Vehicle all-time state cooperative control method and system based on multi-source perception data fusion

Abstract

This invention discloses a vehicle all-time cooperative control method and system based on multi-source perception data fusion, belonging to the field of vehicle control. The method includes the following steps: S1, synchronously acquiring vertical pressure signals, yaw rate, vehicle three-axis acceleration, vertical acceleration generated by road surface excitation, distance and relative velocity of obstacles ahead, and images of the road surface ahead, forming multi-source perception data; S2, fusing preprocessed multi-source perception data at the same timestamp, determining the vehicle's real-time three-dimensional center of gravity, vehicle attitude angles, and real-time road surface state, and obtaining predicted road surface state based on historical multi-source perception data; S3, collaboratively controlling braking force distribution, steer-by-wire, and active suspension. By employing the above-mentioned vehicle all-time cooperative control method and system based on multi-source perception data fusion, full-dimensional coverage of vehicle state, road environment, and obstacle information is achieved, ensuring stable and reliable perception results.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a method and system for all-time cooperative control of vehicles based on multi-source perception data fusion. Background Technology

[0002] As the automotive industry accelerates its evolution towards intelligence and connectivity, vehicle control technology is upgrading from traditional independent control of a single subsystem to collaborative control of multiple systems. Currently, L2+ to L3 level intelligent driving systems have widely applied hardware platforms such as brake-by-wire, steering-by-wire, and active suspension. However, significant technical bottlenecks still exist in control accuracy, response speed, and collaborative performance under complex road conditions, making it difficult to meet the all-time control requirements of safety, comfort, and efficiency.

[0003] Existing vehicle control systems suffer from fundamental limitations in the perception and fusion of multi-source sensing data. In traditional distributed electronic and electrical architectures (EEA), sensors such as forward-facing cameras, millimeter-wave radars, and inertial measurement units (IMUs) belong to different control subsystems, resulting in isolated data acquisition and processing. The time skew of unsynchronized sensor data can exceed 50ms. When a vehicle is traveling at 120km / h, this time error can lead to an obstacle distance perception deviation exceeding 3m, severely impacting the accuracy of control decisions. Furthermore, spatial calibration errors in different sensor coordinate systems further amplify the fusion deviation. For example, extrinsic parameter calibration errors between visual sensors and lidar can reduce the accuracy of real-time road condition assessment by 40%, failing to provide reliable environmental input for control execution. This "data silo" phenomenon makes it difficult for existing systems to achieve comprehensive perception of vehicle status and environmental information. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for all-time cooperative control of vehicles based on multi-source perception data fusion, thereby solving the aforementioned technical problems.

[0005] To achieve the above objectives, this invention provides a vehicle all-time cooperative control method based on multi-source perception data fusion, comprising the following steps:

[0006] S1. Multi-source sensing data acquisition and preprocessing: Simultaneously acquire vertical pressure signals, yaw rate, vehicle three-axis acceleration, vertical acceleration generated by road excitation, distance and relative velocity of obstacles ahead, and road surface image to form multi-source sensing data. Then, perform moving average filtering, spatiotemporal collaborative synchronization calibration and standardization on the multi-source sensing data in sequence to obtain preprocessed multi-source sensing data.

[0007] S2. Multi-source perception data fusion: Fuse preprocessed multi-source perception data with the same timestamp, and determine the vehicle's real-time three-dimensional center of gravity, vehicle body attitude angle and real-time road surface state based on the fused multi-source perception data, and obtain the predicted road surface state based on historical multi-source perception data.

[0008] S3. Based on the real-time three-dimensional center of gravity of the vehicle, the vehicle body attitude angle, the real-time road surface condition and the predicted road surface condition determined in step S2, coordinate the control of braking force distribution, steer-by-wire and active suspension.

[0009] Preferably, in step S1, four pressure sensors installed on the upper seats of the suspension springs on the left front, right front, left rear, and right rear sides and aligned with the force application points of the suspension springs are used to acquire vertical pressure signals from the left front side. Right anterior vertical pressure signal Left rear vertical pressure signal and right rear vertical pressure signal ;

[0010] The yaw rate of the vehicle is collected using a yaw rate sensor installed at the center of gravity of the vehicle body. ;

[0011] The vehicle's triaxial acceleration is collected using a triaxial accelerometer installed at the vehicle's center of gravity. ;

[0012] The vertical acceleration generated by road surface excitation is collected using a triaxial accelerometer installed on the left or right front wheel. ;

[0013] The distance to obstacles in front is collected using a radar sensor installed at the center of the front bumper. and the relative speed between the vehicle and the obstacle in front. ;

[0014] Images of the road ahead are captured using a vision sensor mounted on the rearview mirror of the windshield.

[0015] The sampling frequency of the pressure sensor, yaw rate sensor and triaxial accelerometer is 1kHz, the sampling frequency of the radar sensor is 10Hz, and the sampling frequency of the vision sensor is 5Hz.

[0016] Dynamic signals from pressure sensors, yaw rate sensors, and triaxial accelerometers are transmitted to the domain controller via a CAN bus; radar sensors and vision sensors transmit signals to the domain controller via an Ethernet bus.

[0017] All multi-source sensing data carry a domain controller synchronization timestamp to achieve alignment in the time dimension.

[0018] Preferably, the moving average filtering expression in step S1 is as follows:

[0019] ;

[0020] In the formula, express Sensing data after being filtered by moving average at any given moment; Indicates the length of the sliding window; express Real-time raw sensing data;

[0021] Spatiotemporal coordinated synchronization calibration includes temporal coordinated synchronization and spatial coordinated synchronization. Temporal coordinated synchronization is based on the domain controller clock and involves linear interpolation and coordinated synchronization of all sensed data according to timestamps.

[0022] ;

[0023] In the formula, express The sensed data after time-coordinated synchronization at the synchronization moment; and Respectively represent and Two adjacent acquisition times at synchronization time , Sensing data after time-synchronized collaboration;

[0024] Spatial collaborative synchronization is achieved by unifying spatial data from different sensors into the vehicle coordinate system through coordinate transformation.

[0025] Preferably, the real-time three-dimensional center of gravity expression of the vehicle described in step S2 is as follows:

[0026] ;

[0027] in,

[0028] ;

[0029] In the formula, This indicates the real-time three-dimensional center of gravity coordinates of the vehicle; , , , These represent the installation coordinates of the four pressure sensors mounted on the upper seats of the suspension springs at the front left, front right, rear left, and rear right, respectively.

[0030] Vehicle attitude angles include roll angles and pitch angle Among them, the roll angle The expression is as follows:

[0031] ;

[0032] In the formula, Represents gravitational acceleration; Indicates the longitudinal speed of the vehicle, and , Indicates the vehicle's own speed;

[0033] Pitch angle The expression is as follows:

[0034] ;

[0035] Real-time road condition via real-time road level Sure:

[0036] ;

[0037] in,

[0038] ;

[0039] ;

[0040] In the formula, The range of values ​​is , and Both represent pre-calibrated weighting coefficients, and , ; Indicates road surface smoothness; Indicates the slope of the road surface; and These represent the number of rows and columns of pixels in the image of the road surface ahead, respectively. Indicates the image of the road ahead. The grayscale value of a pixel; This represents the average grayscale value of the image of the road surface ahead; This represents the longitudinal acceleration during braking, and , This indicates the braking force transmission efficiency of the bidirectional converter; and These represent the front axle braking force and the rear axle braking force, respectively. , , This represents the tire-road adhesion coefficient. Indicates the vertical load on the front axle. Indicates wheelbase. Indicates the distance from the rear axle to the center of gravity. Indicates the height of the center of gravity; , Indicates the vertical load on the rear axle; Indicates the total mass of the vehicle. ; Indicates the load transfer correction factor. .

[0041] Preferably, in step S3, when the real-time road surface grade ,or When this occurs, the following active suspension height-stiffness coordinated adjustment is triggered:

[0042] ;

[0043] ;

[0044] In the formula, Indicates the first The target height of the suspension, and These represent the front left, front right, rear left, and rear right suspensions, respectively. Indicates the steady-state suspension height; This indicates the height adjustment factor corresponding to the real-time road surface grade; This indicates the height adjustment factor corresponding to the center of gravity shift; Indicates the first The stiffness of the suspension; This represents the stiffness adjustment coefficient corresponding to the real-time road surface grade. This represents the stiffness adjustment factor corresponding to the roll angle; This indicates that a secondary level threshold has been set; This indicates that the lateral coordinates are set; Represents the steady-state lateral coordinates of the center of gravity;

[0045] When the radar sensor detects an obstacle ahead, and When this occurs, the following coordinated control of brake-steer-drive and active suspension is triggered:

[0046] ;

[0047] ;

[0048] ;

[0049] ;

[0050] In the formula, Indicates the steering angle; This indicates the vehicle's real-time deceleration, and , Indicates total braking force; Indicates the braking force distribution coefficient; This indicates the adjustment coefficient for the center of gravity offset; Represents the longitudinal coordinate of the steady-state center of gravity; Indicates the stiffness of the suspension on the stressed side; Indicates the steady-state suspension stiffness; This represents the stiffness increment coefficient corresponding to the roll angle; Indicates the target height of the non-load-bearing side suspension; This indicates the roll angle-height adjustment factor; Indicates the steady-state suspension height; Indicates a safe distance, and , Indicates a safety margin. Indicates the vehicle's maximum deceleration. , Indicates the maximum braking force;

[0051] when Or the slope of the road surface When this occurs, the following active suspension-seat posture coordination adjustment mechanism is triggered:

[0052] ;

[0053] ;

[0054] In the formula, Indicates the first The target support force of the suspension; This represents the suspension damping coefficient, and ; This represents the steady-state damping coefficient of the suspension. This represents the damping adjustment coefficient corresponding to the predicted road surface grade; Indicates the first The rate of change of suspension height; represents; Indicates the seat pitch angle; This represents the proportionality coefficient, and ; This indicates the setting of a road surface inclination threshold; Indicates the predicted road surface condition; This indicates that a threshold for the secondary level has been set.

[0055] A system for implementing a vehicle all-time cooperative control method based on multi-source perception data fusion includes:

[0056] The multi-source sensing data acquisition and preprocessing module is used to simultaneously acquire vertical pressure signals, yaw rate, vehicle three-axis acceleration, vertical acceleration generated by road excitation, distance and relative velocity of obstacles ahead, and road surface image of each suspension to form multi-source sensing data. The multi-source sensing data is then subjected to moving average filtering, spatiotemporal collaborative synchronization calibration and standardization processing in sequence to obtain preprocessed multi-source sensing data.

[0057] The multi-source perception data fusion module is used to fuse preprocessed multi-source perception data with the same timestamp, and determine the vehicle's real-time three-dimensional center of gravity, vehicle body attitude angle and real-time road surface state based on the fused multi-source perception data, and predict the road surface state based on historical multi-source perception data.

[0058] The collaborative control module is used to collaboratively control braking force distribution, steer-by-wire, and active suspension based on the vehicle's real-time three-dimensional center of gravity, body attitude angle, real-time road conditions, and predicted road conditions.

[0059] Therefore, the vehicle all-time cooperative control method and system based on multi-source perception data fusion described above have the following beneficial effects:

[0060] 1. Full-dimensional perception without blind spots: Through the collaboration of "pressure sensor (suspension load) + vision sensor (road texture) + radar (speed) + acceleration / yaw rate sensor (vehicle attitude)", it covers the full dimensions of "vehicle status - road environment - obstacles", solving the problem of limited perception of traditional single sensors (such as relying solely on wheel speed sensors);

[0061] 2. Significantly reduced roll / fishtail risk: Breaking through the traditional independent control logic of "steering + single-sided braking", a coordinated control mechanism of "steering angle - braking force - suspension stiffness" is established, which can achieve a body roll angle of ≤5° during active avoidance (traditional solution >15°), reducing the risk of fishtail by 80%;

[0062] 3. Dynamically adaptable suspension damping to all road conditions: The suspension damping is dynamically adjusted according to the road surface grade, which solves the contradiction of traditional fixed damping: "smooth road surface, but large vibration on bumpy road surface".

[0063] 4. Seat posture coordination reduces discomfort: The seat pitch angle adjusts according to the predicted value of the vehicle pitch angle, and the posture change range is only 50% of the vehicle body, reducing the pitch discomfort caused by uphill / downhill, braking / acceleration.

[0064] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0065] Figure 1 This is a flowchart of the vehicle all-time cooperative control method based on multi-source perception data fusion according to the present invention. Detailed Implementation

[0066] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the embodiments of the present invention and are not intended to limit the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout.

[0067] It should be noted that the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, such as a process, method, system, product, or server that includes a series of steps or units, not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or device.

[0068] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0069] like Figure 1 As shown, the vehicle all-time cooperative control method based on multi-source perception data fusion includes the following steps:

[0070] S1. Multi-source sensing data acquisition and preprocessing: Simultaneously acquire vertical pressure signals, yaw rate, vehicle three-axis acceleration, vertical acceleration generated by road excitation, distance and relative velocity of obstacles ahead, and road surface image to form multi-source sensing data. Then, perform moving average filtering, spatiotemporal collaborative synchronization calibration and standardization on the multi-source sensing data in sequence to obtain preprocessed multi-source sensing data.

[0071] In step S1, four pressure sensors installed on the upper seats of the suspension springs on the left front, right front, left rear, and right rear, and aligned with the force application points of the suspension springs, are used to acquire the vertical pressure signal from the left front. Right anterior vertical pressure signal Left rear vertical pressure signal and right rear vertical pressure signal ;

[0072] The yaw rate of the vehicle is collected using a yaw rate sensor installed at the center of gravity of the vehicle body. ;

[0073] The vehicle's triaxial acceleration is collected using a triaxial accelerometer installed at the vehicle's center of gravity. ;

[0074] The vertical acceleration generated by road surface excitation is collected using a triaxial accelerometer installed on the left or right front wheel. ;

[0075] The distance to obstacles in front is collected using a radar sensor installed at the center of the front bumper. and the relative speed between the vehicle and the obstacle in front. ;

[0076] Images of the road ahead are captured using a vision sensor mounted on the rearview mirror of the windshield.

[0077] The sampling frequency of the pressure sensor, yaw rate sensor and triaxial accelerometer is 1kHz, the sampling frequency of the radar sensor is 10Hz, and the sampling frequency of the vision sensor is 5Hz.

[0078] Dynamic signals from pressure sensors, yaw rate sensors, and triaxial accelerometers are transmitted to the domain controller via a CAN bus; radar sensors and vision sensors transmit signals to the domain controller via an Ethernet bus.

[0079] All multi-source sensing data carry a domain controller synchronization timestamp to achieve alignment in the time dimension.

[0080] The moving average filter expression described in step S1 is as follows:

[0081] ;

[0082] In the formula, express Sensing data after being filtered by moving average at any given moment; Indicates the length of the sliding window; express Real-time raw sensing data;

[0083] Spatiotemporal coordinated synchronization calibration includes temporal coordinated synchronization and spatial coordinated synchronization. Temporal coordinated synchronization is based on the domain controller clock and involves linear interpolation and coordinated synchronization of all sensed data according to timestamps.

[0084] ;

[0085] In the formula, express The sensed data after time-coordinated synchronization at the synchronization moment; and Respectively represent and Two adjacent acquisition times at synchronization time , Sensing data after time-synchronized collaboration;

[0086] Spatial collaborative synchronization is achieved by unifying spatial data from different sensors into the vehicle coordinate system through coordinate transformation.

[0087] S2. Multi-source perception data fusion: Preprocessed multi-source perception data with the same timestamp are fused, and the real-time three-dimensional center of gravity, vehicle attitude angle, and real-time road surface state of the vehicle are determined based on the fused multi-source perception data. The predicted road surface state is obtained based on historical multi-source perception data. In this embodiment, the predicted location can be determined by radar sensors, and then historical multi-source perception data can be searched to determine the predicted road surface state. Alternatively, historical multi-source perception data and location information can be input into a neural network model to establish a mapping relationship between historical multi-source perception data and location information. Then, the predicted location can be input into the trained neural network model to obtain the predicted road surface state.

[0088] The real-time three-dimensional center of gravity expression of the vehicle mentioned in step S2 is as follows:

[0089] ;

[0090] in,

[0091] ;

[0092] In the formula, This indicates the real-time three-dimensional center of gravity coordinates of the vehicle; , , , These represent the installation coordinates of the four pressure sensors mounted on the upper seats of the suspension springs at the front left, front right, rear left, and rear right, respectively.

[0093] Vehicle attitude angles include roll angles and pitch angle Among them, the roll angle The expression is as follows:

[0094] ;

[0095] In the formula, Represents gravitational acceleration; Indicates the longitudinal speed of the vehicle, and , Indicates the vehicle's own speed;

[0096] Pitch angle The expression is as follows:

[0097] ;

[0098] Real-time road condition via real-time road level Sure:

[0099] ;

[0100] in,

[0101] ;

[0102] ;

[0103] In the formula, The range of values ​​is , and Both represent pre-calibrated weighting coefficients, and , ; Indicates road surface smoothness; Indicates the slope of the road surface; and These represent the number of rows and columns of pixels in the image of the road surface ahead, respectively. Indicates the image of the road ahead. The grayscale value of a pixel; This represents the average grayscale value of the image of the road surface ahead; This represents the longitudinal acceleration during braking, and , This indicates the braking force transmission efficiency of the bidirectional converter; and These represent the front axle braking force and the rear axle braking force, respectively. , , This represents the tire-road adhesion coefficient. Indicates the vertical load on the front axle. Indicates wheelbase. Indicates the distance from the rear axle to the center of gravity. Indicates the height of the center of gravity; , Indicates the vertical load on the rear axle; Indicates the total mass of the vehicle. ; Indicates the load transfer correction factor. .

[0104] S3. Based on the real-time three-dimensional center of gravity of the vehicle, the vehicle body attitude angle, the real-time road surface condition and the predicted road surface condition determined in step S2, coordinate the control of braking force distribution, steer-by-wire and active suspension.

[0105] In step S3, when the real-time road surface level ,or When this occurs, the following active suspension height-stiffness coordinated adjustment is triggered:

[0106] ;

[0107] ;

[0108] In the formula, Indicates the first The target height of the suspension, and These represent the front left, front right, rear left, and rear right suspensions, respectively. Indicates the steady-state suspension height; This indicates the height adjustment factor corresponding to the real-time road surface grade; This indicates the height adjustment factor corresponding to the center of gravity shift; Indicates the first The stiffness of the suspension; This represents the stiffness adjustment coefficient corresponding to the real-time road surface grade. This represents the stiffness adjustment factor corresponding to the roll angle; This indicates that a secondary level threshold has been set; This indicates that the lateral coordinates are set; Represents the steady-state lateral coordinates of the center of gravity;

[0109] When the radar sensor detects an obstacle ahead, and When this occurs, the following coordinated control of brake-steer-drive and active suspension is triggered:

[0110] ;

[0111] ;

[0112] ;

[0113] ;

[0114] In the formula, Indicates the steering angle; This indicates the vehicle's real-time deceleration, and , Indicates total braking force; Indicates the braking force distribution coefficient; This indicates the adjustment coefficient for the center of gravity offset; Represents the longitudinal coordinate of the steady-state center of gravity; Indicates the stiffness of the suspension on the stressed side; Indicates the steady-state suspension stiffness; This represents the stiffness increment coefficient corresponding to the roll angle; Indicates the target height of the non-load-bearing side suspension; This indicates the roll angle-height adjustment factor; Indicates the steady-state suspension height; Indicates a safe distance, and , Indicates a safety margin. Indicates the vehicle's maximum deceleration. , Indicates the maximum braking force;

[0115] when Or the slope of the road surface When this occurs, the following active suspension-seat posture coordination adjustment mechanism is triggered:

[0116] ;

[0117] ;

[0118] In the formula, Indicates the first The target support force of the suspension; This represents the suspension damping coefficient, and ; This represents the steady-state damping coefficient of the suspension. This represents the damping adjustment coefficient corresponding to the predicted road surface grade; Indicates the first The rate of change of suspension height; represents; Indicates the seat pitch angle; This represents the proportionality coefficient, and ; This indicates the setting of a road surface inclination threshold; Indicates the predicted road surface condition; This indicates that a threshold for the secondary level has been set.

[0119] A system for implementing a vehicle all-time cooperative control method based on multi-source perception data fusion includes:

[0120] The multi-source sensing data acquisition and preprocessing module is used to simultaneously acquire vertical pressure signals, yaw rate, vehicle three-axis acceleration, vertical acceleration generated by road excitation, distance and relative velocity of obstacles ahead, and road surface image of each suspension to form multi-source sensing data. The multi-source sensing data is then subjected to moving average filtering, spatiotemporal collaborative synchronization calibration and standardization processing in sequence to obtain preprocessed multi-source sensing data.

[0121] The multi-source perception data fusion module is used to fuse preprocessed multi-source perception data with the same timestamp, and determine the vehicle's real-time three-dimensional center of gravity, vehicle body attitude angle and real-time road surface state based on the fused multi-source perception data, and predict the road surface state based on historical multi-source perception data.

[0122] The collaborative control module is used to collaboratively control braking force distribution, steer-by-wire, and active suspension based on the vehicle's real-time three-dimensional center of gravity, body attitude angle, real-time road conditions, and predicted road conditions.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A vehicle all-time state cooperative control method based on multi-source perception data fusion, characterized in that: Includes the following steps: S1. Multi-source sensing data acquisition and preprocessing: Simultaneously acquire vertical pressure signals, yaw rate, vehicle three-axis acceleration, vertical acceleration generated by road excitation, distance and relative velocity of obstacles ahead, and road surface image to form multi-source sensing data. Then, perform moving average filtering, spatiotemporal collaborative synchronization calibration and standardization on the multi-source sensing data in sequence to obtain preprocessed multi-source sensing data. S2. Multi-source perception data fusion: Fusion of preprocessed multi-source perception data with the same timestamp, and determination of the vehicle's real-time three-dimensional center of gravity, vehicle body attitude angle and real-time road surface state based on the fused multi-source perception data, and prediction of road surface state based on historical multi-source perception data. S3. Based on the real-time three-dimensional center of gravity of the vehicle, the vehicle body attitude angle, the real-time road surface condition and the predicted road surface condition determined in step S2, coordinate the control of braking force distribution, steer-by-wire and active suspension. The moving average filter expression described in step S1 is as follows: ； In the formula, represents sensed data filtered by a sliding average at the time instant; represents the length of the sliding window; represents original sensed data at the time instant; Spatiotemporal coordinated synchronization calibration includes temporal coordinated synchronization and spatial coordinated synchronization. Temporal coordinated synchronization is based on the domain controller clock and involves linear interpolation and coordinated synchronization of all sensed data according to timestamps. ； In the formula, express The sensed data after time-coordinated synchronization at the synchronization moment; and Respectively represent and Two adjacent acquisition times at synchronization time , Sensing data after time-synchronized collaboration; Spatial collaborative synchronization is achieved by unifying spatial data from different sensors into the vehicle coordinate system through coordinate transformation.

2. The vehicle all-time cooperative control method based on multi-source perception data fusion according to claim 1, characterized in that: In step S1, four pressure sensors installed on the upper seats of the suspension springs on the left front, right front, left rear, and right rear, and aligned with the force application points of the suspension springs, are used to acquire the vertical pressure signal from the left front. Right anterior vertical pressure signal Left rear vertical pressure signal and right rear vertical pressure signal ; The yaw rate of the vehicle is collected using a yaw rate sensor installed at the center of gravity of the vehicle body. ; The vehicle's triaxial acceleration is collected using a triaxial accelerometer installed at the vehicle's center of gravity. ; The vertical acceleration generated by road surface excitation is collected using a triaxial accelerometer installed on the left or right front wheel. ; The distance to obstacles in front is collected using a radar sensor installed at the center of the front bumper. and the relative speed between the vehicle and the obstacle in front. ; Images of the road ahead are captured using a vision sensor mounted on the rearview mirror of the windshield. The sampling frequency of the pressure sensor, yaw rate sensor and triaxial accelerometer is 1kHz, the sampling frequency of the radar sensor is 10Hz, and the sampling frequency of the vision sensor is 5Hz. Dynamic signals from pressure sensors, yaw rate sensors, and triaxial accelerometers are transmitted to the domain controller via a CAN bus; radar sensors and vision sensors transmit signals to the domain controller via an Ethernet bus. All multi-source sensing data carry a domain controller synchronization timestamp to achieve alignment in the time dimension.

3. The vehicle all-time cooperative control method based on multi-source perception data fusion according to claim 2, characterized in that: The real-time three-dimensional center of gravity expression of the vehicle mentioned in step S2 is as follows: ； in, ； In the formula, This indicates the real-time three-dimensional center of gravity coordinates of the vehicle; , , , These represent the installation coordinates of the four pressure sensors mounted on the upper seats of the suspension springs at the front left, front right, rear left, and rear right, respectively. Vehicle attitude angles include roll angles and pitch angle Among them, the roll angle The expression is as follows: ； In the formula, Represents gravitational acceleration; Indicates the longitudinal speed of the vehicle, and , Indicates the vehicle's own speed; Pitch angle The expression is as follows: ； Real-time road condition via real-time road level Sure: ； in, ； ； In the formula, The range of values ​​is , and Both represent pre-calibrated weighting coefficients, and , ; Indicates road surface smoothness; Indicates the slope of the road surface; and These represent the number of rows and columns of pixels in the image of the road surface ahead, respectively. Indicates the image of the road ahead. The grayscale value of a pixel; This represents the average grayscale value of the image of the road surface ahead; This represents the longitudinal acceleration during braking, and , This indicates the braking force transmission efficiency of the bidirectional converter; and These represent the front axle braking force and the rear axle braking force, respectively. , , This represents the tire-road adhesion coefficient. Indicates the vertical load on the front axle. Indicates wheelbase. Indicates the distance from the rear axle to the center of gravity. Indicates the height of the center of gravity; , Indicates the vertical load on the rear axle; Indicates the total mass of the vehicle. ; Indicates the load transfer correction factor. .

4. The vehicle all-time cooperative control method based on multi-source perception data fusion according to claim 3, characterized in that: In step S3, when the real-time road surface level ,or When this occurs, the following active suspension height-stiffness coordinated adjustment is triggered: ； ； In the formula, Indicates the first The target height of the suspension, and These represent the front left, front right, rear left, and rear right suspensions, respectively. Indicates the steady-state suspension height; This indicates the height adjustment factor corresponding to the real-time road surface grade; This indicates the height adjustment factor corresponding to the center of gravity shift; Indicates the first The stiffness of the suspension; This represents the stiffness adjustment coefficient corresponding to the real-time road surface grade. This represents the stiffness adjustment factor corresponding to the roll angle; This indicates that a threshold for the second-level classification has been set. This indicates that the lateral coordinates are set; Represents the steady-state lateral coordinates of the center of gravity; When the radar sensor detects an obstacle ahead, and When this occurs, the following coordinated control of brake-steer-drive and active suspension is triggered: ； ； ； ； In the formula, Indicates the steering angle; This indicates the vehicle's real-time deceleration, and , Indicates total braking force; Indicates the braking force distribution coefficient; This indicates the adjustment coefficient for the center of gravity offset; Represents the longitudinal coordinate of the steady-state center of gravity; Indicates the stiffness of the suspension on the stressed side; Indicates the steady-state suspension stiffness; This represents the stiffness increment coefficient corresponding to the roll angle; Indicates the target height of the non-load-bearing side suspension; This indicates the roll angle-height adjustment factor; Indicates the steady-state suspension height; Indicates a safe distance, and , Indicates a safety margin. Indicates the vehicle's maximum deceleration. , Indicates the maximum braking force; when Or the slope of the road surface When this occurs, the following active suspension-seat posture coordination adjustment mechanism is triggered: ； ； In the formula, Indicates the first The target support force of the suspension; This represents the suspension damping coefficient, and ; This represents the steady-state damping coefficient of the suspension. This represents the damping adjustment coefficient corresponding to the predicted road surface grade; Indicates the first The rate of change of suspension height; Indicates the seat pitch angle; This represents the proportionality coefficient, and ; This indicates the setting of a road surface inclination threshold; Indicates the predicted road surface condition; This indicates that a threshold for the secondary level has been set.

5. A system for executing the vehicle all-time cooperative control method based on multi-source perception data fusion as described in any one of claims 1-4, characterized in that: include: The multi-source sensing data acquisition and preprocessing module is used to simultaneously acquire vertical pressure signals, yaw rate, vehicle three-axis acceleration, vertical acceleration generated by road excitation, distance and relative velocity of obstacles ahead, and road surface image of each suspension to form multi-source sensing data. The multi-source sensing data is then subjected to moving average filtering, spatiotemporal collaborative synchronization calibration and standardization processing in sequence to obtain preprocessed multi-source sensing data. The multi-source perception data fusion module is used to fuse preprocessed multi-source perception data with the same timestamp, and determine the vehicle's real-time three-dimensional center of gravity, vehicle attitude angle and real-time road surface state based on the fused multi-source perception data, and predict the road surface state based on historical multi-source perception data. The collaborative control module is used to collaboratively control braking force distribution, steer-by-wire, and active suspension based on the vehicle's real-time three-dimensional center of gravity, body attitude angle, real-time road conditions, and predicted road conditions.

Images