Vehicle chassis adjusting method and system, electronic equipment and storage medium

Abstract

The invention provides a vehicle chassis adjusting method and system, electronic equipment and a storage medium, and relates to the technical field of vehicle control, and the method comprises the steps that multi-source sensing information used for representing a driving path in front of a vehicle is acquired; performing fusion processing on the navigation information and the radar point cloud data to obtain target road condition information; based on the target road condition information, generating road condition characteristic parameters corresponding to a driving path in front of the vehicle; according to the road condition characteristic parameters, a control instruction used for adjusting a vehicle chassis is generated; and the vehicle chassis is adjusted in response to the control instruction. According to the method, the vehicle chassis can be controlled according to the multi-source fusion data, the chassis adjustment accuracy is improved, and then the vehicle can better adapt to complex and diversified driving environments.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle chassis adjustment method, system, electronic device and storage medium. Background Technology

[0002] With the continuous development of SDV (Software Defined Vehicle) technology, the control logic of vehicle chassis systems is also rapidly evolving towards intelligence, adaptability, and refinement. As a key execution system connecting the vehicle body and the road surface, the chassis's adjustment performance directly affects the vehicle's handling stability and ride comfort. Especially under varying road conditions, the response speed and accuracy of chassis adjustment become important indicators for measuring the dynamic quality of the entire vehicle.

[0003] However, current mainstream chassis control solutions still generally suffer from problems such as reliance on a single data source, static adjustment strategies, and a lack of foresight regarding road conditions, making it difficult to adapt to complex and diverse driving environments.

[0004] Therefore, a new method for adjusting vehicle chassis is urgently needed. Summary of the Invention

[0005] In view of the above problems, embodiments of this application provide a vehicle chassis adjustment method, system, electronic device, and storage medium to overcome or at least partially solve the above problems.

[0006] A first aspect of this application provides a vehicle chassis adjustment method, the method comprising: Acquire multi-source perception information to characterize the driving path in front of the vehicle, the multi-source perception information including at least: navigation information to characterize the driving path in front of the vehicle, and radar point cloud data to characterize obstacle information on the driving path in front of the vehicle. The navigation information and the radar point cloud data are fused to obtain the target road condition information; Based on the target road condition information, road condition feature parameters corresponding to the driving path are generated. The road condition feature parameters are used to characterize the distribution characteristics of the driving path in the road condition feature dimension and obstacle dimension. Based on the road condition characteristic parameters, control commands for adjusting the vehicle chassis are generated; In response to the control command, the vehicle chassis is adjusted.

[0007] Optionally, the step of fusing the navigation information and the radar point cloud data to obtain target road condition information includes: The navigation information and the radar point cloud data are time-stamped and synchronized to obtain the mapping relationship between the navigation information and the radar point cloud data in the time dimension. The navigation information includes any one or more of the following: latitude and longitude data, elevation data and curve curvature radius. The radar point cloud data includes any one or more of the following: obstacle height data and obstacle density data. The navigation information and the radar point cloud data are respectively subjected to coordinate system transformation to obtain the mapping relationship between the navigation information and the radar point cloud data in the spatial dimension; Based on the mapping relationship between the navigation information and the radar point cloud data in the time dimension and in the spatial dimension, the navigation information and the radar point cloud data are fused according to a preset confidence weighting strategy to obtain the target road condition information.

[0008] Optionally, the step of fusing the navigation information and the radar point cloud data according to a preset confidence weighting strategy to obtain the target road condition information includes: Obtain current environmental information and the vehicle's equipment status information; The environmental information, the device status information, the navigation information with a predetermined mapping relationship between time and space dimensions, and the radar point cloud data are input into a pre-trained control model to obtain the confidence level of the radar point cloud data and the confidence level of the navigation information. The confidence level of the radar point cloud data is determined based on the environmental information, and the confidence level of the navigation information is determined based on the device status information. The weights of the radar point cloud data are determined based on the confidence level of the radar point cloud data, and the weights of the navigation information are determined based on the confidence level of the navigation information. Based on the respective weights of the radar point cloud data and the navigation information, the radar point cloud data and the navigation information are weighted and fused to obtain the target road condition information.

[0009] Optionally, generating road condition feature parameters corresponding to the driving path based on the target road condition information includes: The target road condition information is preprocessed to obtain the preprocessed result of the target road condition information; For the preprocessing results, feature value extraction operations are performed in multiple dimensions, including any two or more of the following: road type, path slope, curve curvature, obstacle density, and impact intensity level; By combining the feature values ​​of each dimension, the road condition feature parameters corresponding to the driving path are obtained; The step of generating control commands for adjusting the vehicle chassis based on the road condition characteristic parameters includes: Based on the road type, path gradient, and curve curvature in the road condition characteristic parameters, a first control command for suppressing vehicle vibration is generated. Based on the road type, obstacle density, and impact intensity level in the road condition characteristic parameters, a second control command is generated to adjust the suspension height and damping. Based on the curvature of the curves and the slope of the path in the road condition characteristic parameters, a third control command is generated to adjust the torque distribution of the four-wheel drive system.

[0010] Optionally, the step of generating a second control command for adjusting suspension height and damping based on the road type, obstacle density, and impact intensity level in the road condition characteristic parameters includes: Based on the road type and obstacle density in the road condition characteristic parameters, determine the target height adjustment value and target damping adjustment value for adjusting the suspension height; Based on the impact intensity level in the road condition characteristic parameters, determine the response sensitivity for adjusting suspension height and damping; Based on the target height adjustment value, the target damping adjustment value, and the response sensitivity, an adjustment curve for suspension height and suspension damping is constructed. The adjustment curve for suspension height and suspension damping is a nonlinear gradual function curve. The second control command is generated based on the adjustment curves of the suspension height and suspension damping.

[0011] Optionally, generating control commands for adjusting the vehicle chassis based on the road condition characteristic parameters includes: Obtain the current driving status data of the vehicle, which includes one or more of the following: current vehicle speed, current yaw rate, and current pitch angle; Based on the driving status data, the road condition feature parameters are corrected to obtain the corrected target road condition feature parameters. Based on the target road condition feature parameters and the vehicle's current driving state, a preset rolling time-domain optimization algorithm is used to generate control commands for adjusting the vehicle chassis. The rolling time-domain optimization algorithm represents the control command generation algorithm that enables the vehicle chassis performance indicators to reach the target performance indicators.

[0012] Optionally, after adjusting the vehicle chassis, the method further includes: Monitor the vehicle's body posture change parameters and vertical vibration level parameters to determine the actual response data of adjusting the vehicle's chassis based on the control commands; The actual response data is compared and analyzed with the predictive control results generated based on the road condition feature parameters to determine the control deviation between the actual response data and the predictive control results. The predictive control results are obtained by inputting the road condition feature parameters into a pre-trained control model. Based on the control deviation, the weights of the radar point cloud data and the navigation information are adjusted, as are the model parameters of the control model.

[0013] A second aspect of this application provides a vehicle chassis adjustment system, the system comprising: The acquisition module acquires multi-source perception information for characterizing the driving path in front of the vehicle. The multi-source perception information includes at least: navigation information for characterizing the driving path in front of the vehicle, and radar point cloud data for characterizing obstacle information on the driving path in front of the vehicle. The data fusion processing module is used to fuse the navigation information and the radar point cloud data to obtain target road condition information; The first generation module is used to generate road condition feature parameters corresponding to the driving path based on the target road condition information. The road condition feature parameters are used to characterize the distribution characteristics of the driving path in the road condition feature dimension and the obstacle dimension. The second generation module is used to generate control commands for adjusting the vehicle chassis based on the road condition characteristic parameters. An execution module is used to adjust the vehicle chassis in response to the control command.

[0014] Optionally, the data fusion processing module for fusing the navigation information and the radar point cloud data to obtain target road condition information includes: The timestamp synchronization processing submodule is used to perform timestamp synchronization processing on the navigation information and the radar point cloud data respectively, so as to obtain the mapping relationship between the navigation information and the radar point cloud data in the time dimension. The navigation information includes any one or more of the following: latitude and longitude data, elevation data and curve curvature radius. The radar point cloud data includes any one or more of the following: obstacle height data and obstacle density data. The coordinate system transformation processing submodule is used to perform coordinate system transformation processing on the navigation information and the radar point cloud data respectively, so as to obtain the mapping relationship between the navigation information and the radar point cloud data in the spatial dimension; The fusion processing submodule is used to fuse the navigation information and the radar point cloud data according to the mapping relationship in the time dimension and the mapping relationship in the spatial dimension, and according to a preset confidence weighting strategy to obtain the target road condition information.

[0015] Optionally, the navigation information and the radar point cloud data are fused according to a preset confidence weighting strategy to obtain the target road condition information. The fusion processing submodule includes: The acquisition subunit is used to acquire current environmental information and the vehicle's equipment status information; The confidence level determination subunit is used to input the environmental information, the device status information, and the navigation information and radar point cloud data with the time-dimensional and spatial-dimensional mapping relationships determined into a pre-trained control model to obtain the confidence level of the radar point cloud data and the confidence level of the navigation information. The confidence level of the radar point cloud data is determined based on the environmental information, and the confidence level of the navigation information is determined based on the device status information. The weight determination subunit is used to determine the weight of the radar point cloud data based on the confidence level of the radar point cloud data, and to determine the weight of the navigation information based on the confidence level of the navigation information; The weighted fusion subunit is used to perform weighted fusion of the radar point cloud data and the navigation information according to their respective weights to obtain the target road condition information.

[0016] Optionally, the first generation module, which generates road condition feature parameters corresponding to the driving path based on the target road condition information, includes: The preprocessing submodule is used to preprocess the target road condition information to obtain the preprocessing result of the target road condition information; The execution submodule is used to perform feature value extraction operations in multiple dimensions for the preprocessing results. The feature values ​​in multiple dimensions include any two or more of the following: road type, path slope, curve curvature, obstacle density, and impact intensity level. The combination submodule is used to combine the feature values ​​of each dimension to obtain the road condition feature parameters corresponding to the driving path. The second generation module, which generates control commands for adjusting the vehicle chassis based on the road condition characteristic parameters, includes: The first generation submodule is used to generate a first control command for suppressing vehicle vibration based on the road type, path slope and curve curvature in the road condition feature parameters. The second generation submodule is used to generate a second control command for adjusting the suspension height and damping based on the road type, obstacle density and impact intensity level in the road condition characteristic parameters. The third generation submodule is used to generate a third control command for adjusting the four-wheel drive torque distribution based on the curvature of the curve and the slope of the path in the road condition characteristic parameters.

[0017] Optionally, the second control command for adjusting suspension height and damping is generated based on the road type, obstacle density, and impact intensity level in the road condition characteristic parameters. The second generation submodule includes: The first determining subunit determines the target height adjustment value and the target damping adjustment value for adjusting the suspension height based on the road type and obstacle density in the road condition characteristic parameters. The second determining subunit is used to determine the response sensitivity for adjusting suspension height and damping based on the impact intensity level in the road condition characteristic parameters. A subunit is constructed to build an adjustment curve for suspension height and suspension damping based on the target height adjustment value, the target damping adjustment value, and the response sensitivity. The adjustment curve for suspension height and suspension damping is a nonlinear gradual function curve. A generation subunit is used to generate the second control command based on the adjustment curves of the suspension height and suspension damping.

[0018] Optionally, the step of generating control commands for adjusting the vehicle chassis based on the road condition characteristic parameters includes: The acquisition submodule is used to acquire the current driving status data of the vehicle, which includes one or more of the following: current vehicle speed, current yaw rate and current pitch angle. The correction submodule is used to correct the road condition feature parameters based on the driving status data to obtain the corrected target road condition feature parameters. The rolling time-domain optimization submodule is used to generate control commands for adjusting the vehicle chassis based on the target road condition feature parameters and the current driving state of the vehicle using a preset rolling time-domain optimization algorithm. The rolling time-domain optimization algorithm represents the control command generation algorithm that enables the vehicle chassis performance indicators to reach the target performance indicators.

[0019] Optionally, the system further includes: The monitoring submodule is used to monitor the vehicle's body posture change parameters and vertical vibration level parameters, and determine the actual response data of adjusting the vehicle's chassis based on the control command. The comparative analysis submodule is used to compare and analyze the actual response data with the predictive control results generated based on the road condition feature parameters, and to determine the control deviation between the actual response data and the predictive control results. The predictive control results are obtained by inputting the road condition feature parameters into a pre-trained control model. The adjustment submodule is used to adjust the weights of the radar point cloud data and the navigation information according to the control deviation, and to adjust the model parameters of the control model.

[0020] A third aspect of this application provides an electronic device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the vehicle chassis adjustment method as described in the first aspect of this application.

[0021] A fourth aspect of this application provides a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the vehicle chassis adjustment method as described in the first aspect of this application.

[0022] The beneficial effects of this application are: This application proposes a vehicle chassis adjustment method, comprising: acquiring multi-source perception information characterizing the driving path ahead of the vehicle, the multi-source perception information including at least: navigation information characterizing the driving path and radar point cloud data characterizing obstacle information on the driving path; fusing the navigation information and the radar point cloud data to obtain target road condition information; generating road condition feature parameters corresponding to the driving path based on the target road condition information, the road condition feature parameters characterizing the distribution characteristics of the driving path in the road condition feature dimension and obstacle dimension; generating control commands for adjusting the vehicle chassis according to the road condition feature parameters; and adjusting the vehicle chassis in response to the control commands. This application obtains target road condition information by fusing navigation information and radar point cloud data, determines road condition feature parameters corresponding to the driving path based on the fused target road condition information, and finally generates control commands for adjusting the vehicle chassis based on the road condition feature parameters, thereby achieving control of the vehicle chassis based on multi-source fused data, improving the accuracy of chassis adjustment, and enabling the vehicle to better adapt to complex and diverse driving environments. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic flowchart of a vehicle chassis adjustment method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the overall system architecture of a vehicle chassis adjustment method provided in an embodiment of this application; Figure 3 This is a detailed process flow diagram of a vehicle chassis adjustment method provided in an embodiment of this application; Figure 4 This is a schematic diagram of a vehicle chassis adjustment system provided in an embodiment of this application; Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] Exemplary embodiments of this application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0026] In a first aspect, this application provides a vehicle chassis adjustment method, such as... Figure 1 As shown, the method includes: Step S101: Obtain multi-source perception information for characterizing the driving path in front of the vehicle. The multi-source perception information includes at least: navigation information for characterizing the driving path in front of the vehicle, and radar point cloud data for characterizing obstacle information on the driving path in front of the vehicle.

[0027] In this step, multi-source perception information is acquired to characterize the vehicle's forward driving path. This multi-source perception information includes at least navigation information and radar point cloud data. Navigation information describes the geographical structural features of the vehicle's current and planned forward paths, such as road morphology, elevation changes, and curvature information. Radar point cloud data comes from onboard millimeter-wave radar or lidar sensors and is primarily used to detect obstacles, potholes, protrusions, and other environmental elements on the road surface ahead of the vehicle in real time. By unifying the acquisition of path and environmental information from different data sources, a necessary data foundation is provided for subsequent fusion processing and feature extraction.

[0028] Step S102: The navigation information and the radar point cloud data are fused to obtain target road condition information.

[0029] In this step, the navigation information and the radar point cloud data are fused. Specifically, the two types of information are aligned according to spatial coordinate systems and timestamps to ensure comparability and consistency. Based on this, a pre-defined fusion algorithm is used to weight the two types of information, forming a unified road condition description model, i.e., target road condition information. This fusion process enables complementary collaboration between structured path data and real-time obstacle perception data, helping to enhance the vehicle's ability to identify and adapt to complex road environments.

[0030] Step S103: Based on the target road condition information, generate road condition feature parameters corresponding to the driving path. The road condition feature parameters are used to characterize the distribution characteristics of the driving path in the road condition feature dimension and obstacle dimension.

[0031] In this step, based on the target road condition information, road condition feature parameters corresponding to the vehicle's forward travel path are generated. These road condition feature parameters characterize the state changes of the vehicle's current path and the path within a certain distance ahead in multiple dimensions, including but not limited to: road type (such as paved or unpaved road surface), slope change, road curvature, obstacle distribution density, and impact intensity level. Extracting these feature parameters helps transform complex raw data into structured control input variables for subsequent adjustment strategies.

[0032] Step S104: Generate control commands for adjusting the vehicle chassis based on the road condition characteristic parameters.

[0033] In this step, control commands for adjusting the vehicle chassis are generated based on road condition characteristic parameters. In some cases, this process can comprehensively consider the current vehicle driving state, such as dynamic parameters like vehicle speed, yaw rate, and pitch angle. Combined with the extracted road condition characteristic parameters, and through optimization algorithms or control models, control commands for driving various chassis subsystems (such as air suspension and damping adjustment devices) are output. These control commands are dynamic and adaptive, automatically matching appropriate chassis parameter settings to driving needs under different road conditions.

[0034] Step S105: In response to the control command, adjust the vehicle chassis.

[0035] In this step, in response to the generated control commands, the vehicle chassis is adjusted. In some cases, this may include continuous or stepped adjustments to the suspension height, damper stiffness adjustment, or modification of the torque distribution strategy of the four-wheel drive system. By executing the control commands, the chassis system can achieve dynamic control of the vehicle's attitude, thereby improving the vehicle's passability, stability, and comfort in different road scenarios, and ultimately optimizing the overall driving experience.

[0036] This application proposes a vehicle chassis adjustment method, the method comprising: acquiring multi-source perception information characterizing the driving path ahead of the vehicle, the multi-source perception information including at least: navigation information characterizing the driving path ahead of the vehicle, and radar point cloud data characterizing obstacle information on the driving path ahead of the vehicle; fusing the navigation information and the radar point cloud data to obtain target road condition information; generating road condition feature parameters corresponding to the driving path ahead of the vehicle based on the target road condition information, the road condition feature parameters characterizing the distribution characteristics of the driving path ahead of the vehicle in the road condition feature dimension and the obstacle dimension; generating control commands for adjusting the vehicle chassis according to the road condition feature parameters; and adjusting the vehicle chassis in response to the control commands. This application obtains target road condition information by fusing navigation information and radar point cloud data, and determines the road condition feature parameters corresponding to the driving path based on the fused target road condition information. Finally, it generates control commands for adjusting the vehicle chassis based on the road condition feature parameters, thereby realizing the control of the vehicle chassis based on multi-source fused data, improving the accuracy of chassis adjustment, and enabling the vehicle to better adapt to complex and diverse driving environments.

[0037] In one embodiment, the step of fusing the navigation information and the radar point cloud data to obtain target road condition information includes: The navigation information and the radar point cloud data are time-stamped and synchronized to obtain the mapping relationship between the navigation information and the radar point cloud data in the time dimension. The navigation information includes any one or more of the following: latitude and longitude data, elevation data and curve curvature radius. The radar point cloud data includes any one or more of the following: obstacle height data and obstacle density data. The navigation information and the radar point cloud data are respectively subjected to coordinate system transformation to obtain the spatial mapping relationship between the navigation information and the radar point cloud data; Based on the mapping relationship between the navigation information and the radar point cloud data in the time dimension and in the spatial dimension, the navigation information and the radar point cloud data are fused according to a preset confidence weighting strategy to obtain the target road condition information.

[0038] In this embodiment, firstly, the navigation information and the radar point cloud data are time-stamped and synchronized to establish a mapping relationship between them in the time dimension. Navigation information typically originates from high-precision maps or real-time route planning systems, and its data update frequency is low, usually recorded at second-level intervals. In contrast, radar point cloud data is collected in real-time by vehicle-mounted millimeter-wave radar or lidar, with a higher update frequency, reaching millisecond levels. Therefore, to ensure the accuracy and coordination of subsequent fusion processing, the timestamps of the two data sources need to be calibrated first.

[0039] Specifically, based on the vehicle system's unified clock, the radar data frame closest to the navigation time point can be selected for matching, or resampling can be performed through interpolation to establish a one-to-one or approximately corresponding mapping relationship between navigation data and radar point cloud on the time axis. During this synchronization process, navigation information may include, but is not limited to, static path description data such as latitude and longitude data, elevation information, and curve curvature radius; while radar point cloud data may include dynamic environmental perception information such as obstacle height, obstacle density, and spatial distribution.

[0040] Secondly, coordinate system transformation is performed on navigation information and radar point cloud data separately to establish a spatial mapping relationship between the two. Navigation information is typically expressed in a geographic coordinate system, with units of longitude, latitude, and altitude, while radar point cloud data is referenced to the vehicle itself and is usually expressed in a vehicle coordinate system or sensor coordinate system. Therefore, both types of data must be transformed to a unified spatial reference frame before fusion processing can be performed. In this embodiment, vehicle multi-sensor calibration parameters and transformation matrices can be used to project radar coordinate system data onto the vehicle coordinate system or a unified geodetic coordinate system, and precise coordinate alignment is achieved by combining the vehicle's current positioning attitude (such as yaw angle, heading angle, etc.). By completing this spatial mapping, it can be ensured that the navigation path and perceived obstacles are represented in the same spatial reference, providing support for subsequent spatial domain fusion calculations.

[0041] Finally, based on the mapping relationship between navigation information and radar point cloud data in the time and spatial dimensions, the two are fused according to a preset confidence weighting strategy to generate target road condition information.

[0042] In one embodiment, the navigation information and the radar point cloud data are fused according to a preset confidence weighting strategy to obtain the target road condition information, including: Obtain current environmental information and the vehicle's equipment status information; The environmental information, the device status information, the navigation information with a predetermined mapping relationship between time and space dimensions, and the radar point cloud data are input into a pre-trained control model to obtain the confidence level of the radar point cloud data and the confidence level of the navigation information. The confidence level of the radar point cloud data is determined based on the environmental information, and the confidence level of the navigation information is determined based on the device status information. The weights of the radar point cloud data are determined based on the confidence level of the radar point cloud data, and the weights of the navigation information are determined based on the confidence level of the navigation information. Based on the respective weights of the radar point cloud data and the navigation information, the radar point cloud data and the navigation information are weighted and fused to obtain the target road condition information.

[0043] In this embodiment, firstly, the current environmental information and the vehicle's equipment status information are obtained.

[0044] Environmental information can include external environmental factors affecting the reliability of the sensing system, such as current weather conditions (sunny, rainy, snowy, etc.), light intensity (daytime, nighttime, or tunnel conditions, etc.), road slipperiness, or ambient temperature. This information can be acquired by vehicle-mounted weather sensors, light sensors, camera image recognition modules, etc., and is used to assess the impact of current external conditions on the accuracy of the sensing system. Equipment status information mainly includes data related to the operation of the navigation system and sensing equipment, such as the current signal quality of the GNSS module, whether the map data version is up-to-date, and the health status of sensors (whether there is obstruction or signal interference). By collecting this information, the reliability of each data source can be determined, providing a supporting basis for subsequent weight allocation.

[0045] Secondly, environmental information, equipment status information, and navigation information and radar point cloud data that have undergone time and spatial dimension alignment processing are input into a pre-trained control model. This control model is a fusion decision model trained during the development phase based on a large amount of historical road data, perception data, and labeled confidence data. The model can be implemented using machine learning algorithms, such as decision trees, support vector machines, or lightweight neural network structures. Input data includes: path structure descriptions (such as elevation and curvature) and their corresponding time / space coordinates in the navigation information; obstacle morphology and spatial distribution information extracted from the radar point cloud data; and external environmental information and equipment operating status indicators. After receiving the above inputs, the control model will automatically output the confidence values ​​of the navigation information and the radar point cloud data at the current moment. Among them, the confidence value of the navigation information is mainly affected by the equipment status. For example, when the GPS signal is stable and the map is updated in a timely manner, its confidence value is naturally higher; conversely, in weak signal scenarios such as tall buildings or tunnels, its confidence value will be significantly reduced. The confidence level of radar point cloud data is dynamically adjusted based on environmental factors. For example, in rainy or snowy weather, the recognition accuracy will be reduced due to the greater interference with radar wave signals, and the model will give a lower confidence level accordingly.

[0046] Next, the fusion weights are determined based on the confidence level of the radar point cloud data, and the corresponding fusion weights are determined based on the confidence level of the navigation information.

[0047] The weight values ​​can be determined using a standardized linear mapping method or a lookup table-based hierarchical method. For example, confidence values ​​can be divided into several levels according to intervals, with each level corresponding to a set of preset weight coefficients (e.g., a weight of 0.7 for higher confidence and 0.3 for lower confidence). Alternatively, confidence values ​​can be directly used as weight values ​​in the fusion calculation. This step ensures that the contribution of each data source can be dynamically adjusted according to changes in data reliability during fusion, achieving adaptive collaboration between data sources.

[0048] Finally, based on their respective calculated weights, the navigation information and radar point cloud data are weighted and fused to output unified target road condition information. This fusion process not only includes a weighted average of the original data values ​​but also incorporates multi-level fusion processing by combining the spatial complementarity of the features of each data source. Taking elevation data as an example, navigation information can provide an overall trend, while radar point cloud data can supplement local abrupt changes and fluctuations. The target road condition information obtained through fusion will have the advantages of both continuity and local details, reflecting both the overall path structure and capturing environmental changes, serving as the core input basis for subsequent extraction of road condition feature parameters such as road type, slope, and obstacle density.

[0049] For example, after completing the mapping in both time and space, a pre-defined confidence model can be used to perform weighted fusion processing on data from different sources. This confidence strategy is dynamically adjusted based on factors such as the complexity of the road condition scenario, sensor data quality, and weather conditions. For instance, in straight road sections and areas with good positioning, the confidence weight of navigation information can be set to 0.7 to reflect its advantage in path structure recognition; while in areas where the map has not been updated or when sudden changes in road conditions occur, this weight can be reduced to 0.3 to minimize the impact of outdated maps on judgment. Simultaneously, the confidence of radar point cloud data can be dynamically calculated based on indicators such as echo intensity and point cloud density. Especially in low-visibility scenarios such as rain and snow, enhanced filtering and recognition algorithms can improve its environmental perception accuracy. The fusion method can employ linear weighting, Bayesian estimation, deep feature fusion, etc., ultimately outputting structured target road condition information. The target road condition information not only includes road features such as the continuity, slope, and curvature of the path ahead of the vehicle, but also comprehensively expresses environmental factors such as obstacle distribution and obstacle shape, providing a highly reliable data foundation for subsequent road condition feature extraction and chassis control decisions.

[0050] In one embodiment, generating road condition feature parameters corresponding to the driving path ahead of the vehicle based on the target road condition information includes: The target road condition information is preprocessed to obtain the preprocessed result of the target road condition information; For the preprocessing results, feature value extraction operations are performed in multiple dimensions. The feature values ​​in the multiple dimensions include any two or more of the following: road type, path slope, curve curvature, obstacle density, and impact intensity level. By combining the feature values ​​of each dimension, the road condition feature parameters corresponding to the driving path ahead are obtained. The step of generating control commands for adjusting the vehicle chassis based on the road condition characteristic parameters includes: Based on the road type, path gradient, and curve curvature in the road condition characteristic parameters, a first control command for suppressing vehicle vibration is generated. Based on the road type, obstacle density, and impact intensity level in the road condition characteristic parameters, a second control command is generated to adjust the suspension height and damping. Based on the curvature of the curves and the slope of the path in the road condition characteristic parameters, a third control command is generated to adjust the torque distribution of the four-wheel drive system.

[0051] In this embodiment, the target road condition information is first preprocessed to obtain the preprocessed result. In some cases, the preprocessing operations include smoothing and filtering the navigation elevation data, removing outliers, clustering and reducing outliers in the radar point cloud, and compensating for missing data to improve data quality and structure. This preprocessing significantly improves the accuracy and stability of subsequent feature extraction, providing a cleaner and more reliable input data foundation for feature analysis.

[0052] Next, feature value extraction operations are performed on the preprocessed results in multiple dimensions.

[0053] Specifically, in this embodiment, the extracted feature dimensions include, but are not limited to, at least two or more of the following: Road type indicates the type of road surface structure corresponding to the road segment ahead, such as paved road, unpaved road, muddy road, icy road, etc. The path gradient is calculated based on the relationship between the elevation changes and the projected distances of continuous path points, reflecting the intensity of the climb or descent that the vehicle will face. Curve curvature is assessed by curve fitting based on a sequence of path points and by calculating the maximum curvature value to evaluate the sharpness of the curve. Obstacle density, obtained by counting the number of obstacles in a unit area, reflects the complexity of the road surface and the risk of passage. Impact intensity level is determined by taking into account factors such as obstacle height, density, and the vehicle's current speed. The model estimates the vertical impact level that the vehicle will face, and the level is usually divided into 1 to 5.

[0054] Finally, the feature values ​​of the above dimensions are combined to form a set of structured road condition feature parameters, which are used to comprehensively characterize the distribution characteristics of the driving path ahead in the road condition feature dimension and obstacle dimension.

[0055] After obtaining the road condition characteristic parameters, control commands for adjusting the vehicle chassis are generated based on these parameters. The control commands are divided into three sub-control commands according to their functions, targeting different chassis control modules: the first control command, the second control command, and the third control command.

[0056] The first control command is used to suppress vehicle body vibration. Based on the road type, path slope, and curve curvature in the road condition characteristic parameters, the possible attitude changes and vertical disturbance trends of the vehicle on this road section are predicted, and then control signals are generated to adjust the suspension response speed and active damping control, so as to reduce the amplitude of vehicle body vibration generated during the vehicle's passage and improve ride comfort.

[0057] The second control command is used to adjust the suspension height and damping stiffness. This control command is generated based on a combination of road type, obstacle density, and impact intensity level. If a high-impact risk or area with concentrated obstacles is detected ahead, the suspension is actively raised and the damping coefficient is increased to enhance the wheel's contact with the ground and its cushioning ability, ensuring passability and vehicle stability.

[0058] The third control command is used to adjust the torque distribution strategy of the four-wheel drive system. Based on the curvature and slope information of the curves in the path, it predicts the trend of lateral force changes and the distribution of driving force demand for the vehicle on that road section. Using this information, it dynamically adjusts the driving torque ratio between the front and rear wheels or between the left and right wheels to improve cornering stability and climbing power output, thereby achieving enhanced active handling.

[0059] This embodiment achieves dynamic coordinated control of multiple subsystems such as chassis height, damping, and torque through the joint generation and issuance of the above three types of control commands, which can maintain an organic balance between vehicle handling stability and ride comfort in complex road environments.

[0060] In one embodiment, generating a second control command for adjusting suspension height and damping based on the road type, obstacle density, and impact intensity level in the road condition characteristic parameters includes: Based on the road type and obstacle density in the road condition characteristic parameters, determine the target height adjustment value and target damping adjustment value for adjusting the suspension height; Based on the impact intensity level in the road condition characteristic parameters, determine the response sensitivity for adjusting suspension height and damping; Based on the target height adjustment value, the target damping adjustment value, and the response sensitivity, an adjustment curve for suspension height and suspension damping is constructed. The adjustment curve for suspension height and suspension damping is a nonlinear gradual function curve. The second control command is generated based on the adjustment curves of the suspension height and suspension damping.

[0061] In this embodiment, firstly, based on the road type and obstacle density in the road condition characteristic parameters, the target height adjustment value and the target damping adjustment value for adjusting the suspension height are determined.

[0062] Road type reflects the structural nature of the road section where the vehicle is located, such as paved road, unpaved road, gravel road, icy road, etc. Different types of roads have different requirements for vehicle chassis height and suspension stiffness.

[0063] For example, unpaved or potholed roads typically require higher ground clearance and softer damping to enhance cushioning, while high-speed, smooth roads tend to require lower vehicle bodies and stiffer damping to improve stability. Obstacle density, an indicator of the number of obstacles per unit area, can be used to assess road complexity and traverse risk. In areas with high obstacle density, it is advisable to prioritize increasing the suspension travel limit and reducing damping stiffness to achieve adequate shock absorption.

[0064] Based on the combined results of these two dimensions, the target height adjustment value and target damping adjustment value at the current moment are determined by looking up a table or by using a model algorithm, providing a static target reference for subsequent adjustment actions.

[0065] Secondly, based on the impact intensity level in the road condition characteristic parameters, the response sensitivity for adjusting suspension height and damping is determined.

[0066] Impact intensity rating is a classification of the overall impact risk along the path ahead, typically estimated based on obstacle height, obstacle distribution pattern, and the vehicle's current speed. As the impact intensity rating increases, it means that suspension parameters need to be adjusted quickly to cope with the impending severe disturbance; therefore, the corresponding adjustment response should be faster and more precise.

[0067] In this embodiment, the response sensitivity can be reflected in the target response time of the suspension control system (such as completing the adjustment within 500ms), the adjustment amplitude amplification factor, or the slope factor of the nonlinear transition curve, etc., to drive the actuator to quickly and efficiently complete parameter switching.

[0068] Then, based on the target height adjustment value, the target damping adjustment value, and the response sensitivity, the suspension height and damping adjustment curves are constructed.

[0069] In this embodiment, to avoid vehicle posture fluctuations or ride discomfort caused by sudden changes in control commands, this application employs a nonlinear gradual function curve for parameter transition control. Specifically, the adjustment curve can be a parameter gradual curve based on the Sigmoid function, or it can be a piecewise linear interpolation curve or a Bezier curve, etc., to ensure that the suspension height and damping coefficient present a smooth transition process between the current value and the target value. In this embodiment, as the impact intensity level increases, the rate of change of the above-mentioned adjustment curve increases accordingly, and as the impact intensity level decreases, the rate of change of the above-mentioned adjustment curve decreases accordingly.

[0070] Finally, based on the adjustment curves of the suspension height and damping, a second control command is generated and sent to the suspension execution system.

[0071] In some cases, control commands may include: the current starting state, the desired target value, the transition function parameters, the execution time interval, etc. The controller schedules the execution in the form of time steps, so that the suspension can achieve predictable and adjustable dynamic response under different operating conditions.

[0072] The second control command generated by this method in this embodiment has adaptive and nonlinear flexible control characteristics, which can significantly improve the vehicle's shock mitigation ability and driving stability under complex road conditions, improve the driving experience, and reduce perceived NVH risks.

[0073] In one embodiment, generating control commands for adjusting the vehicle chassis based on the road condition characteristic parameters includes: Obtain the current driving status data of the vehicle, which includes one or more of the following: current vehicle speed, current yaw rate, and current pitch angle; Based on the driving status data, the road condition feature parameters are corrected to obtain the corrected target road condition feature parameters. Based on the target road condition feature parameters and the vehicle's current driving state, a preset rolling time-domain optimization algorithm is used to generate control commands for adjusting the vehicle chassis. The rolling time-domain optimization algorithm represents the control command generation algorithm that enables the vehicle chassis performance indicators to reach the target performance indicators.

[0074] Specifically, in this embodiment, after acquiring the target road condition characteristic parameters and the vehicle's current driving state, these are used as state variables and external disturbance inputs to construct a predictive model for the vehicle chassis. Based on this predictive model, the dynamic response of the vehicle chassis at multiple future moments is predicted within a preset rolling time domain. The optimization objective is to make the vehicle chassis performance indicators (such as driving stability, comfort, or safety) approach or reach the target performance indicators, and corresponding objective functions and constraints are established. The optimal control sequence at the current moment is obtained through a rolling time domain optimization algorithm, and the control quantity corresponding to the current moment is selected as the control command for the vehicle chassis. After executing the control command, the updated road condition characteristic parameters and vehicle driving state are acquired again as time progresses, and the above optimization and solution process is repeated, thereby realizing real-time and adaptive adjustment of the vehicle chassis.

[0075] In this embodiment, firstly, the current driving status data of the vehicle is acquired. This driving status data includes one or more of the following: current vehicle speed, current yaw rate, and current pitch angle. This step is used to obtain the current dynamic operating state of the vehicle. Vehicle speed data can be used to evaluate the timeliness requirements of the vehicle's chassis adjustment response; for example, higher requirements are placed on adjustment speed and control smoothness when driving at high speeds. Yaw rate reflects the vehicle's lateral steering state, helping to determine whether it is in a turning or lane-changing situation. Pitch angle is used to identify the trend of vehicle posture changes during acceleration and deceleration. The above status data can be provided by devices such as the onboard ECU, inertial measurement unit (IMU), or wheel speed sensors, constituting a dynamic input set reflecting the current operating posture of the vehicle.

[0076] Secondly, based on the driving status data, the road condition characteristic parameters are corrected to obtain the corrected target road condition characteristic parameters.

[0077] While road condition characteristic parameters can be extracted by fusing sensing information, errors may still be amplified or their effect delayed during actual driving due to vehicle dynamic behavior. Therefore, dynamically correcting the original characteristic parameters based on the vehicle's current driving state is an important means of improving control accuracy.

[0078] For example, during rapid acceleration or deceleration, the vehicle's response to road surface undulations may be masked by forward or backward pitching, requiring compensation for slope parameters. During high-speed cornering, additional safety margins are introduced into curvature-related characteristic parameters to enhance lateral stability. This correction process can employ weighted adjustment, fuzzy correction, or lookup table correction, using driving state parameters as adjustment factors to ensure a more accurate reflection of the actual impact on chassis performance at the current moment.

[0079] Then, based on the target road condition characteristic parameters and the vehicle's current driving state, a preset rolling horizontal optimization algorithm is used to generate control commands for adjusting the vehicle chassis. Rolling horizontal optimization (or model predictive control) is a forward-looking control strategy for dynamic systems. Its core idea is to predict the possible motion state of the vehicle over a future period (i.e., the prediction time domain) within each control cycle, starting from the current moment, and generate the optimal control input sequence based on the prediction results. In this embodiment, a rolling horizontal optimization model is established using this optimization method, with the "corrected target road condition characteristic parameters" and "current driving state" as the model's input variables. By constructing an objective function and constraints, the optimal combination of chassis control parameters is solved.

[0080] The objective function may include, but is not limited to: minimizing the vertical acceleration of the vehicle body to reduce vibration; minimizing the suspension adjustment range to improve energy efficiency and system stability; limiting the rate of suspension change to ensure smooth adjustment; and optimizing the torque distribution between the four wheels to enable the vehicle to maintain better handling stability under complex road conditions.

[0081] The constraints may include mechanical limits of the suspension system, actuator delays, and control cycle time limits. The rolling time-domain optimization model executes the optimal control action only for the current time step and re-rolls the prediction in the next cycle, ensuring that the system has the ability to adjust in real time and adapt to the environment.

[0082] Finally, based on the control output generated by the above optimization process, control commands are formed to drive the vehicle chassis actuators. These control commands can be applied to the air suspension height adjustment module, damping adjuster, active roll control system, or electronic four-wheel drive system, etc., to complete the real-time control of chassis structural parameters, thereby achieving adaptive height adjustment of the vehicle under complex road conditions and changing postures, improving the overall vehicle stability, comfort, and safety.

[0083] In one embodiment, after adjusting the vehicle chassis, the method further includes: Monitor the vehicle's body posture change parameters and vertical vibration level parameters to determine the actual response data of adjusting the vehicle's chassis based on the control commands; The actual response data is compared and analyzed with the predictive control results generated based on the road condition feature parameters to determine the control deviation between the actual response data and the predictive control results. The predictive control results are obtained by inputting the road condition feature parameters into a pre-trained control model. Based on the control deviation, the weights of the radar point cloud data and the navigation information are adjusted, as are the model parameters of the control model.

[0084] In this embodiment, firstly, the vehicle's body attitude change parameters and vertical vibration level parameters are monitored to determine the actual response data of adjusting the vehicle chassis based on control commands. The body attitude change parameters may include pitch angle changes, roll angle changes, and roll angle changes during the adjustment process, reflecting the overall motion trend of the vehicle. The vertical vibration level parameters are typically measured using onboard acceleration sensors and are used to quantify the degree of dynamic disturbance of the vehicle body in the vertical direction. This actual response data reflects the physical execution effect of the chassis control commands, providing an objective basis for subsequent performance evaluation and control optimization.

[0085] Secondly, the actual response data is compared and analyzed with the predictive control results generated based on road condition characteristic parameters to determine the control deviation between the two. The predictive control result refers to the expected response behavior obtained by inputting the extracted road condition characteristic parameters into a pre-trained control model before control execution. This control model can be the rolling time-domain optimization model mentioned above. For example, in scenarios where the estimated obstacle density is high and the impact intensity level is high, the predictive control model may anticipate a certain degree of height increase and damping change in the chassis to mitigate the impact. By analyzing the difference between the actual monitored vehicle body response and the expected value output by the control model, a set of control deviations can be calculated. These deviation indicators may include vibration response amplitude error, attitude angle change delay, and insufficient adjustment amplitude.

[0086] Then, based on the calculated control deviation, the fusion weights of radar point cloud data and navigation information are dynamically adjusted, and the parameters of the control model are optimized and corrected at the same time.

[0087] In this embodiment, when a control deviation is detected to be greater than a set threshold, it can be considered that the reliability of the original sensing information is somewhat insufficient. At this time, the confidence level allocation in the data fusion stage is corrected by tracing back the original sensing path. For example: If the main source of error is inaccurate prediction of road structure, the weight of navigation information can be reduced and the participation of radar point cloud data can be increased. If obstacle detection results in false alarms or missed detections, the confidence level of navigation data can be improved, or redundant information from other sensors can be utilized.

[0088] In addition, this embodiment can also fine-tune the parameters of the control model used to generate control commands online, specifically by adjusting the response sensitivity factor, activation function parameters, fuzzy rule weights, or optimizing constraints in the model, thereby improving the adaptability and accuracy of the subsequent predictive control process.

[0089] Through the aforementioned closed-loop feedback mechanism, this embodiment can gradually correct its perception fusion strategy and control strategy during multiple driving processes, realizing a closed-loop self-learning process between data fusion, control decision-making, and execution feedback, significantly improving the intelligence level and multi-scenario adaptability of vehicle chassis control.

[0090] In one embodiment, reference is made to... Figure 2 The schematic diagram of the overall system architecture of the vehicle chassis adjustment method shown includes: a data acquisition layer, a data processing layer, a decision control layer, and an action execution layer.

[0091] The data acquisition layer is used to collect various raw input data required during vehicle operation, specifically including: navigation information of the driving path; radar point cloud data of obstacles on the driving path; and vehicle driving status data.

[0092] The data processing layer is used to fuse and extract features from the collected data. Specifically, it includes: fusing multi-source data to generate target road condition information; and extracting road condition feature parameters of the path ahead based on the fused data.

[0093] The decision control layer is used to generate chassis adjustment control commands based on the extracted road condition feature parameters. This layer takes the extracted features as input, completes the control logic judgment, and outputs commands.

[0094] The action execution layer receives and executes control commands to make specific adjustments to the vehicle chassis system. This includes: a first control command to suppress vehicle body vibration; a second control command to adjust suspension height and damping; and a third control command to adjust four-wheel drive torque distribution.

[0095] In one embodiment, reference is made to... Figure 3 The detailed processing flow diagram of the vehicle chassis adjustment method shown includes multiple stages: data preprocessing stage, core processing stage, control decision stage, and closed-loop feedback stage.

[0096] In the data preprocessing stage, the collected navigation data and radar data are processed separately, specifically including: Navigation data preprocessing: path prediction interpolation; elevation curvature calculation; path slope estimation; Radar data preprocessing: radar density estimation; impact intensity determination.

[0097] In the core processing stage, the processed navigation data and radar data are further integrated to generate unified road condition characteristic parameters, which may include, but are not limited to: road type; path gradient; curve curvature; obstacle density; impact intensity level, etc.

[0098] During the control decision-making phase, a rolling time-domain optimization model is used as the control decision logic. Control decisions are based on this model, using the road condition characteristic parameters as input, and control commands are generated in real time. Decision outputs include: suspension adjustment; four-wheel drive distribution adjustment.

[0099] In the closed-loop feedback phase, after the control command is executed, there are two additional feedback mechanisms: vehicle posture feedback, which is used to monitor the vehicle response status; and drive efficiency monitoring, which is used to evaluate the performance of the chassis control system.

[0100] Based on the same inventive concept, a second aspect of the embodiments of this application provides a vehicle chassis adjustment system, such as... Figure 4 As shown, the system includes: The acquisition module 201 acquires multi-source perception information for characterizing the driving path in front of the vehicle. The multi-source perception information includes at least: navigation information for characterizing the driving path in front of the vehicle, and radar point cloud data for characterizing obstacle information on the driving path in front of the vehicle. Data fusion processing module 202 is used to fuse the navigation information and the radar point cloud data to obtain target road condition information; The first generation module 203 is used to generate road condition feature parameters corresponding to the driving path in front of the vehicle based on the target road condition information. The road condition feature parameters are used to characterize the distribution characteristics of the driving path in front of the vehicle in the road condition feature dimension and the obstacle dimension. The second generation module 204 is used to generate control commands for adjusting the vehicle chassis based on the road condition characteristic parameters. The execution module 205 is used to adjust the vehicle chassis in response to the control command.

[0101] Optionally, the data fusion processing module 202, which fuses the navigation information and the radar point cloud data to obtain target road condition information, includes: The timestamp synchronization processing submodule is used to perform timestamp synchronization processing on the navigation information and the radar point cloud data respectively, so as to obtain the mapping relationship between the navigation information and the radar point cloud data in the time dimension. The navigation information includes any one or more of the following: latitude and longitude data, elevation data and curve curvature radius. The radar point cloud data includes any one or more of the following: obstacle height data and obstacle density data. The coordinate system transformation processing submodule is used to perform coordinate system transformation processing on the navigation information and the radar point cloud data respectively, so as to obtain the mapping relationship between the navigation information and the radar point cloud data in the spatial dimension; The fusion processing submodule is used to fuse the navigation information and the radar point cloud data according to the mapping relationship in the time dimension and the mapping relationship in the spatial dimension, and according to a preset confidence weighting strategy to obtain the target road condition information.

[0102] Optionally, the navigation information and the radar point cloud data are fused according to a preset confidence weighting strategy to obtain the target road condition information. The fusion processing submodule includes: The acquisition subunit is used to acquire current environmental information and the vehicle's equipment status information; The confidence determination subunit is used to input the environmental information, the device status information, the navigation information with a determined time and space dimension mapping relationship, and the radar point cloud data into a pre-trained control model to obtain the confidence of the radar point cloud data and the confidence of the navigation information. The confidence of the radar point cloud data is determined based on the environmental information, and the confidence of the navigation information is determined based on the device status information. The weight determination subunit is used to determine the weight of the radar point cloud data based on the confidence level of the radar point cloud data, and to determine the weight of the navigation information based on the confidence level of the navigation information; The weighted fusion subunit is used to perform weighted fusion of the radar point cloud data and the navigation information according to their respective weights to obtain the target road condition information.

[0103] Optionally, the first generation module 203, which generates road condition feature parameters corresponding to the driving path ahead of the vehicle based on the target road condition information, includes: The preprocessing submodule is used to preprocess the target road condition information to obtain the preprocessing result of the target road condition information; The execution submodule is used to perform feature value extraction operations in multiple dimensions for the preprocessing results. The feature values ​​in multiple dimensions include any two or more of the following: road type, path slope, curve curvature, obstacle density, and impact intensity level. The combination submodule is used to combine the feature values ​​of each dimension to obtain the road condition feature parameters corresponding to the driving path ahead. The second generation module 204, which generates control commands for adjusting the vehicle chassis based on the road condition characteristic parameters, includes: The first generation submodule is used to generate a first control command for suppressing vehicle vibration based on the road type, path slope and curve curvature in the road condition feature parameters. The second generation submodule is used to generate a second control command for adjusting the suspension height and damping based on the road type, obstacle density and impact intensity level in the road condition characteristic parameters. The third generation submodule is used to generate a third control command for adjusting the four-wheel drive torque distribution based on the curvature of the curve and the slope of the path in the road condition characteristic parameters.

[0104] Optionally, the second control command for adjusting suspension height and damping is generated based on the road type, obstacle density, and impact intensity level in the road condition characteristic parameters. The second generation submodule includes: The first determining subunit determines the target height adjustment value and the target damping adjustment value for adjusting the suspension height based on the road type and obstacle density in the road condition characteristic parameters. The second determining subunit is used to determine the response sensitivity for adjusting suspension height and damping based on the impact intensity level in the road condition characteristic parameters. A subunit is constructed to build an adjustment curve for suspension height and suspension damping based on the target height adjustment value, the target damping adjustment value, and the response sensitivity. The adjustment curve for suspension height and suspension damping is a nonlinear gradual function curve. A generation subunit is used to generate the second control command based on the adjustment curves of the suspension height and suspension damping.

[0105] Optionally, the step of generating control commands for adjusting the vehicle chassis based on the road condition characteristic parameters includes: The acquisition submodule is used to acquire the current driving status data of the vehicle, which includes one or more of the following: current vehicle speed, current yaw rate and current pitch angle. The correction submodule is used to correct the road condition feature parameters based on the driving status data to obtain the corrected target road condition feature parameters. The rolling time-domain optimization submodule is used to generate control commands for adjusting the vehicle chassis based on the target road condition feature parameters and the current driving state of the vehicle using a preset rolling time-domain optimization algorithm. The rolling time-domain optimization algorithm represents the control command generation algorithm that enables the vehicle chassis performance indicators to reach the target performance indicators.

[0106] Optionally, the system further includes: The monitoring submodule is used to monitor the vehicle's body posture change parameters and vertical vibration level parameters, and determine the actual response data of adjusting the vehicle's chassis based on the control command. The comparative analysis submodule is used to compare and analyze the actual response data with the predictive control results generated based on the road condition feature parameters, and to determine the control deviation between the actual response data and the predictive control results. The predictive control results are obtained by inputting the road condition feature parameters into a pre-trained control model. The adjustment submodule is used to adjust the weights of the radar point cloud data and the navigation information according to the control deviation, and to adjust the model parameters of the control model.

[0107] Based on the same inventive concept, a third aspect of the embodiments of this application provides a method as follows: Figure 5The electronic device 100 shown includes a processor 120, a memory 110, and a program or instructions stored in the memory 110 and executable on the processor 120, wherein the program or instructions, when executed by the processor 120, implement the steps of the vehicle chassis adjustment method as described in the first aspect of this application.

[0108] Based on the same inventive concept, in a fourth aspect of this application, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the vehicle chassis adjustment method as described in the first aspect of this application.

[0109] Each embodiment in this specification focuses on the differences from other embodiments. For the same or similar parts between the embodiments, please refer to each other.

[0110] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0111] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0112] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0114] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0115] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0116] The above provides a detailed description of a vehicle chassis adjustment method, system, electronic device, and storage medium. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for adjusting a vehicle chassis, characterized in that, The method includes: Acquire multi-source perception information to characterize the driving path in front of the vehicle, the multi-source perception information including at least: navigation information to characterize the driving path in front of the vehicle, and radar point cloud data to characterize obstacle information on the driving path in front of the vehicle. The navigation information and the radar point cloud data are fused to obtain the target road condition information; Based on the target road condition information, road condition feature parameters corresponding to the driving path are generated. The road condition feature parameters are used to characterize the distribution characteristics of the driving path in the road condition feature dimension and obstacle dimension. Based on the road condition characteristic parameters, control commands for adjusting the vehicle chassis are generated; In response to the control command, the vehicle chassis is adjusted.

2. The vehicle chassis adjustment method according to claim 1, characterized in that, The process of fusing the navigation information and the radar point cloud data to obtain target road condition information includes: The navigation information and the radar point cloud data are time-stamped and synchronized to obtain the mapping relationship between the navigation information and the radar point cloud data in the time dimension. The navigation information includes any one or more of the following: latitude and longitude data, elevation data and curve curvature radius. The radar point cloud data includes any one or more of the following: obstacle height data and obstacle density data. The navigation information and the radar point cloud data are respectively subjected to coordinate system transformation to obtain the mapping relationship between the navigation information and the radar point cloud data in the spatial dimension; Based on the mapping relationship between the navigation information and the radar point cloud data in the time dimension and in the spatial dimension, the navigation information and the radar point cloud data are fused according to a preset confidence weighting strategy to obtain the target road condition information.

3. The vehicle chassis adjustment method according to claim 2, characterized in that, The process of fusing the navigation information and the radar point cloud data according to a preset confidence weighting strategy to obtain the target road condition information includes: Obtain current environmental information and the vehicle's equipment status information; The environmental information, the device status information, the navigation information with a predetermined mapping relationship between time and space dimensions, and the radar point cloud data are input into a pre-trained control model to obtain the confidence level of the radar point cloud data and the confidence level of the navigation information. The confidence level of the radar point cloud data is determined based on the environmental information, and the confidence level of the navigation information is determined based on the device status information. The weights of the radar point cloud data are determined based on the confidence level of the radar point cloud data, and the weights of the navigation information are determined based on the confidence level of the navigation information. Based on the respective weights of the radar point cloud data and the navigation information, the radar point cloud data and the navigation information are weighted and fused to obtain the target road condition information.

4. The vehicle chassis adjustment method according to claim 1, characterized in that, The step of generating road condition feature parameters corresponding to the driving path based on the target road condition information includes: The target road condition information is preprocessed to obtain the preprocessed result of the target road condition information; For the preprocessing results, feature value extraction operations are performed in multiple dimensions, including any two or more of the following: road type, path slope, curve curvature, obstacle density, and impact intensity level; By combining the feature values ​​of each dimension, the road condition feature parameters corresponding to the driving path are obtained; The step of generating control commands for adjusting the vehicle chassis based on the road condition characteristic parameters includes: Based on the road type, path gradient, and curve curvature in the road condition characteristic parameters, a first control command for suppressing vehicle vibration is generated. Based on the road type, obstacle density, and impact intensity level in the road condition characteristic parameters, a second control command is generated to adjust the suspension height and damping. Based on the curvature of the curves and the slope of the path in the road condition characteristic parameters, a third control command is generated to adjust the torque distribution of the four-wheel drive system.

5. The vehicle chassis adjustment method according to claim 4, characterized in that, The second control command for adjusting suspension height and damping is generated based on the road type, obstacle density, and impact intensity level in the road condition characteristic parameters, including: Based on the road type and obstacle density in the road condition characteristic parameters, determine the target height adjustment value and target damping adjustment value for adjusting the suspension height; Based on the impact intensity level in the road condition characteristic parameters, determine the response sensitivity for adjusting suspension height and damping; Based on the target height adjustment value, the target damping adjustment value, and the response sensitivity, an adjustment curve for suspension height and suspension damping is constructed. The adjustment curve for suspension height and suspension damping is a nonlinear gradual function curve. The second control command is generated based on the adjustment curves of the suspension height and suspension damping.

6. The vehicle chassis adjustment method according to claim 1, characterized in that, The step of generating control commands for adjusting the vehicle chassis based on the road condition characteristic parameters includes: Obtain the current driving status data of the vehicle, which includes one or more of the following: current vehicle speed, current yaw rate, and current pitch angle; Based on the driving status data, the road condition feature parameters are corrected to obtain the corrected target road condition feature parameters. Based on the target road condition feature parameters and the vehicle's current driving state, a preset rolling time-domain optimization algorithm is used to generate control commands for adjusting the vehicle chassis. The rolling time-domain optimization algorithm represents the control command generation algorithm that enables the vehicle chassis performance indicators to reach the target performance indicators.

7. The vehicle chassis adjustment method according to claim 3, characterized in that, After adjusting the vehicle chassis, the method further includes: Monitor the vehicle's body posture change parameters and vertical vibration level parameters to determine the actual response data of adjusting the vehicle's chassis based on the control commands; The actual response data is compared and analyzed with the predictive control results generated based on the road condition feature parameters to determine the control deviation between the actual response data and the predictive control results. The predictive control results are obtained by inputting the road condition feature parameters into a pre-trained control model. Based on the control deviation, the weights of the radar point cloud data and the navigation information are adjusted, as are the model parameters of the control model.

8. A vehicle chassis adjustment system, characterized in that, The system includes: The acquisition module acquires multi-source perception information for characterizing the driving path in front of the vehicle. The multi-source perception information includes at least: navigation information for characterizing the driving path in front of the vehicle, and radar point cloud data for characterizing obstacle information on the driving path in front of the vehicle. The data fusion processing module is used to fuse the navigation information and the radar point cloud data to obtain target road condition information; The first generation module is used to generate road condition feature parameters corresponding to the driving path based on the target road condition information. The road condition feature parameters are used to characterize the distribution characteristics of the driving path in the road condition feature dimension and the obstacle dimension. The second generation module is used to generate control commands for adjusting the vehicle chassis based on the road condition characteristic parameters. An execution module is used to adjust the vehicle chassis in response to the control command.

9. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the vehicle chassis adjustment method as described in any one of claims 1-7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the vehicle chassis adjustment method as described in any one of claims 1-7.

Images