A vehicle seat control method, system, computer device and storage medium

Abstract

The application provides a vehicle seat control method, system, computer device and storage medium, comprising: extracting a road surface feature according to target point cloud data, and identifying a pothole area in the road surface based on the road surface feature; associating the pothole area with a vehicle driving state, and performing shock absorption control on the vehicle seat according to an association result. The application associates the pothole area with the vehicle driving state to perform shock absorption control on the vehicle seat, which not only enables the vehicle seat shock absorption system to adapt to complex road conditions such as potholes, improves the adaptability and effect of seat shock absorption, but also effectively reduces the vibration impact of the vehicle seat, so that passengers can have a more stable riding experience in complex road conditions. The application performs shock absorption control on the vehicle seat, reduces the impact of the road surface on the passengers, improves the stability of the vehicle control and the safety of the passengers, reduces the fatigue and discomfort of the driver and the passengers in long-distance driving, and improves the driving comfort.

Description

Technical Field

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

[0002] Traditional seat damping systems primarily rely on mechanical springs and damping structures to passively reduce vibrations transmitted to passengers during vehicle operation. However, traditional seat damping systems have limited effectiveness when dealing with complex road conditions (such as potholes and speed bumps), and struggle to achieve active response and adaptive adjustment to vibrations. Summary of the Invention

[0003] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a vehicle seat control method, system, computer device and storage medium to solve the technical problem that the shock absorption effect of traditional seat shock absorption systems is limited when facing complex road conditions.

[0004] To achieve the above and other related objectives, this application provides a vehicle seat control method, comprising the following steps:

[0005] Acquire target point cloud data, wherein the target point cloud data includes road surface point cloud data;

[0006] Road surface features are extracted from target point cloud data, and pothole areas in the road surface are identified based on the road surface features. The road surface features include at least one of road surface height features, road surface curvature features, and road surface slope features.

[0007] The indentation area is correlated with the vehicle's driving status, and the vehicle seat is subjected to shock absorption control based on the correlation result; wherein, the vehicle's driving status includes at least one of vehicle speed, vehicle position, and vehicle steering angle.

[0008] In one embodiment of this application, if the vehicle seat includes a magnetorheological seat, the process of controlling the shock absorption of the vehicle seat based on the correlation result includes:

[0009] Based on the correlation between the pitted area and the vehicle's driving state, a target current for adjusting the damping response of the magnetorheological damper is calculated, and the magnetorheological damper is adjusted based on the target current to obtain the damping force fed back by the magnetorheological damper.

[0010] The vibration amplitude of the seat acceleration sensor based on the damping force feedback is read, and the damping force is updated when the vibration amplitude is not within the preset range, until the vibration amplitude corresponding to the updated damping force is within the preset range.

[0011] In one embodiment of this application, the process of extracting road surface features based on target point cloud data includes:

[0012] For the coordinates of each point in the road surface point cloud data, perform three-dimensional spatial surface fitting; including:

[0013]

[0014] In the formula, (x, y) represents the coordinates of each point cloud in the road surface point cloud data, z represents the height of the fitted surface, and a0,...,a5 represent the fitting parameters. Indicates the fitting error;

[0015] Based on the maximum and minimum height values ​​of the fitted surface, the height difference between the fitted surfaces is calculated, and this height difference is used as a road surface height feature; including:

[0016] Δz = z1 - z2;

[0017] In the formula, Δz represents the height difference of the fitted surface, z1 represents the maximum height value of the fitted surface, and z2 represents the minimum height value of the fitted surface;

[0018] Calculating the curvature of the fitted surface and using the curvature of the fitted surface as a feature of road surface curvature; including:

[0019]

[0020] In the formula, κ represents the curvature of the fitted surface;

[0021] The slope is calculated based on the gradient of the fitted surface, and the slope is used as a feature of the road surface gradient; including:

[0022]

[0023] In the formula, This represents the gradient of the fitted surface in the x and y directions;

[0024] Slope indicates the degree of inclination.

[0025] In one embodiment of this application, the process of identifying pothole areas in the road surface based on the road surface features includes:

[0026] Calculate road surface point P i (x i ,y i ,z i The residual values ​​of the fitted surface corresponding to the road surface features; including:

[0027]

[0028] In the formula, Representing point (x) i ,y i The corresponding fitted surface height value, d i Represents point P on the road surface i (x i ,y i ,z i The residual value of the fitted surface corresponding to the road surface feature;

[0029] The residual values ​​of all road surface points are compared with the preset threshold T th Compare the results and assign residual values ​​greater than a preset threshold T. th Road surface points are marked as anomalies;

[0030] Spatial clustering is performed on all marked outliers, and each clustering result is taken as a pit region to obtain the pit regions in the road surface.

[0031] In one embodiment of this application, the method further includes:

[0032] Calculate the center position (x) of the pit area based on the point cloud data of the pit area. center ,y center );include:

[0033]

[0034] In the formula, n represents the number of point clouds in the pit area;

[0035] Based on the lowest point P of the pit area min (x min ,y min ,z min ), calculate the depth d of the pit region. pothole ;include:

[0036]

[0037] In the formula, Representing point (x) min ,y min The corresponding fitted surface height, z min Representing point (x) min ,y min The actual height of the ).

[0038] In one embodiment of this application, after obtaining the pothole area in the road surface, the method further includes:

[0039] Establish the local surface equation for the pit region; including: z(x,y)=a0+a1x+a2y+a3x 2 +a4xy+a5y 2 ;

[0040] Calculate the local curvature of the pit region using the local surface equation; including:

[0041]

[0042] In the formula, Curvature represents the local curvature of the pit region, and f x ,f y f represents the surface partial derivative of the pit region. xx ,f yy ,f xy This represents the second-order partial derivative of the pit region.

[0043] In one embodiment of this application, the process of associating the pitted area with the vehicle's driving state includes:

[0044] Get the vehicle position (x) at time k. k y k The vehicle heading angle θ at time k k The vehicle speed v at time k k The vehicle steering angle δ at time k k The position d of the crater at time k pothole,k The pit depth h at time k pothole,k ;

[0045] Based on the vehicle position (x) at time k k y k The vehicle heading angle θ at time k k The vehicle speed v at time k k The vehicle steering angle δ at time k k The position d of the crater at time k pothole,k The pit depth h at time k pothole,k Define the state vector x k ;include:

[0046]

[0047] The state vector x k The data is input into a pre-defined or real-time determined observation function to correlate the pitted area with the vehicle's driving state; including:

[0048] z k =h(x k )+v k ;

[0049]

[0050] In the formula, h() is the observation function, v k It measures noise.

[0051] This application also provides a vehicle seat control system, the system comprising:

[0052] The data acquisition module is used to acquire target point cloud data, including road surface point cloud data;

[0053] The pothole recognition module is used to extract road surface features based on target point cloud data and identify pothole areas in the road surface based on the road surface features. The road surface features include at least one of road surface height features, road surface curvature features, and road surface slope features.

[0054] The shock absorption control module is used to associate the dented area with the vehicle's driving state and to control the shock absorption of the vehicle seat based on the association result; wherein, the vehicle driving state includes at least one of vehicle speed, vehicle position, and vehicle steering angle.

[0055] This application also provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the vehicle seat control method described in any one of the above.

[0056] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle seat control method described in any one of the above.

[0057] As described above, this application provides a vehicle seat control method, system, computer device, and storage medium, which has the following beneficial effects: By acquiring target point cloud data, extracting road surface features based on the target point cloud data, identifying pothole areas on the road surface based on the road surface features, and finally associating the pothole areas with the vehicle's driving state, the application performs shock absorption control on the vehicle seat based on the association result. Therefore, this application, by associating pothole areas with the vehicle's driving state to perform shock absorption control on the vehicle seat, not only enables the vehicle seat shock absorption system to adapt to complex road conditions such as potholes, improving the adaptability and effectiveness of seat shock absorption, but also effectively reduces the vibration impact of the vehicle seat, providing passengers with a smoother riding experience under complex road conditions. Simultaneously, by controlling the vehicle seat's shock absorption, this application reduces the impact of road impacts on passengers, improves the stability of vehicle handling and passenger safety, reduces driver and passenger fatigue and discomfort during long-distance driving, and enhances driving comfort. Attached Figure Description

[0058] Figure 1 This is a schematic flowchart of a vehicle seat control method provided in one embodiment of this application;

[0059] Figure 2 This is a schematic diagram of the perception process during vehicle seat control according to an embodiment of this application;

[0060] Figure 3 This is a schematic diagram of the decision control process for vehicle seat control provided in one embodiment of this application;

[0061] Figure 4 This is a schematic diagram of the hardware structure of a vehicle seat control system provided in one embodiment of this application;

[0062] Figure 5 This is a schematic diagram of the hardware structure of a computer device suitable for implementing one or more embodiments of this application. Detailed Implementation

[0063] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0064] It should be noted that the illustrations provided in this embodiment are only schematic representations of the basic concept of this application. Therefore, the illustrations only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0065] Figure 1 A schematic flowchart of a vehicle seat control method according to an embodiment of this application is shown. Specifically, in an exemplary embodiment, as follows... Figure 1 As shown, this embodiment provides a vehicle seat control method, which includes the following steps:

[0066] S110, acquire target point cloud data, which includes road surface point cloud data. In some embodiments, the process of acquiring road surface point cloud data can be achieved by using a pre-configured LiDAR on the vehicle to perceive and identify three-dimensional spatial data on the road surface, obtaining LiDAR three-dimensional point cloud data; preprocessing the LiDAR three-dimensional point cloud data, and performing point cloud segmentation based on the preprocessing results to obtain the road surface point cloud data; wherein, preprocessing includes, but is not limited to, denoising, filtering, and downsampling. Specifically, as an example, LiDAR can be used to perceive and identify three-dimensional spatial data on the road surface in real time, capturing minute changes in the road surface, and outputting three-dimensional spatial point cloud data composed of multiple three-dimensional coordinate points, each of which represents a certain location point on the road surface. The acquired three-dimensional spatial point cloud data is then subjected to denoising, filtering, and downsampling processing. Denoising removes environmental interference or error data, filtering removes unwanted distant points, and downsampling reduces computational load. Clear and sparse point cloud data is output, retaining important road surface features. Road surface points are then separated from the three-dimensional spatial point cloud data. Since 3D point cloud data contains points from different objects, the RANSAC (Road Point Acquisition and Retrieval System) algorithm is used to identify and extract the road surface point cloud data, which includes information about the road surface traveled by vehicles. A minimum number of points are randomly selected from the road surface point cloud data for plane fitting. For plane fitting, three points are sufficient. The plane equation for the 3D point cloud data is: Ax + By + Cz + D = 0, where A, B, C, and D are plane parameters, which can be estimated using the least squares method from the selected three points. The formula for the distance from a point to the plane is: Where (x0, y0, z0) are the coordinates of any point in the 3D spatial point cloud data. Furthermore, the determination of interior and exterior points is as follows: if Distance ≤ ε, the point is an interior point; otherwise, it is an exterior point, where ε is a set distance threshold. In some embodiments, the vehicle can be a fuel-powered vehicle or a new energy vehicle.

[0067] S120, extract road surface features based on target point cloud data, and identify pothole areas in the road surface based on road surface features. Road surface features include at least one of road surface height features, road surface curvature features, and road surface slope features.

[0068] S130, associating the dented area with the vehicle's driving status, and controlling the vehicle seat's shock absorption based on the association result; wherein, the vehicle's driving status includes at least one of vehicle speed, vehicle position, and vehicle steering angle.

[0069] In one embodiment of this application, if the vehicle seat includes a magnetorheological seat, the process of controlling the vibration damping of the vehicle seat based on the correlation result includes: calculating a target current for adjusting the damping response of the magnetorheological damper based on the correlation result between the pit area and the vehicle driving state, and adjusting the magnetorheological damper based on the target current to obtain the damping force fed back by the magnetorheological damper; reading the vibration amplitude based on the damping force feedback from the seat acceleration sensor, and updating the damping force when the vibration amplitude is not within a preset amplitude range, until the vibration amplitude corresponding to the updated damping force is within the preset amplitude range. In some embodiments, the process of controlling the vibration damping of the magnetorheological seat based on the correlation result between the pit area and the vehicle driving state may be: based on the vehicle speed v k and pit depth h pothole,k Generate the corresponding target current I target To adjust the damping response of the magnetorheological damper; including: I target =K v v k +K h h pothole,k In the formula, K v K is the vehicle speed control gain. h Gain is controlled by the pit depth. The generated target current I... target This technology is applied to the control of magnetorheological dampers to adjust the seat's damping effect in real time. The magnetorheological damper adjusts its internal damping characteristics according to the input current, providing a damping force corresponding to the target current; including: F actual =Map(I target ), where F actual The damping force is generated by the magnetorheological damper based on the target current. Map(I) is the mapping relationship between the current and the output force, which can be obtained experimentally. Finally, the vibration amplitude is fed back by the seat acceleration sensor to determine whether the vibration amplitude is within the allowable range. If not, the damping force of the magnetorheological damper is updated until the vibration amplitude corresponding to the updated damping force is within the preset range. Therefore, this method can identify potholes in advance and adjust the damping in real time, effectively reducing vibration impact and providing passengers with a smoother riding experience in complex road conditions. At the same time, by identifying potholes and precisely adjusting the damping, the frequency and amplitude of seat vibration are significantly reduced, thereby reducing fatigue caused by long-distance driving. Moreover, the rapid response capability of the magnetorheological damping system allows the seat to adjust to the optimal damping state in a very short time, more effectively mitigating the impact of uneven roads on passengers.

[0070] In one embodiment of this application, the process of extracting road surface features based on target point cloud data includes:

[0071] For the coordinates of each point in the road surface point cloud data, perform 3D spatial surface fitting; including: In the formula, (x,y) represents the coordinates of each point in the road surface point cloud data, z represents the height of the fitted surface, and a0,...,a5 represent the fitting parameters. Indicates the fitting error;

[0072] Based on the maximum and minimum height values ​​of the fitted surface, the height difference of the fitted surface is calculated and used as a road surface height feature to measure road surface undulation; including: Δz=z1-z2; where Δz represents the height difference of the fitted surface, z1 represents the maximum height value of the fitted surface, and z2 represents the minimum height value of the fitted surface.

[0073] Calculate the curvature of the fitted surface and use it as a feature of road surface curvature; including: In the formula, κ represents the curvature of the fitted surface;

[0074] The slope is calculated based on the gradient of the fitted surface, and the slope is used as a feature of the road surface gradient; including: In the formula, The gradient of the fitted surface in the x and y directions represents the change of the road surface in these directions; the slope represents the inclination.

[0075] Therefore, in the process of extracting road surface features from target point cloud data, surface fitting can be used to accurately model the road surface point cloud, extracting features such as road surface undulations, pothole locations, and depths. Thus, by using fitting methods to fit surfaces, the shape and changes of the road surface can be analyzed, outputting road surface features such as undulations, curvature, and slope, especially accurately extracting road surface features in abnormal terrain areas such as potholes.

[0076] In one embodiment of this application, the process of identifying pothole areas in the road surface based on road surface features includes:

[0077] Calculate road surface point P i (x i ,y i ,z i The residual values ​​of the fitted surface corresponding to the road surface features; including: In the formula, Representing point (x) i ,y i The corresponding fitted surface height value, d i Represents point P on the road surface i (x i ,y i ,z i The residual values ​​of the fitted surface corresponding to the road surface features;

[0078] The residual values ​​of all road surface points are compared with the preset threshold T thCompare the results and assign residual values ​​greater than a preset threshold T. th Points on the road surface are marked as outliers; spatial clustering is performed on all marked outliers, and each clustering result is treated as a pit region to obtain the pit regions in the road surface. A preset threshold T is used. th It can be used to distinguish smooth areas from pitted or raised areas. If point P i Differences d i If the value is greater than the threshold, the point is considered to be located in a pit or convex region, meaning d can be... i >T th Points with significant differences are marked as outliers. Based on the surface difference detection results, all points with differences greater than a threshold are marked, indicating potential pits or bumps. For pits, these points are typically located where the height of the fitted surface is less than the height of the pitted surface. Points with large differences and heights less than the fitted surface are marked as pits. When performing spatial clustering on all marked outliers, the K-means clustering algorithm can be used to divide the detected outliers into different regions. Through spatial clustering, different pit regions are identified, with each region representing an independent pit.

[0079] Specifically, the process of using the K-means clustering algorithm to divide detected outliers into different regions can be as follows:

[0080] (1) Initialize the cluster center.

[0081] Choose k initial cluster centers (also called centroids). These initial points can be chosen randomly, let the point set be X = {x1, x2, ..., x...} n}, where x i These are the coordinates of the road surface points.

[0082] (2) Calculate the distance from each point to the cluster center.

[0083] For each road surface point x, calculate its distance from each cluster center c. j The distance is usually measured using Euclidean distance. Where, x i =(x i1 ,x i2 ,…,x ip ) represents the coordinates of a point on the road surface, c j =(c j1 ,c j2 ,…,c jp ) are the coordinates of the cluster center.

[0084] (3) Assign each point to the nearest cluster center.

[0085] For each point x i Assigned to the nearest cluster center cj The corresponding cluster C j C j =x i :d(x i ,c j )≤d(x i ,c l )l≠j.

[0086] (4) Update the cluster center.

[0087] Calculate the new center of each cluster by taking the average coordinates of all points within each cluster as the new cluster center; this includes: Among them, |C j | is cluster C j The number of points in the array.

[0088] Repeat steps (2) to (4) until the cluster centers no longer change significantly or the maximum number of iterations is reached. The usual convergence condition is that the change in cluster centers is less than a set threshold ε. in, This represents the Euclidean distance between the centers of the old and new clusters.

[0089] By using the K-means clustering algorithm, the detected outliers are divided into different regions, thereby identifying different pit regions.

[0090] In one embodiment of this application, it may further include: calculating the center position (x) of the pit region based on the pit region point cloud data. center ,y center );include: In the formula, n represents the number of point clouds in the pit area;

[0091] Based on the lowest point P of the pit area min (x min ,y min ,z min ), calculate the depth d of the pit region. pothole ;include: In the formula, Representing point (x) min ,y min The corresponding fitted surface height, z min Representing point (x) min ,y min The actual height of the pit. That is, the depth of the pit refers to the difference between the height of the lowest point within the pit region and the height of the corresponding point on the fitted surface. Furthermore, to further analyze the severity of the pit, the maximum depth of the region can also be calculated by selecting the depths of all points within the region and taking the maximum value.

[0092] In one embodiment of this application, after obtaining the pothole region in the road surface, the method may further include: establishing the local surface equation of the pothole region, that is, the surface fitting of the pothole region can be performed using quadratic surface fitting, to obtain the local surface equation of the pothole region; where: z(x,y)=a0+a1x+a2y+a3x 2 +a4xy+a5y 2 ;

[0093] Calculate the local curvature of the pit region using the local surface equation; including: In the formula, Curvature represents the local curvature of the pit region, and f x ,f y f represents the surface partial derivative of the pit region. xx ,f yy ,f xy This represents the second-order partial derivative of the pit region.

[0094] In one embodiment of this application, the process of associating the dent area with the vehicle's driving state includes: obtaining the vehicle position (x) at time k. k y k The vehicle heading angle θ at time k k The vehicle speed v at time k k The vehicle steering angle δ at time k k The position d of the crater at time k pothole,k The pit depth h at time k pothole,k ;

[0095] Based on the vehicle position (x) at time k k y k The vehicle heading angle θ at time k k The vehicle speed v at time k k The vehicle steering angle δ at time k k The position d of the crater at time k pothole,k The pit depth h at time k pothole,k Define the state vector x k ;include:

[0096] The state vector x k The data is input into a pre-defined or real-time determined observation function to correlate the pothole area with the vehicle's driving status; including: z k =h(x k )+v k ; In the formula, h() is the observation function, v k It measures noise.

[0097] Furthermore, vehicle dynamics models can be used to describe state evolution, thereby predicting the vehicle's driving state; including: x k+1 =f(x) k ,u k )+w k Where f(·) is the nonlinear state transition function, u k It is the control input (such as acceleration, steering angular velocity), w k It is process noise. Specifically, it can be expressed as:

[0098]

[0099] Where L is the vehicle wheelbase, a k For acceleration, ω k Let d be the angular velocity of the steering direction. pothole,k -v k The relative distance between the Δt dent and the vehicle decreases as the vehicle moves.

[0100] At the same time, in defining the state vector x k Then, the state vector x can also be... k Extended Kalman filtering was performed to obtain a real-time state vector containing ditch information and vehicle driving status. The specific steps of extended Kalman filtering are as follows:

[0101] ①Prediction steps

[0102] State prediction: Predicting the state at the next time step using state transition equations; including:

[0103] Covariance prediction: Predicted state covariance matrix P k∣k-1 ;include: in, Q is the Jacobian matrix of the state transition matrix. k It is the process noise covariance matrix.

[0104] ②Update steps

[0105] Kalman gain calculation: Calculate the Kalman gain; including: in, R is the Jacobian matrix of the observation model. k It is the measurement noise covariance matrix.

[0106] State update: Correcting the predicted state using observed data; including:

[0107] Covariance Update: Updates the state covariance matrix; includes: P k =(IK k H k )Pk∣k-1 .

[0108] After performing state estimation using extended Kalman filtering, a real-time state vector containing ditch information and vehicle driving state is obtained.

[0109] In another exemplary embodiment of this application, the embodiment also provides a seat control method, which can be applied to a magnetorheological seat. The seat control method includes a perception and recognition process and a decision control process. The perception and recognition process is as follows: Figure 2 As shown, the decision control process is as follows: Figure 3 As shown. In Figure 2 In this system, a lidar system can acquire three-dimensional point cloud data of the surrounding environment by emitting a laser beam and receiving reflected light. After identifying pothole areas using the acquired three-dimensional point cloud data, the shock absorption system pre-adjusts the seat's damping characteristics. The lidar system scans and analyzes the road surface in real time to identify the location, depth, shape, and other features of potholes, outputting information such as the pothole's spatial coordinates, depth, shape, and curvature, as well as parameters related to the vehicle's current driving state (e.g., speed, acceleration). The pothole identification data is synchronized with the vehicle's real-time driving state (e.g., speed, direction of travel, acceleration, seat load). Data is transmitted via the vehicle control system's CAN (Controller Area Network) bus. Finally, the system integrates the pothole features and the vehicle's driving state data to perform forward-looking calculations for shock absorption control, determining the required damping characteristics, such as damping value and response time, when approaching a pothole. Figure 3 In this system, dent information identified by LiDAR can be fused with data from other sensors (such as accelerometers, GPS, and IMU) and combined with the vehicle's real-time driving status (such as speed and steering angle) to generate a dynamic damping adjustment strategy. For example, a fusion algorithm (extended Kalman filter) can be used to combine dent information with the vehicle's real-time driving status (such as speed and steering angle) for comprehensive analysis, forming a complete environment and state model, and generating a dynamic magnetorheological seat damping control strategy. Then, the integrated model of dent information and vehicle state data provides real-time feedback to the damping system, guiding the adjustment of the magnetorheological seat. Finally, the dent identification and modeling results are transmitted to the magnetorheological seat damping control system in real time, thereby achieving optimal comfort and damping effect. Figure 2 and Figure 3 The processes involved in lidar data acquisition, point cloud data preprocessing, road surface point cloud data separation, road surface feature extraction, pothole area detection and identification, and seat shock absorption control can be referred to in the other embodiments mentioned above, and will not be repeated here.

[0110] In summary, this application provides a vehicle seat control method that acquires target point cloud data, extracts road surface features from the target point cloud data, identifies pothole areas on the road surface based on the road surface features, and finally associates the pothole areas with the vehicle's driving state, and controls the vehicle seat's vibration damping based on the association result. Therefore, this method, by associating pothole areas with the vehicle's driving state to control the vehicle seat's vibration damping, not only allows the vehicle seat's vibration damping system to adapt to complex road conditions such as potholes, improving the adaptability and effectiveness of seat vibration damping, but also effectively reduces the vibration impact on the vehicle seat, providing passengers with a smoother riding experience under complex road conditions. Simultaneously, by controlling the vehicle seat's vibration damping, this method reduces the impact of road impacts on passengers, improves vehicle handling stability and passenger safety, reduces driver and passenger fatigue and discomfort during long-distance driving, and enhances driving comfort. Furthermore, this method can identify potholes in advance and adjust damping in real time, effectively reducing vibration impact and providing passengers with a smoother riding experience under complex road conditions. Meanwhile, by identifying potholes and precisely adjusting damping, the frequency and amplitude of seat vibration are significantly reduced, thereby reducing fatigue from long journeys. Furthermore, the rapid response of the magnetorheological damping system allows the seat to adjust to its optimal damping state in a very short time, more effectively mitigating the impact of road unevenness on passengers. Moreover, by optimizing the control strategy of the magnetorheological damping system, energy consumption and component wear caused by frequent adjustments are reduced, extending the system's lifespan while ensuring efficient energy utilization. Therefore, this method combines a predictive mode and a real-time feedback mode. This dual-mode control ensures that even in the event of predictive failure or misjudgment, precise adjustments can still be made through real-time feedback, thus balancing the accuracy and fault tolerance of the damping system's response.

[0111] In another exemplary embodiment of this application, such as Figure 4 As shown, this embodiment also provides a vehicle seat control system, including:

[0112] The data acquisition module 410 is used to acquire target point cloud data, which includes road surface point cloud data. In some embodiments, the process of acquiring road surface point cloud data can be achieved by using a pre-configured lidar on the vehicle to perceive and identify three-dimensional spatial data on the road surface, thereby obtaining lidar three-dimensional point cloud data; preprocessing the lidar three-dimensional point cloud data, and segmenting the point cloud based on the preprocessing results to obtain the road surface point cloud data; wherein, preprocessing includes, but is not limited to, denoising, filtering, and downsampling. Specifically, as an example, lidar can be used to perceive and identify three-dimensional spatial data on the road surface in real time, capturing minute changes in the road surface, and outputting three-dimensional spatial point cloud data composed of multiple three-dimensional coordinate points, each of which represents a certain location point on the road surface. The acquired three-dimensional spatial point cloud data is then subjected to denoising, filtering, and downsampling processing. Denoising removes environmental interference or error data, filtering removes unwanted distant points, and downsampling reduces computational load. Clear and sparse point cloud data is output, retaining important road surface features. Road surface points are then separated from the three-dimensional spatial point cloud data. Since 3D point cloud data contains points from different objects, the RANSAC (Road Point Acquisition and Retrieval System) algorithm is used to identify and extract the road surface point cloud data, which includes information about the road surface traveled by vehicles. A minimum number of points are randomly selected from the road surface point cloud data for plane fitting. For plane fitting, three points are sufficient. The plane equation for the 3D point cloud data is: Ax + By + Cz + D = 0, where A, B, C, and D are plane parameters, which can be estimated using the least squares method from the selected three points. The formula for the distance from a point to the plane is: Where (x0, y0, z0) are the coordinates of any point in the 3D spatial point cloud data. Furthermore, the determination of interior and exterior points is as follows: if Distance ≤ ε, the point is an interior point; otherwise, it is an exterior point, where ε is a set distance threshold. In some embodiments, the vehicle can be a fuel-powered vehicle or a new energy vehicle.

[0113] The pothole recognition module 420 is used to extract road surface features based on target point cloud data and identify pothole areas in the road surface based on the road surface features. The road surface features include at least one of road surface height features, road surface curvature features, and road surface slope features.

[0114] The shock absorption control module 430 is used to associate the dent area with the vehicle's driving state and to control the shock absorption of the vehicle seat based on the association result; wherein, the vehicle driving state includes at least one of vehicle speed, vehicle position, and vehicle steering angle.

[0115] In one embodiment of this application, if the vehicle seat includes a magnetorheological seat, the process of controlling the vibration damping of the vehicle seat based on the correlation result includes: calculating a target current for adjusting the damping response of the magnetorheological damper based on the correlation result between the pit area and the vehicle driving state, and adjusting the magnetorheological damper based on the target current to obtain the damping force fed back by the magnetorheological damper; reading the vibration amplitude based on the damping force feedback from the seat acceleration sensor, and updating the damping force when the vibration amplitude is not within a preset amplitude range, until the vibration amplitude corresponding to the updated damping force is within the preset amplitude range. In some embodiments, the process of controlling the vibration damping of the magnetorheological seat based on the correlation result between the pit area and the vehicle driving state may be: based on the vehicle speed v k and pit depth h pothole,k Generate the corresponding target current I target To adjust the damping response of the magnetorheological damper; including: I target =K v v k +K h h pothole,k In the formula, K v K is the vehicle speed control gain. h Gain is controlled by the pit depth. The generated target current I... target This technology is applied to the control of magnetorheological dampers to adjust the seat's damping effect in real time. The magnetorheological damper adjusts its internal damping characteristics according to the input current, providing a damping force corresponding to the target current; including: F actual =Map(I target ), where F actual The damping force is generated by the magnetorheological damper based on the target current. Map(I) is the mapping relationship between the current and the output force, which can be obtained experimentally. Finally, the vibration amplitude is fed back by the seat acceleration sensor to determine whether the vibration amplitude is within the allowable range. If not, the damping force of the magnetorheological damper is updated until the vibration amplitude corresponding to the updated damping force is within the preset range. Therefore, this method can identify potholes in advance and adjust the damping in real time, effectively reducing vibration impact and providing passengers with a smoother riding experience under complex road conditions. At the same time, by identifying potholes and precisely adjusting the damping, the frequency and amplitude of seat vibration are significantly reduced, thereby reducing fatigue caused by long-distance driving. Moreover, the rapid response capability of the magnetorheological damping system allows the seat to adjust to the optimal damping state in a very short time, more effectively mitigating the impact of uneven roads on passengers.

[0116] In one embodiment of this application, the process of extracting road surface features based on target point cloud data includes:

[0117] For the coordinates of each point in the road surface point cloud data, perform 3D spatial surface fitting; including: In the formula, (x,y) represents the coordinates of each point in the road surface point cloud data, z represents the height of the fitted surface, and a0,...,a5 represent the fitting parameters. Indicates the fitting error;

[0118] Based on the maximum and minimum height values ​​of the fitted surface, the height difference of the fitted surface is calculated and used as a road surface height feature to measure road surface undulation; including: Δz=z1-z2; where Δz represents the height difference of the fitted surface, z1 represents the maximum height value of the fitted surface, and z2 represents the minimum height value of the fitted surface.

[0119] Calculate the curvature of the fitted surface and use it as a feature of road surface curvature; including: In the formula, κ represents the curvature of the fitted surface;

[0120] The slope is calculated based on the gradient of the fitted surface, and the slope is used as a feature of the road surface gradient; including: In the formula, The gradient of the fitted surface in the x and y directions represents the change of the road surface in these directions; the slope represents the inclination.

[0121] Therefore, in the process of extracting road surface features from target point cloud data, surface fitting can be used to accurately model the road surface point cloud, extracting features such as road surface undulations, pothole locations, and depths. Thus, by using fitting methods to fit surfaces, the shape and changes of the road surface can be analyzed, outputting road surface features such as undulations, curvature, and slope, especially accurately extracting road surface features in abnormal terrain areas such as potholes.

[0122] In one embodiment of this application, the process of identifying pothole areas in the road surface based on road surface features includes:

[0123] Calculate road surface point P i (x i ,y i ,z i The residual values ​​of the fitted surface corresponding to the road surface features; including: In the formula, Representing point (x) i ,y i The corresponding fitted surface height value, d i Represents point P on the road surface i (x i ,y i ,z i The residual values ​​of the fitted surface corresponding to the road surface features;

[0124] The residual values ​​of all road surface points are compared with the preset threshold T thCompare the results and assign residual values ​​greater than a preset threshold T. th Points on the road surface are marked as outliers; spatial clustering is performed on all marked outliers, and each clustering result is treated as a pit region to obtain the pit regions in the road surface. A preset threshold T is used. th It can be used to distinguish smooth areas from pitted or raised areas. If point P i Differences d i If the value is greater than the threshold, the point is considered to be located in a pit or convex region, meaning d can be... i >T th Points with significant differences are marked as outliers. Based on the surface difference detection results, all points with differences greater than a threshold are marked, indicating potential pits or bumps. For pits, these points are typically located where the height of the fitted surface is less than the height of the pitted surface. Points with large differences and heights less than the fitted surface are marked as pits. When performing spatial clustering on all marked outliers, the K-means clustering algorithm can be used to divide the detected outliers into different regions. Through spatial clustering, different pit regions are identified, with each region representing an independent pit.

[0125] Specifically, the process of using the K-means clustering algorithm to divide detected outliers into different regions can be as follows:

[0126] (1) Initialize the cluster center.

[0127] Choose k initial cluster centers (also called centroids). These initial points can be chosen randomly, let the point set be X = {x1, x2, ..., x...} n}, where x i These are the coordinates of the road surface points.

[0128] (2) Calculate the distance from each point to the cluster center.

[0129] For each road surface point x, calculate its distance from each cluster center c. j The distance is usually measured using Euclidean distance. Where, x i =(x i1 ,x ii2 ,…,x ip ) represents the coordinates of a point on the road surface, c j =(c j1 ,c j2 ,…,c jp ) are the coordinates of the cluster center.

[0130] (3) Assign each point to the nearest cluster center.

[0131] For each point x i Assigned to the nearest cluster center cj The corresponding cluster C j C j =x i :d(x i ,c j )≤d(x i ,c l )l≠j.

[0132] (4) Update the cluster center.

[0133] Calculate the new center of each cluster by taking the average coordinates of all points within each cluster as the new cluster center; this includes: Among them, |C j | is cluster C j The number of points in the array.

[0134] Repeat steps (2) to (4) until the cluster centers no longer change significantly or the maximum number of iterations is reached. The usual convergence condition is that the change in cluster centers is less than a set threshold ε. in, This represents the Euclidean distance between the centers of the old and new clusters.

[0135] By using the K-means clustering algorithm, the detected outliers are divided into different regions, thereby identifying different pit regions.

[0136] In one embodiment of this application, it may further include: calculating the center position (x) of the pit region based on the pit region point cloud data. center ,y center );include: In the formula, n represents the number of point clouds in the pit area;

[0137] Based on the lowest point P of the pit area min (x min ,y min ,z min ), calculate the depth d of the pit region. pothole ;include: In the formula, Representing point (x) min ,y min The corresponding fitted surface height, z min Representing point (x) min ,y min The actual height of the pit. That is, the depth of the pit refers to the difference between the height of the lowest point within the pit region and the height of the corresponding point on the fitted surface. Furthermore, to further analyze the severity of the pit, the maximum depth of the region can also be calculated by selecting the depths of all points within the region and taking the maximum value.

[0138] In one embodiment of this application, after obtaining the pothole region in the road surface, the method may further include: establishing the local surface equation of the pothole region, that is, the surface fitting of the pothole region can be performed using quadratic surface fitting, to obtain the local surface equation of the pothole region; where: z(x,y)=a0+a1x+a2y+a3x 2 +a4xy+a5y 2 ;

[0139] Calculate the local curvature of the pit region using the local surface equation; including: In the formula, Curvature represents the local curvature of the pit region, and f x ,f y f represents the surface partial derivative of the pit region. xx ,f yy ,f xy This represents the second-order partial derivative of the pit region.

[0140] In one embodiment of this application, the process of associating the dent area with the vehicle's driving state includes: obtaining the vehicle position (x) at time k. k y k The vehicle heading angle θ at time k k The vehicle speed v at time k k The vehicle steering angle δ at time k k The position d of the crater at time k pothole,k The pit depth h at time k pothole,k ;

[0141] Based on the vehicle position (x) at time k k y k The vehicle heading angle θ at time k k The vehicle speed v at time k k The vehicle steering angle δ at time k k The position d of the crater at time k pothole,k The pit depth h at time k pothole,k Define the state vector x k ;include:

[0142] The state vector x k The data is input into a pre-defined or real-time determined observation function to correlate the pothole area with the vehicle's driving status; including: z k =h(x k )+v k ; In the formula, h() is the observation function, v k It measures noise.

[0143] Furthermore, vehicle dynamics models can be used to describe state evolution, thereby predicting the vehicle's driving state; including: x k+1 =f(x) k ,u k )+w k Where f(·) is the nonlinear state transition function, u k It is the control input (such as acceleration, steering angular velocity), w k It is process noise. Specifically, it can be expressed as:

[0144]

[0145] Where L is the vehicle wheelbase, a k For acceleration, ω k Let d be the angular velocity of the steering direction. pothole,k -v k The relative distance between the Δt dent and the vehicle decreases as the vehicle moves.

[0146] At the same time, in defining the state vector x k Then, the state vector x can also be... k Extended Kalman filtering was performed to obtain a real-time state vector containing ditch information and vehicle driving status. The specific steps of extended Kalman filtering are as follows:

[0147] ①Prediction steps

[0148] State prediction: Predicting the state at the next time step using state transition equations; including:

[0149] Covariance prediction: Predicted state covariance matrix P k∣k-1 ;include: in, Q is the Jacobian matrix of the state transition matrix. k It is the process noise covariance matrix.

[0150] ②Update steps

[0151] Kalman gain calculation: Calculate the Kalman gain; including: in, R is the Jacobian matrix of the observation model. k It is the measurement noise covariance matrix.

[0152] State update: Correcting the predicted state using observed data; including:

[0153] Covariance Update: Updates the state covariance matrix; includes: P k =(IK k H k )Pk∣k-1 .

[0154] After performing state estimation using extended Kalman filtering, a real-time state vector containing ditch information and vehicle driving state is obtained.

[0155] In another exemplary embodiment of this application, a seat control system is also provided, which can be applied to a magnetorheological seat. The seat control system includes a perception and recognition process and a decision control process. The perception and recognition process is as follows: Figure 2 As shown, the decision control process is as follows: Figure 3 As shown. In Figure 2 In this system, a lidar system can acquire three-dimensional point cloud data of the surrounding environment by emitting a laser beam and receiving reflected light. After identifying pothole areas using the acquired three-dimensional point cloud data, the shock absorption system pre-adjusts the seat's damping characteristics. The lidar system scans and analyzes the road surface in real time to identify the location, depth, shape, and other features of potholes, outputting information such as the pothole's spatial coordinates, depth, shape, and curvature, as well as parameters related to the vehicle's current driving state (e.g., speed, acceleration). The pothole identification data is synchronized with the vehicle's real-time driving state (e.g., speed, direction of travel, acceleration, seat load). Data is transmitted via the vehicle control system's CAN (Controller Area Network) bus. Finally, the system integrates the pothole features and the vehicle's driving state data to perform forward-looking calculations for shock absorption control, determining the required damping characteristics, such as damping value and response time, when approaching a pothole. Figure 3 In this system, dent information identified by LiDAR can be fused with data from other sensors (such as accelerometers, GPS, and IMU) and combined with the vehicle's real-time driving status (such as speed and steering angle) to generate a dynamic damping adjustment strategy. For example, a fusion algorithm (extended Kalman filter) can be used to combine dent information with the vehicle's real-time driving status (such as speed and steering angle) for comprehensive analysis, forming a complete environment and state model, and generating a dynamic magnetorheological seat damping control strategy. Then, the integrated model of dent information and vehicle state data provides real-time feedback to the damping system, guiding the adjustment of the magnetorheological seat. Finally, the dent identification and modeling results are transmitted to the magnetorheological seat damping control system in real time, thereby achieving optimal comfort and damping effect. Figure 2 and Figure 3 The processes involved in lidar data acquisition, point cloud data preprocessing, road surface point cloud data separation, road surface feature extraction, pothole area detection and identification, and seat shock absorption control can be referred to in the other embodiments mentioned above, and will not be repeated here.

[0156] In summary, this application provides a vehicle seat control system that acquires target point cloud data, extracts road surface features based on the target point cloud data, identifies pothole areas on the road surface based on the road surface features, and finally associates the pothole areas with the vehicle's driving state, and performs shock absorption control on the vehicle seat based on the association result. Therefore, this system, by associating pothole areas with the vehicle's driving state to control the vehicle seat's shock absorption, not only allows the vehicle seat's shock absorption system to adapt to complex road conditions such as potholes, improving the adaptability and effectiveness of seat shock absorption, but also effectively reduces the vibration impact on the vehicle seat, providing passengers with a smoother riding experience under complex road conditions. Simultaneously, by controlling the vehicle seat's shock absorption, this system reduces the impact of road impacts on passengers, improves vehicle handling stability and passenger safety, reduces driver and passenger fatigue and discomfort during long-distance driving, and enhances driving and riding comfort. Furthermore, this system can identify potholes in advance and adjust damping in real time, effectively reducing vibration impact and providing passengers with a smoother riding experience under complex road conditions. Meanwhile, by identifying potholes and precisely adjusting damping, the frequency and amplitude of seat vibration are significantly reduced, thereby reducing fatigue from long drives. Furthermore, the rapid response of the magnetorheological damping system allows the seat to adjust to optimal damping in a very short time, more effectively mitigating the impact of road unevenness on passengers. In addition, by optimizing the control strategy of the magnetorheological damping system, energy consumption and component wear caused by frequent adjustments are reduced, extending the lifespan of the system while ensuring efficient energy utilization. Therefore, this system combines a predictive mode and a real-time feedback mode. This dual-mode control ensures that even in the event of predictive failure or misjudgment, precise adjustments can still be made through real-time feedback, thus balancing the accuracy and fault tolerance of the damping system's response.

[0157] It should be noted that the vehicle seat control system provided in the above embodiments and the vehicle seat control method provided in the above embodiments belong to the same concept. The specific way in which the vehicle seat control method performs its operation has been described in detail in the above method embodiments, and will not be repeated here. In practical applications, the vehicle seat control system provided in the above embodiments can be assigned to different functional modules as needed. That is, the internal structure of the vehicle seat control system can be divided into different functional modules, and then all or part of the functions of the corresponding functional modules can be implemented through the vehicle seat control method described in the above embodiments. No specific limitations are imposed here.

[0158] This application also provides a computer device, which may include a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to cause the computer device to perform... Figure 1 The steps of the vehicle seat control method described above. Figure 5 A schematic diagram of the structure of a computer device 1000 is shown. (See attached diagram.) Figure 5 As shown, the computer device 1000 includes: a processor 1010, a memory 1020, a power supply 1030, a display unit 1040, and an input unit 1060.

[0159] The processor 1010 is the control center of the computer device 1000. It connects various components via interfaces and lines, and executes various functions of the computer device 1000 by running or executing computer programs / instructions stored in the memory 1020, thereby providing overall monitoring of the computer device 1000. In this embodiment, when the processor 1010 calls the computer program stored in the memory 1020, it executes... Figure 1 The steps of the vehicle seat control method are described above. Optionally, the processor 1010 may include one or more processing units; preferably, the processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. In some embodiments, the processor and memory can be implemented on a single chip; in some embodiments, they can also be implemented separately on independent chips.

[0160] The memory 1020 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, various applications, etc.; the data storage area may store instruction data created based on the use of the computer device 1000, etc. In addition, the memory 1020 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0161] The computer device 1000 also includes a power supply 1030 (such as a battery) that supplies power to various components. The power supply can be logically connected to the processor 1010 through a power management system, thereby enabling the management of charging, discharging, and power consumption.

[0162] The display unit 1040 can be used to display information input by the user or information provided to the user, as well as various menus of the computer device 1000. In this embodiment, it is mainly used to display the display interfaces of various applications in the computer device 1000, as well as text, images, and other objects displayed on the display interfaces. The display unit 1040 may include a display panel 1050. The display panel 1050 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0163] The input unit 1060 can be used to receive information such as numbers or characters input by the user. The input unit 1060 may include a touch panel 1070 and other input devices 1080. The touch panel 1070, also known as a touch screen, can collect touch operations on or near the touch panel 1070 by the user (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel 1070).

[0164] Specifically, the touch panel 1070 can detect user touch operations and the signals generated by these operations, convert them into touch point coordinates, send them to the processor 1010, and receive and execute commands from the processor 1010. Furthermore, the touch panel 1070 can be implemented using various types of touch technologies, including resistive, capacitive, infrared, and surface acoustic wave. Other input devices 1080 can include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0165] Of course, the touch panel 1070 can cover the display panel 1050. When the touch panel 1070 detects a touch operation on or near it, it transmits the information to the processor 1010 to determine the type of touch event. Subsequently, the processor 1010 provides corresponding visual output on the display panel 1050 based on the type of touch event. Although in Figure 5 In this embodiment, the touch panel 1070 and the display panel 1050 are two separate components to realize the input and output functions of the computer device 1000. However, in some embodiments, the touch panel 1070 and the display panel 1050 can be integrated to realize the input and output functions of the computer device 1000.

[0166] The computer device 1000 may also include one or more sensors, such as pressure sensors, gravity acceleration sensors, proximity sensors, etc. Of course, depending on the specific application requirements, the computer device 1000 may also include other components such as cameras.

[0167] This application also provides a computer-readable storage medium storing a computer program / instructions. When executed by a processor, the computer program / instructions enable the aforementioned device to perform the functions described in this application. Figure 1 The steps of the vehicle seat control method described above.

[0168] It will be understood by those skilled in the art that Figure 5This is merely an example of a computer device and does not constitute a limitation on the device. The device may include more or fewer components than illustrated, or a combination of certain components, or different components. For ease of description, the above sections are divided into modules (or units) according to their functions and described separately. Of course, in implementing this application, the functions of each module (or unit) can be implemented in one or more software or hardware components.

[0169] Those skilled in the art will understand that this application may take the form of a computer program product embodied 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. This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application, and should be understood to be achievable by computer program instructions for each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams. These computer program instructions may be applied to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing 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 functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus 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.

[0170] It should be noted that the above embodiments, in collecting, storing, using, processing, transmitting, providing, disclosing, and deleting relevant data (such as 3D spatial point cloud data, road surface point cloud data, etc.), are carried out with or with the user's consent. For example, the 3D spatial point cloud data and road surface point cloud data are obtained with the user's knowledge and consent; or they are provided voluntarily by the user after reading the relevant instructions; or they are actively authorized / provided / uploaded by the user when using some or all of the functions described in the above embodiments; or they are obtained through other means or channels with the user's consent.

[0171] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A vehicle seat control method, characterized in that, The method includes the following steps: Acquire target point cloud data, wherein the target point cloud data includes road surface point cloud data; Road surface features are extracted from target point cloud data, and pothole areas in the road surface are identified based on the road surface features. The road surface features include at least one of road surface height features, road surface curvature features, and road surface slope features. The indentation area is correlated with the vehicle's driving status, and the vehicle seat is subjected to shock absorption control based on the correlation result; wherein, the vehicle's driving status includes at least one of vehicle speed, vehicle position, and vehicle steering angle. The process of extracting road surface features from target point cloud data includes: For the coordinates of each point in the road surface point cloud data, perform three-dimensional spatial surface fitting; including: In the formula, (x, y) represents the coordinates of each point cloud in the road surface point cloud data, z represents the height of the fitted surface, and a0,...,a5 represent the fitting parameters. Indicates the fitting error; Based on the maximum and minimum height values ​​of the fitted surface, the height difference between the fitted surfaces is calculated, and this height difference is used as a road surface height feature; including: Δz = z1 - z2; In the formula, Δz represents the height difference of the fitted surface, z1 represents the maximum height value of the fitted surface, and z2 represents the minimum height value of the fitted surface; Calculating the curvature of the fitted surface and using the curvature of the fitted surface as a feature of road surface curvature; including: In the formula, κ represents the curvature of the fitted surface; The slope is calculated based on the gradient of the fitted surface, and the slope is used as a feature of the road surface gradient; including: In the formula, The slope represents the gradient of the fitted surface in the x and y directions; the slope represents the inclination.

2. The vehicle seat control method according to claim 1, characterized in that, If the vehicle seat includes a magnetorheological seat, the process of controlling the shock absorption of the vehicle seat based on the correlation results includes: Based on the correlation between the pitted area and the vehicle's driving state, a target current for adjusting the damping response of the magnetorheological damper is calculated, and the magnetorheological damper is adjusted based on the target current to obtain the damping force fed back by the magnetorheological damper. The vibration amplitude of the seat acceleration sensor based on the damping force feedback is read, and the damping force is updated when the vibration amplitude is not within the preset range, until the vibration amplitude corresponding to the updated damping force is within the preset range.

3. The vehicle seat control method according to claim 1 or 2, characterized in that, The process of identifying pothole areas in the road surface based on the aforementioned road surface features includes: Calculate road surface point P i (x i ,y i ,z i The residual values ​​of the fitted surface corresponding to the road surface features; including: In the formula, Representing point (x) i ,y i The corresponding fitted surface height value, d i Represents point P on the road surface i (x i ,y i ,z i The residual value of the fitted surface corresponding to the road surface feature; The residual values ​​of all road surface points are compared with the preset threshold T th Compare the results and assign residual values ​​greater than a preset threshold T. th Road surface points are marked as anomalies; Spatial clustering is performed on all marked outliers, and each clustering result is taken as a pit region to obtain the pit regions in the road surface.

4. The vehicle seat control method according to claim 3, characterized in that, The method further includes: Calculate the center position (x) of the pit area based on the point cloud data of the pit area. center ,y center );include: In the formula, n represents the number of point clouds in the pit area; Based on the lowest point P of the pit area min (x min ,y min ,z min ), calculate the depth d of the pit region. pothole ;include: In the formula, Representing point (x) min ,y min The corresponding fitted surface height, z min Representing point (x) min ,y min The actual height of the ).

5. The vehicle seat control method according to claim 4, characterized in that, After obtaining the pothole areas in the road surface, the method further includes: Establish the local surface equation for the pit region; including: z(x,y)=a0+a1x+a2y+a3x 2 +a4xy+a5y 2 ; Calculate the local curvature of the pit region using the local surface equation; including: In the formula, Curvature represents the local curvature of the pit region, and f x ,f y f represents the surface partial derivative of the pit region. xx ,f yy ,f xy This represents the second-order partial derivative of the pit region.

6. The vehicle seat control method according to claim 1 or 2, characterized in that, The process of associating the dented area with the vehicle's driving status includes: Get the vehicle position (x) at time k. k y k The vehicle heading angle θ at time k k The vehicle speed v at time k k The vehicle steering angle δ at time k k The position d of the crater at time k pothole,k The pit depth h at time k pothole,k ; Based on the vehicle position (x) at time k k y k The vehicle heading angle θ at time k k The vehicle speed v at time k k The vehicle steering angle δ at time k k The position d of the crater at time k pothole,k The pit depth h at time k pothole,k Define the state vector x k ;include: The state vector x k The data is input into a pre-defined or real-time determined observation function to correlate the pitted area with the vehicle's driving state; including: z k =h(x k )+v k ; In the formula, h() is the observation function, v k It measures noise.

7. A vehicle seat control system, characterized in that, The system includes: The data acquisition module is used to acquire target point cloud data, including road surface point cloud data; The pothole recognition module is used to extract road surface features based on target point cloud data and identify pothole areas in the road surface based on the road surface features. The road surface features include at least one of road surface height features, road surface curvature features, and road surface slope features. The shock absorption control module is used to associate the dented area with the vehicle's driving state and to control the shock absorption of the vehicle seat based on the association result; wherein, the vehicle driving state includes at least one of vehicle speed, vehicle position, and vehicle steering angle. The process by which the pothole recognition module extracts road surface features from the target point cloud data includes: For the coordinates of each point in the road surface point cloud data, perform three-dimensional spatial surface fitting; including: In the formula, (x, y) represents the coordinates of each point cloud in the road surface point cloud data, z represents the height of the fitted surface, and a0,...,a5 represent the fitting parameters. Indicates the fitting error; Based on the maximum and minimum height values ​​of the fitted surface, the height difference between the fitted surfaces is calculated, and this height difference is used as a road surface height feature; including: Δz = z1 - z2; In the formula, Δz represents the height difference of the fitted surface, z1 represents the maximum height value of the fitted surface, and z2 represents the minimum height value of the fitted surface; Calculating the curvature of the fitted surface and using the curvature of the fitted surface as a feature of road surface curvature; including: In the formula, κ represents the curvature of the fitted surface; The slope is calculated based on the gradient of the fitted surface, and the slope is used as a feature of the road surface gradient; including: In the formula, The slope represents the gradient of the fitted surface in the x and y directions; the slope represents the inclination.

8. A computer device, characterized in that, The system includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the vehicle seat control method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the steps of the vehicle seat control method according to any one of claims 1 to 6.

Images