorithms are then used to process this data, obtaining visual environmental information such as roads, traffic signs, buildings, and obstacles. Lateral acceleration and angular velocity are acquired via an IMU to determine if the vehicle has deviated, providing vehicle deviation information. Finally, GPS is used to obtain the vehicle's position information.

[0045] Step S202: Based on visual environment information, vehicle offset information, and a pre-trained wind field feature model, determine the current crosswind level.

[0046] Among them, the wind field feature model refers to a model trained by machine learning algorithms based on historical crosswind data. It is used to establish the mapping relationship between visual environment information and vehicle offset information and crosswind level. Machine learning algorithms can be, for example, random forests, neural networks, etc.

[0047] Based on visual environment information and vehicle offset information, a wind field feature model is established using machine learning algorithms to monitor the impact of crosswinds on vehicles in real time. The impact of crosswinds on vehicles is predicted based on different visual images and expressed in the form of crosswind level.

[0048] For example, features such as road width, building density, and lateral acceleration can be input into a wind field feature model trained based on a random forest model to determine the current crosswind level.

[0049] Step S203: Obtain weather forecast information.

[0050] Weather forecast information refers to real-time or predicted meteorological data, such as wind speed and direction. Weather forecast information can be obtained through external interfaces, vehicle-mounted weather sensors, digital broadcasting, and other methods.

[0051] In this step, real-time or predicted weather forecast information such as wind speed and direction is obtained for the current road segment and subsequent road segments.

[0052] For example, the application programming interface (API) for weather forecasts can be called to obtain weather forecast information such as wind speed and wind direction for the current road segment and subsequent road segments.

[0053] Step S204: Based on the current crosswind level, meteorological forecast information, and crosswind database, generate crosswind environment prediction results.

[0054] The crosswind database is used to store historical crosswind information. For example, the crosswind database could be data annotated with the historical impact of crosswinds on various road sections, or it could be map data annotated with the characteristic information of each road section.

[0055] Crosswind environment prediction results refer to the prediction output generated by combining the current crosswind level, meteorological forecast information and crosswind database. It can include the predicted crosswind road section and the predicted crosswind level, and can also include the time period when the crosswind occurs. For example, it is predicted that there is a medium level crosswind in the section of bridge A that the vehicle is about to enter; it is predicted that the vehicle will enter the crosswind environment during the time period [t1, t2], and the level of the crosswind is low level.

[0056] In this step, the crosswind database is queried to obtain the historical crosswind information of the current road segment and subsequent road segments. The current crosswind level, weather forecast information and historical crosswind information of each road segment are fused by a rule engine or neural network to predict the crosswind environment and generate crosswind environment prediction results.

[0057] By supplementing the input features with a crosswind database, the accuracy of the generated crosswind environment prediction results is improved, and proactive prediction of the crosswind environment is achieved.

[0058] Step S205: Adjust the vehicle's suspension parameters based on the crosswind environment prediction results and vehicle location information.

[0059] Suspension parameters refer to parameters that affect the performance of a vehicle's suspension system and the vehicle's ride comfort. These parameters can include damping force and hydraulic pressure, and are used to optimize vehicle stability.

[0060] Based on the crosswind environment forecast results and combined with vehicle location information, the vehicle's suspension parameters, such as damping force and hydraulic pressure, are adjusted before the vehicle enters the predicted crosswind section or before the crosswind occurs. This optimizes vehicle stability and allows for proactive intervention before the crosswind occurs, preventing lateral deviation, body roll, or even loss of control due to lateral forces, thereby improving vehicle driving safety and stability.

[0061] For example, damping force can be added before a vehicle enters a section of road with predicted crosswinds of high meteorological satellite winds to optimize vehicle stability.

[0062] This application provides a suspension adjustment method for crosswind environments. During vehicle operation, visual environment information and vehicle dynamic information are acquired. Based on the visual environment information, vehicle body offset information, and a pre-trained wind field feature model, the current crosswind level is accurately determined. Furthermore, crosswind modeling is completed by combining the current crosswind level, weather forecast information, and a crosswind database storing historical crosswind information. Multi-dimensional data complements and supplements the input features, significantly improving the accuracy and precision of crosswind environment prediction results. Then, using this accurate crosswind environment prediction result and vehicle position information, the vehicle's suspension parameters are specifically adjusted before the vehicle enters the crosswind area. This truly achieves proactive prediction of key parameters such as crosswind level and impact, and proactive intervention before crosswinds occur. This effectively optimizes the vehicle's driving stability in crosswind scenarios, avoiding the risk of lateral deviation, body roll, or even loss of control due to lateral forces, and significantly improving the safety and stability of vehicle operation.

[0063] Figure 3 A flowchart illustrating a suspension adjustment method under crosswind conditions provided in this application embodiment. Figure 2 In this embodiment Figure 2 Based on the embodiments, a suspension adjustment method under crosswind conditions is described in detail. In this embodiment, the crosswind database includes a crosswind labeling map and a crosswind risk map. The crosswind labeling map is used to store standard information of road sections, and the crosswind risk map is used to store crosswind levels. The crosswind environment prediction results include: predicted road sections where crosswinds will occur and predicted crosswind levels.

[0064] like Figure 3 As shown, the method includes:

[0065] Step S301: During vehicle operation, visual environment information and vehicle dynamic information are acquired. The vehicle dynamic information includes vehicle body offset information and vehicle position information.

[0066] Step S301 is similar to step S201, and will not be described again here.

[0067] Step S302: Perform image processing on the visual environment information to obtain road geometric features and road segment environment information.

[0068] Among them, road geometric features refer to the geometric elements of a road, such as the number of lanes, width, straight sections, circular curve sections, longitudinal slope, etc.

[0069] Road segment environmental information refers to the environment surrounding the road segment, such as buildings, mountains, obstacles, etc.

[0070] In this step, image processing algorithms such as edge detection, feature extraction, and object recognition are used to process the visual environment information to obtain road geometric features such as the number and width of lanes, as well as road segment environmental information such as traffic signs, buildings, and obstacles.

[0071] For example, image processing is performed on the visual environment information of road segment A to determine that road segment A is an elevated road, uphill, with office buildings on the left and an old residential area on the right.

[0072] Step S303: The road geometric features, road segment environmental information and vehicle offset information are fused to obtain fused features.

[0073] Fusion processing refers to associating and combining different types of data. Fusion processing can be early-stage fusion or mid-stage fusion.

[0074] Data-level stitching can be performed on road geometry features, road segment environmental information, and vehicle offset information to obtain fused features. Alternatively, feature-level fusion can be performed on road geometry features, road segment environmental information, and vehicle offset information, for example, through weighted fusion using an attention mechanism to obtain fused features.

[0075] Step S304: Model the mapping relationship between the fused features and the crosswind level using the wind field feature model to generate the current crosswind level.

[0076] In this step, the fused features are input into the wind field feature model, and the mapping relationship between the fused features and the crosswind level is modeled by machine learning algorithms to generate the current crosswind level.

[0077] For example, the current crosswind level can be determined by the voting results of multiple decision trees in a random forest.

[0078] By fusing multiple features and inputting them into the wind field feature model, the generalization ability of the model is improved.

[0079] Step S305: Obtain weather forecast information.

[0080] Step S305 is similar to step S203, and will not be described again here.

[0081] In one possible implementation, before generating the crosswind environment prediction result, the method further includes: acquiring second vehicle driving data of multiple vehicles on different target road segments; extracting crosswind situation information of any target road segment from the second vehicle driving data of the target road segment; constructing the correlation between the road segment location information and the crosswind situation information of the target road segment; and obtaining a crosswind risk map based on the correlation between the road segment location information and the crosswind situation information of different target road segments.

[0082] The crosswind situation information includes the presence of crosswinds on the target road section and the crosswind intensity when they are present. The road section location information refers to the geographical coordinates of the road section, which can be represented by the road section's GPS data.

[0083] Crosswind risk maps are temporary databases derived from feedback data from other users. For example, crosswind risk maps obtained based on feedback data from other users will differ when there is no wind and when there is wind.

[0084] Second vehicle driving data of multiple vehicles in different target road sections are obtained, and data mining technology is used to extract the crosswind situation information of each target road section. The crosswind situation information of the target road section is correlated with the road section location information to obtain a crosswind risk map.

[0085] For example, the content of the crosswind risk map includes: GPS of section A - crosswind presence and level of section A.

[0086] By constructing a crosswind risk map, the system provides a query tool for crosswind levels on different road sections, thus providing a data foundation for crosswind environment prediction.

[0087] Step S306: Based on the vehicle location information, query the crosswind level in the crosswind risk map to determine the stored crosswind level corresponding to the vehicle location information.

[0088] Among them, the stored crosswind level refers to the crosswind level stored in the crosswind risk map and associated with the road segment location information.

[0089] The crosswind risk map stores the correlation between crosswind situation information and road segment location information. By querying the crosswind risk map based on the road segment location information, the stored crosswind level corresponding to the vehicle's location information can be obtained. This includes retrieving the stored crosswind level corresponding to the current vehicle's location on the road segment, as well as the stored crosswind level corresponding to the road segment the vehicle is about to enter.

[0090] Step S307: Perform a weighted fusion of the current crosswind level and the stored crosswind level to obtain the fused crosswind level.

[0091] Among them, the fused crosswind level refers to the weighted fusion result of the current crosswind level and the stored crosswind level.

[0092] The current crosswind level and the stored crosswind level can be weighted and merged based on the weight coefficients preset by the rule engine to obtain a merged crosswind level. Alternatively, the current crosswind level can be matched with the stored crosswind level based on accuracy to obtain a matching result, and the weight coefficients can be dynamically determined based on the matching result to weightedly merge the current crosswind level and the stored crosswind level to obtain a merged crosswind level.

[0093] In one possible implementation, before generating the crosswind environment prediction result, the method further includes: acquiring a base map of the target area and first vehicle driving data of multiple vehicles; based on the vehicle driving data, identifying road segments in the base map whose crosswind frequency reaches a preset threshold as crosswind-prone road segments, and determining the crosswind labeling level of the crosswind-prone road segments; extracting characteristic information of the crosswind-prone road segments to form a target feature set; comparing and analyzing the target feature set with the feature information of other road segments in the base map to determine the crosswind labeling level of other road segments; and labeling the base map based on the crosswind labeling level and other labeling information to obtain a crosswind-labeled map.

[0094] Other labeling information includes at least one of the following: road segment location information, road segment type, and road attributes.

[0095] The process involves acquiring a base map of the target area, obtaining first-stage vehicle driving data based on field surveys and data provided by users' actual vehicles, and identifying road sections on the base map where the frequency of crosswinds reaches a preset threshold as crosswind-prone road sections. Characteristic information of these crosswind-prone road sections is then extracted, including terrain, building distribution, and wind tunnel effects, resulting in a target feature set. This target feature set is compared and analyzed with the feature information of other road sections on the base map; for example, a weighted cosine similarity algorithm can be used to determine the crosswind labeling level of other road sections. Based on the crosswind labeling level and other labeling information, the base map is annotated to obtain a crosswind-labeled map. This crosswind-labeled map provides information on road sections susceptible to crosswinds.

[0096] For example, a crosswind-marked map includes the following information: road segment GPS, road segment type (urban road, highway, etc.), crosswind marking level (low, medium, high), and related road attributes (such as width, roadside obstacles, and openness).

[0097] The crosswind-marked map provides information on road sections susceptible to crosswinds, improving the accuracy of crosswind environment prediction results.

[0098] Optionally, the crosswind marking map and crosswind risk map can be continuously updated and improved based on vehicle driving data.

[0099] Step S308: Obtain the marking information of each section of the road the vehicle travels from the crosswind marking map.

[0100] The road segment in question includes the current road segment the vehicle is traveling on and the road segment it is about to enter.

[0101] Obtain the marking information of the current road segment and the road segment that the vehicle is about to enter from the crosswind-marked map.

[0102] Step S309: Based on the fused crosswind level, and combined with the wind speed and direction data in the meteorological forecast information and the various marking information of the vehicle driving section, generate the crosswind environment prediction result.

[0103] Based on the fusion of crosswind levels, combined with wind speed and direction data from meteorological forecasts and various markings on vehicle driving sections, the above information is weighted and fused, and combined with machine learning models (such as neural network models, transform models, etc.) to generate crosswind environment prediction results, thereby improving the comprehensiveness of crosswind environment prediction.

[0104] For example, at the bridge exit section, more accurate prediction results can be generated by combining the various marking information of the bridge exit section with real-time wind speed and wind direction data.

[0105] Step S310: Combining vehicle location information, before the vehicle travels to the section of road where the predicted crosswind is expected, determine the target damping force corresponding to the predicted crosswind level based on the preset mapping relationship between crosswind level and damping force.

[0106] The mapping relationship between crosswind level and damping force refers to the damping force setting value corresponding to different crosswind levels. For example, a high crosswind level corresponds to a high damping force. For instance, when the crosswind level is "high", the target damping force is set to 500 N·s / m.

[0107] In this step, based on the vehicle's location information, before the vehicle travels to the section of road where the predicted crosswind is expected, the target damping force corresponding to the predicted crosswind level is determined according to the damping force setting value corresponding to different crosswind levels.

[0108] By combining vehicle location information, vehicle stability was enhanced before crosswinds occurred.

[0109] Step S311: Based on the target damping force, generate and send a damping force adjustment command to the suspension control system to adjust the vehicle's suspension parameters.

[0110] The suspension control system refers to the module that performs damping force adjustment, such as a solenoid valve, oil pump, or damper. For example, the solenoid valve adjusts the opening of the damper's oil circuit according to instructions, thereby changing the damping force.

[0111] Based on the target damping force, a damping force adjustment command is generated and sent to the suspension control system. After receiving the damping force adjustment command, the suspension control system executes the damping force adjustment command, thereby adjusting the vehicle's suspension parameters.

[0112] By mapping the crosswind level to the damping force, the suspension parameters were dynamically optimized.

[0113] Optionally, a virtual crosswind scenario can be generated before sending the damping force adjustment command to the suspension control system to verify the feasibility of the damping force adjustment command through simulation.

[0114] Figure 4 This application provides a schematic diagram of a suspension adjustment method in a crosswind environment, as illustrated in the embodiments of this application. Figure 4 As shown, through data collection, the driving data of the first vehicle, the driving data of the second vehicle, and historical crosswind information were obtained. A crosswind labeling map and a crosswind risk map were constructed using the first and second vehicle driving data. A wind field characteristic model was obtained by training the model using historical crosswind information.

[0115] When the vehicle is in motion, the onboard acquisition module obtains visual environment information, vehicle offset information, and vehicle position information. The visual environment information and vehicle offset information are input into the wind field feature model to obtain the current crosswind level. Based on the current crosswind level, combined with the weather forecast information obtained by the meteorological acquisition module, and the stored crosswind level and various annotation information in the crosswind annotation map, such as crosswind-prone location information, a crosswind environment prediction is performed to obtain the crosswind environment prediction result. The crosswind environment prediction result is then sent to the vehicle so that the vehicle can proactively adjust its suspension parameters before driving into crosswind sections to ensure driving stability and safety.

[0116] This application provides a suspension adjustment method under crosswind conditions. During vehicle operation, visual environment information and vehicle dynamic information are acquired. Features are extracted from the visual environment information to obtain road geometry and road segment environmental information, which are then fused with vehicle offset information to obtain fused features. A wind field feature model is used to model the mapping relationship between the fused features and the crosswind level, generating the current crosswind level. Weather forecast information is acquired, and crosswind environment prediction is performed by combining the current crosswind level, weather forecast information, crosswind risk map, and data stored in the crosswind annotation map. The crosswind environment prediction result is obtained. Combined with vehicle location information, before the vehicle reaches the predicted crosswind section, a target damping force corresponding to the predicted crosswind level is determined based on a preset mapping relationship between crosswind level and damping force. Based on the target damping force, a damping force adjustment command is generated and sent to the suspension control system to adjust the vehicle's suspension parameters. By fusing multiple features, the accuracy of crosswind environment prediction results is improved, and the prediction precision is enhanced. Suspension parameters are adjusted in advance based on the prediction results to optimize vehicle stability before crosswinds occur. Active intervention is carried out before crosswinds occur to avoid lateral deviation, body roll, or even loss of control of the vehicle due to lateral forces, thereby improving vehicle driving safety and stability.

[0117] Figure 5 This is a schematic diagram of a suspension adjustment device in a crosswind environment provided in an embodiment of this application, as shown below. Figure 5 As shown, the suspension adjustment device 50 in crosswind conditions provided in this embodiment includes: an on-board acquisition module 501, which acquires visual environment information and vehicle dynamic information during vehicle operation, including vehicle body offset information and vehicle position information; a processing module 502, which determines the current crosswind level based on the visual environment information, vehicle body offset information, and a pre-trained wind field feature model; a meteorological acquisition module 503, which acquires meteorological forecast information; a prediction module 504, which generates a crosswind environment prediction result based on the current crosswind level, meteorological forecast information, and a crosswind database, the crosswind database being used to store historical crosswind information; and an adjustment module 505, which adjusts the vehicle's suspension parameters according to the crosswind environment prediction result and vehicle position information.

[0118] In one possible implementation, the crosswind environment prediction results include: predicted crosswind occurrence sections and predicted crosswind levels. The adjustment module 505 is also used to combine vehicle location information to adjust the vehicle's suspension parameters based on the predicted crosswind level before the vehicle travels to the predicted crosswind occurrence section.

[0119] In one possible implementation, the adjustment module 505 is further configured to determine the target damping force corresponding to the predicted crosswind level based on a preset crosswind level and damping force mapping relationship; and based on the target damping force, generate and send a damping force adjustment command to the suspension control system to adjust the vehicle's suspension parameters.

[0120] In one possible implementation, the processing module 502 is further configured to perform image processing on the visual environment information to obtain road geometric features and road segment environment information; perform fusion processing on the road geometric features, road segment environment information and vehicle offset information to obtain fused features; and model the mapping relationship between the fused features and the crosswind level through the wind field feature model to generate the current crosswind level.

[0121] In one possible implementation, the crosswind database includes a crosswind labeling map and a crosswind risk map. The crosswind labeling map stores standard information about road sections, while the crosswind risk map stores crosswind levels.

[0122] In one possible implementation, the prediction module 504 is further configured to query the crosswind level in the crosswind risk map based on the vehicle location information to determine the stored crosswind level corresponding to the vehicle location information; perform weighted fusion of the current crosswind level and the stored crosswind level to obtain the fused crosswind level; obtain the annotation information of each segment of the vehicle's travel route from the crosswind annotation map; and generate a crosswind environment prediction result based on the fused crosswind level and combined with the wind speed and wind direction data in the meteorological forecast information and the annotation information of each segment of the vehicle's travel route.

[0123] In one possible implementation, the prediction module 504 is further configured to acquire a base map of the target area and first vehicle driving data of multiple vehicles; based on the first vehicle driving data, identify road segments in the base map whose crosswind frequency reaches a preset threshold as crosswind-prone road segments, and determine the crosswind labeling level of the crosswind-prone road segments; extract characteristic information of the crosswind-prone road segments to form a target feature set; compare and analyze the target feature set with the feature information of other road segments in the base map to determine the crosswind labeling level of other road segments; and label the base map based on the crosswind labeling level and other labeling information to obtain a crosswind-labeled map, wherein the other labeling information includes at least one of the following: road segment location information, road segment type, and road attribute.

[0124] In one possible implementation, the prediction module 504 is further configured to acquire second vehicle driving data of multiple vehicles on different target road segments; for any target road segment, extract crosswind situation information of the target road segment from the second vehicle driving data of the target road segment, the crosswind situation information including the presence of crosswinds on the target road segment and the crosswind level when crosswinds are present; construct the correlation between the road segment location information and the crosswind situation information of the target road segment; and obtain a crosswind risk map based on the correlation between the road segment location information and the crosswind situation information of different target road segments.

[0125] This embodiment provides a suspension adjustment device for crosswind environments, which can perform the method provided in the above-described method embodiments. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0126] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 60 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the device 60 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0127] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to perform the above-described method.

[0128] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0129] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0130] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0131] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0132] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0133] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0134] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0135] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0136] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0137] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0138] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0139] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0140] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0141] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A suspension adjustment method under crosswind conditions, characterized in that, include: During vehicle operation, visual environment information and vehicle dynamic information are acquired, including vehicle body offset information and vehicle position information. Based on the visual environment information and vehicle offset information, as well as the pre-trained wind field feature model, the current crosswind level is determined; Obtain weather forecast information; Based on the current crosswind level, the meteorological forecast information, and the crosswind database, a crosswind environment prediction result is generated. The crosswind database is used to store historical crosswind information. Based on the crosswind environment prediction results and vehicle location information, the vehicle's suspension parameters are adjusted.

2. The method according to claim 1, characterized in that, The crosswind environment prediction results include: predicted road sections where crosswinds will occur and predicted crosswind levels. Adjusting the vehicle's suspension parameters based on the crosswind environment prediction results and vehicle location information includes: Based on the vehicle's location information, the vehicle's suspension parameters are adjusted according to the predicted crosswind level before the vehicle travels to the section of road where the crosswind is predicted.

3. The method according to claim 2, characterized in that, The adjustment of the vehicle's suspension parameters based on the predicted crosswind level includes: Based on the preset mapping relationship between crosswind level and damping force, the target damping force corresponding to the predicted crosswind level is determined. Based on the target damping force, a damping force adjustment command is generated and sent to the suspension control system to adjust the vehicle's suspension parameters.

4. The method according to any one of claims 1-3, characterized in that, The determination of the current crosswind level based on the visual environment information, vehicle offset information, and a pre-trained wind field feature model includes: Image processing is performed on the visual environment information to obtain road geometric features and road segment environment information; The road geometric features, road segment environmental information, and vehicle offset information are fused to obtain fused features; The mapping relationship between the fused features and the crosswind level is modeled using the wind field feature model to generate the current crosswind level.

5. The method according to any one of claims 1-3, characterized in that, The crosswind database includes a crosswind labeling map and a crosswind risk map. The crosswind labeling map stores standard information about road sections, and the crosswind risk map stores crosswind levels. The process of generating crosswind environment prediction results based on the current crosswind level, the meteorological forecast information, and the crosswind database includes: Based on the vehicle location information, the crosswind level is queried in the crosswind risk map to determine the stored crosswind level corresponding to the vehicle location information. The current crosswind level and the stored crosswind level are weighted and fused to obtain the fused crosswind level; Obtain the marking information of each section of the vehicle's route from the crosswind marking map; Based on the fused crosswind level, and combined with the wind speed and direction data in the meteorological forecast information and the various marking information of the vehicle driving section, a crosswind environment prediction result is generated.

6. The method according to claim 5, characterized in that, Before generating the crosswind environment prediction result based on the current crosswind level, the meteorological forecast information, and the crosswind database, the method further includes: Obtain the base map of the target area and the first vehicle driving data of multiple vehicles; Based on the first vehicle driving data, from each road segment in the base map, the road segment where the frequency of crosswinds reaches a preset threshold is identified as a crosswind-prone road segment, and the crosswind labeling level of the crosswind-prone road segment is determined. Extract the characteristic information of the road sections prone to crosswinds to form a target feature set; The target feature set is compared and analyzed with the feature information of other road segments in the base map to determine the crosswind labeling level of the other road segments; Based on the crosswind rating and other annotation information, the base map is annotated to obtain a crosswind-annotated map. The other annotation information includes at least one of the following: road segment location information, road segment type, and road attribute.

7. The method according to claim 5, characterized in that, Before generating the crosswind environment prediction result based on the current crosswind level, the meteorological forecast information, and the crosswind database, the method further includes: Acquire second vehicle driving data for multiple vehicles on different target road segments; For any one of the different target road segments, the crosswind situation information of the target road segment is extracted from the second vehicle driving data of the target road segment. The crosswind situation information includes the existence of crosswinds in the target road segment and the crosswind level when crosswinds exist. Construct the correlation between the road segment location information and crosswind situation information of the target road segment; Based on the correlation between the location information of different target road segments and the crosswind situation information, a crosswind risk map is obtained.

8. A suspension adjustment device for crosswind conditions, characterized in that, include: The vehicle-mounted data acquisition module is used to acquire visual environment information and vehicle dynamic information during vehicle operation. The vehicle dynamic information includes vehicle body offset information and vehicle position information. The processing module is used to determine the current crosswind level based on the visual environment information and vehicle offset information, as well as a pre-trained wind field feature model; The weather acquisition module is used to acquire weather forecast information; The prediction module is used to generate crosswind environment prediction results based on the current crosswind level, the meteorological forecast information, and the crosswind database, wherein the crosswind database is used to store historical crosswind information. The adjustment module is used to adjust the suspension parameters of the vehicle based on the crosswind environment prediction results and the vehicle position information.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

11. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images