Active suspension control method and system and vehicle

Abstract

The invention discloses an active suspension control method and system and a vehicle, and relates to the technical field of vehicles. The active suspension control method comprises the steps that multi-source data are obtained, and the multi-source data comprise vehicle information, sensing information and control information; generating suggested control parameters according to the multi-source data by using a deep learning model; and controlling the active suspension of the vehicle according to the suggested control parameters. According to the method, the active suspension can be controlled in advance, and then the safety and comfort of vehicle driving can be improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to an active suspension control method, system and vehicle. Background Art

[0002] At present, the control of active suspension is mostly passive control, that is, when it is detected that the vehicle is in a certain working condition, the active suspension is controlled according to the working condition, which causes control lag and affects driving safety and comfort experience. Summary of the Invention

[0003] The present invention provides an active suspension control method, system and vehicle, so as to improve the safety and comfort of vehicle driving by controlling the active suspension in advance.

[0004] In a first aspect, an embodiment of the present invention proposes an active suspension control method, comprising: acquiring multi-source data, wherein the multi-source data includes vehicle information, perception information, and manipulation information; utilizing a deep learning model to generate recommended control parameters for advance control of the active suspension based on the multi-source data; and controlling the active suspension according to the recommended control parameters.

[0005] In some embodiments, the method further includes: obtaining basic control parameters based on the perception information; wherein, controlling the active suspension according to the recommended control parameters includes: updating the basic control parameters based on the recommended control parameters to obtain target control parameters, and controlling the active suspension according to the target control parameters.

[0006] In some embodiments, updating the basic control parameter based on the recommended control parameter to obtain the target control parameter includes: performing weighted summation on the recommended control parameter and the basic control parameter to obtain the target control parameter.

[0007] In some embodiments, the method further includes: optimizing parameters of the deep learning model using the basic control parameters.

[0008] In some embodiments, the active suspension includes four suspension assemblies, and the four suspension assemblies correspond one-to-one to the four wheels of the vehicle. The target control parameters include four target spring stiffnesses and four target shock absorber dampings corresponding one-to-one to the four suspension assemblies; controlling the active suspension of the vehicle according to the target control parameters includes: controlling the elastic elements of the four suspension assemblies according to the four target spring stiffnesses, and controlling the shock absorber dampers of the four suspension assemblies according to the four target shock absorber dampings.

[0009] In some embodiments, the vehicle information includes at least one of on-board processor information, on-board memory information, localization information, information perception, path planning information, system controller information, on-board map, and vehicle mode; the perception information includes multiple of radar system acquisition information, displacement sensor acquisition information, acceleration sensor acquisition information, camera acquisition information, microphone acquisition information, and surrounding environment acquisition information; the control information includes at least one of internal visual information, internal audio information, external visual information, external audio information, communication connection information, switch connection information, and drive module information.

[0010] In some embodiments, the method further includes: sending the multi-source data to a data center so that the data center optimizes the parameters of the deep learning model; and receiving the parameter-optimized deep learning model sent by the data center.

[0011] In some embodiments, part of the multi-source data is obtained from the data center via a mobile network.

[0012] In a second aspect, the present invention proposes an active suspension control system, comprising: a data acquisition device for collecting multi-source data, wherein the multi-source data includes vehicle information, perception information and control information; an active suspension; and a controller for executing the control method of the active suspension described in the embodiment of the first aspect.

[0013] In a second aspect, the present invention provides a vehicle, comprising: the active suspension control system described in the embodiment of the second aspect.

[0014] The active suspension control method, system, and vehicle of the embodiments of the present invention first acquire multi-source data, then utilize a deep learning model to generate recommended control parameters for proactively controlling the active suspension based on the multi-source data. The vehicle's active suspension is then controlled based on the recommended control parameters. This proactive control of the active suspension can improve vehicle driving safety and comfort.

[0015] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of an active suspension control method according to an embodiment of the present invention;

[0017] Figure 2 is a flow chart of an active suspension control method according to another embodiment of the present invention;

[0018] Figure 3 is a schematic structural diagram of an active suspension according to an example of the present invention;

[0019] Figure 4 is a simplified model schematic diagram of a quarter active suspension according to an example of the present invention;

[0020] Figure 5 is a structural diagram of an example of a method for implementing active suspension control according to the present invention;

[0021] Figure 6 is a communication diagram of an example of an active suspension control method implemented in the present invention;

[0022] Figure 7 is a schematic structural diagram of an active suspension control system according to an embodiment of the present invention;

[0023] Figure 8 4 is a structural block diagram of a vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0025] The active suspension control method, system, and vehicle according to embodiments of the present invention will be described below with reference to the accompanying drawings.

[0026] Figure 1 is a flow chart of an active suspension control method according to an embodiment of the present invention.

[0027] like Figure 1 As shown, the active suspension control method includes:

[0028] S11, obtain multi-source data.

[0029] Among them, multi-source data includes vehicle information, perception information and control information.

[0030] Exemplarily, vehicle information includes on-board processor information (such as the computing power allocation and task scheduling status of the on-board processor), on-board memory information (such as short-term cache information collected by sensors, long-term storage information such as fault logs), localization information (such as positioning data such as the vehicle's real-time position, posture, and heading angle), information perception information (which can be information obtained after identifying perception information), path planning information, system controller information (such as the command logic of the vehicle controller, chassis controller, etc. for power, braking, and steering, etc.), on-board map, and at least one of vehicle mode; perception information refers to information collected by on-board sensors, including multiple information collected by radar system, displacement sensor, acceleration sensor, camera, microphone, and surrounding environment; control information refers to information collected inside and outside the vehicle for direct control of the vehicle or with vehicle control intention, including internal visual information (such as occupant-specific gestures collected by the in-vehicle camera), internal audio information (such as occupant-specific voices collected by the in-vehicle microphone), external visual information, external audio information, communication connection information, switch connection information, and drive module information.

[0031] S12, using a deep learning model to generate recommended control parameters based on multi-source data.

[0032] Among them, the deep learning model can be pre-trained by a third party, such as the cloud or data center, and deployed in the vehicle for use. The data set used for training can be taken from multi-source data obtained by one or more vehicles under various working conditions.

[0033] The trained deep learning model can generate recommended control parameters based on multi-source data. For example, when it detects internal audio information indicating a "slightly drifting vehicle," the deep learning model outputs recommended control parameters for controlling the active suspension's "compression" to lower the vehicle's height and improve vehicle stability. Another example is when it detects a sharp turn ahead, the deep learning model outputs recommended control parameters for controlling the active suspension's "roll." This allows for roll control at the start of the turn, improving ride comfort during cornering.

[0034] S13: Control the active suspension based on the recommended control parameters.

[0035] This control method uses a deep learning model to generate recommended control parameters based on multi-source data, and controls the active suspension based on the recommended control parameters, achieving advance control of the active suspension and helping to improve vehicle driving safety and comfort.

[0036] For example, before controlling the active suspension based on the recommended control parameters, a query message may be sent, such as whether to control vehicle body lowering or vehicle body roll. Upon receiving a confirmation message, the active suspension is controlled based on the recommended control parameters. This can better meet user needs.

[0037] Figure 2 is a flow chart of an active suspension control method according to another embodiment of the present invention.

[0038] like Figure 2 As shown, the active suspension control method includes:

[0039] S21, obtain multi-source data.

[0040] S22, using a deep learning model to generate recommended control parameters based on multi-source data, and obtain basic control parameters based on the perception information.

[0041] For example, a mapping between sensory information and control parameters can be pre-established to generate a corresponding control strategy, which can then be stored in the vehicle for recall when needed. For example, when a vehicle passes over an uneven road, the wheels are subjected to vibration, which is transmitted to the vehicle body. Sensors detect changes in the position and acceleration of the vehicle body and axle, and transmit these signals to the active suspension controller via a signal processing circuit. The controller then invokes the control strategy to determine the ideal active force required to overcome the vibration and outputs a pulse-width modulation signal (i.e., the basic control parameter) based on the ideal active force. The drive circuit then controls the speed and direction of the brushless DC motor, causing the actuator to output the actual active control force.

[0042] S23 , updating the basic control parameters based on the recommended control parameters to obtain target control parameters, and controlling the active suspension according to the target control parameters.

[0043] Figure 2 The embodiment shown and Figure 1 The difference between the illustrated embodiments is that basic control parameters are also derived based on the sensed information, and these are updated using recommended control parameters. The active suspension is then controlled based on the updated target control parameters. By considering both basic and recommended control parameters, adaptability to complex operating conditions is improved.

[0044] In some examples of the present invention, updating the basic control parameter based on the recommended control parameter to obtain the target control parameter includes: performing weighted summation on the recommended control parameter and the basic control parameter to obtain the target control parameter.

[0045] For example, the target control parameter = k × basic control parameter + (1-k) × recommended control parameter, where k is the weight, which can be a fixed value, such as 0.5; it can also be adaptively adjusted according to the actual vehicle situation. For example, if the recommended control parameter can better meet user needs, the value of k can be reduced.

[0046] As an implementation method, it is recommended that the control parameters, basic control parameters, and target control parameters all include spring stiffness and shock absorber damping, the target spring stiffness = k × real-time spring stiffness + (1-k) × pre-spring stiffness, and the target shock absorber damping = k × real-time shock absorber damping + (1-k) × pre-shock absorber damping.

[0047] In some examples of the present invention, the active suspension includes four suspension assemblies, such as Figure 3 As shown, the front suspension right assembly 101, rear suspension right assembly 102, rear suspension left assembly 103, and front suspension left assembly 104 are each composed of elastic components and shock absorbers. The four suspension assemblies correspond one-to-one to the four wheels of the vehicle, and the target control parameters include four target spring stiffnesses and four target shock absorber damping values ​​corresponding to the four suspension assemblies.

[0048] The active suspension of the vehicle is controlled according to the target control parameters, including: controlling the elastic components of the four suspension assemblies according to four target spring stiffnesses, and controlling the shock absorber dampers of the four suspension assemblies according to four target shock absorber dampings.

[0049] Figure 4 A simplified model of the quarter car suspension is shown. Figure 4 Suspension mass ms refers to the equivalent mass of one-quarter of the vehicle body, mu refers to the equivalent mass of the wheels and axles, ks and kt are the suspension and wheel stiffnesses, respectively. zs, zu, and zr are the sprung mass displacement, unsprung mass displacement, and road input displacement, respectively. The wheel can be considered equivalent to a spring. bs is the suspension damping, and Fa is the active force. In typical suspensions, Fa is considered to be always equal to 0. The initial state is: the suspension is in equilibrium under the action of gravity.

[0050] When controlling the active suspension, the strength of each suspension assembly's elastic components (such as springs) and the damping of the shock absorber are controlled in advance according to the target control parameters, which enables the vehicle's active suspension system to respond in real time. This ensures that when the vehicle reaches the corresponding operating conditions, the vehicle's ride comfort can reach a satisfactory level and the vehicle's handling stability can reach an optimal state.

[0051] In some embodiments of the present invention, the method further includes: optimizing parameters of the deep learning model using basic control parameters.

[0052] Specifically, in real-world vehicle control, to ensure that the deep learning model better meets the proactive control requirements of the active suspension, the basic control parameters can be used to optimize the deep learning model's parameters, enabling adaptive learning. For example, the basic control parameters can be used as supervisory signals to train the deep learning model through distillation learning.

[0053] Optionally, after responding according to the control parameters, the active suspension can feed back the excitation (including the relative displacement change between the sprung mass and the unsprung mass, the vertical acceleration of the sprung mass, etc.) to the controller to optimize the parameters of the deep learning model.

[0054] As an implementation, a reinforcement learning framework can be used to optimize the parameters of a deep learning model online based on incentives. For example, center of mass acceleration, suspension spring rate, and tire displacement are used as agent inputs, and incentives are fed back to the deep learning model through a reward function design. When the actual control effect deviates from the expected, the parameters of the deep learning model, such as weights, are automatically adjusted. The reward function design can be as follows:

[0055] R=-(w1·a 2 +w2·s 2 +w3·d 2 )

[0056] Among them, a is the vertical acceleration of the vehicle body, s is the active suspension displacement, d is the tire dynamic displacement, and w1, w2, and w3 are weight coefficients, which can be dynamically adjusted according to the control effect.

[0057] As another implementation, RMSprop or Adam optimizers are used to automatically adjust parameters in the deep learning model, such as the learning rate, based on the rate of change of the loss function. For example, if the rate of loss decreases below a certain value for multiple consecutive iterations (e.g., 5 iterations), the learning rate is reduced; if the loss fluctuates within a certain range, the learning rate is reset to its initial value, such as 50%.

[0058] It should be noted that compared with Figure 1 In the embodiment shown, Figure 2 In the illustrated embodiment, when using incentives to optimize the parameters of the deep learning model, the role of actual control parameters must also be considered.

[0059] As an embodiment, the method of the present invention can be Figure 5The controller shown in the figure executes. During vehicle operation, the controller acquires data from multiple sources (including road surface information affecting the active suspension). It uses a deep learning model to determine recommended control parameters for preemptively controlling the active suspension based on this multi-source data. Furthermore, it invokes a control strategy based on the perceived information to determine basic control parameters. It then updates the implementation control parameters based on pre-control signals to obtain target control parameters. Furthermore, the controller uses these basic control parameters to optimize the parameters of the deep learning model. The active suspension is then actively controlled based on the target control parameters. After the active suspension responds, the stimulus is fed back to the controller to optimize the parameters of the deep learning model.

[0060] In some embodiments of the present invention, the method further includes: sending multi-source data to a data center so that the data center optimizes parameters of the deep learning model; and receiving the parameter-optimized deep learning model sent by the data center.

[0061] Exemplarily, part of the multi-source data is obtained from the data center via a mobile network.

[0062] Specifically, if Figure 6 As shown, multi-source data can be obtained through a data acquisition device, which is connected to Figure 5 The controller shown is connected and can communicate with the data center via a mobile network (such as a 5G / 6G network). The data acquisition device provides the most important data basis for deep learning models and control strategies, while the mobile network and data center provide network support and data updates for active suspension control.

[0063] The control effect of the method of the present invention is described below in two aspects in combination with specific control functions:

[0064] First, the spring stiffness has two modes: "soft" and "hard," and the shock absorber damping has three modes: "soft," "medium," and "hard." The controller automatically adjusts the active suspension stiffness and shock absorber damping based on multiple data sources, such as vehicle speed and road surface changes. Rapid changes in vehicle speed or steering can cause abrupt changes in vehicle body posture, which is controlled by the present invention. Specific control functions are as follows:

[0065] 1) Anti-roll control

[0066] By setting the spring rate and shock absorber damping to a "hard" state, the vehicle's roll during high-speed cornering can be suppressed, minimizing changes in vehicle posture and improving handling.

[0067] 2) Anti-nodding control

[0068] By changing the spring stiffness and shock absorber damping to a "hard" state, the vehicle's braking "nod" can be suppressed, minimizing changes in the vehicle's posture.

[0069] 3) Anti-fallback control

[0070] By setting the spring rate and shock absorber damping to a "hard" state, the vehicle's backward tilt during acceleration can be suppressed, minimizing changes in vehicle posture.

[0071] 4) High speed control

[0072] Changing the spring rate to "hard" and the shock absorber damping to "medium" improves the vehicle's stability and handling at high speeds.

[0073] 5) Rough road control

[0074] By adjusting the spring rate and shock absorber damping to "medium" or "soft" as needed, the vehicle body can be restrained from bouncing up and down on the suspension, improving the ride comfort when the vehicle is traveling on uneven roads.

[0075] 6) Vibration control and bounce control:

[0076] By changing the spring rate and shock absorber damping to "medium" or "soft" state, the vehicle's bouncing and vibration when traveling on uneven roads can be suppressed.

[0077] 7) Road sensing semi-active control:

[0078] Corresponding to different roads, it provides optimal control of four-wheel independent shock absorption and damping, allowing the vehicle to maintain a constant posture under various roads and driving conditions.

[0079] The second aspect is vehicle body (chassis) height control, which is the active suspension control that raises and lowers the vehicle body according to the switch or system command. Based on the mode selected by the height control switch and the vehicle's state, the controller automatically adjusts the vehicle's height to keep the vehicle in a stable state. The specific control functions are as follows:

[0080] 1) Automatic height control

[0081] When the height control switch is in the "normal" or "high" position, the vehicle height is maintained at a constant height regardless of the weight of the passengers and luggage.

[0082] 2) High speed control

[0083] When the vehicle speed control switch is in the "hight" position, the vehicle height will be lowered to the "normal" state, which can improve aerodynamics and stability when driving at high speeds.

[0084] 3) Ignition switch off control

[0085] When the vehicle height becomes higher than the target height due to changes in passenger and luggage weight after the ignition switch is turned off, the vehicle height can be lowered to the target height, thereby improving the vehicle's parking posture.

[0086] Figure 7 2 is a schematic structural diagram of an active suspension control system according to an embodiment of the present invention.

[0087] like Figure 7 As shown, the active suspension control system 700 includes a data acquisition device 710 , an active suspension 720 and a controller 730 .

[0088] The data acquisition device 710 is used to collect multi-source data, including vehicle information, perception information, and control information. The controller 730 is used to execute the active suspension control method of the above embodiment.

[0089] Figure 8 4 is a structural block diagram of a vehicle according to an embodiment of the present invention.

[0090] like Figure 8 As shown, a vehicle 800 includes the active suspension control system 700 of the above embodiment.

[0091] In summary, the active suspension control method, system, and vehicle of the embodiments of the present invention utilize a deep learning model to generate recommended control parameters based on multi-source data. This allows for proactive control of the active suspension, enabling real-time response and improving vehicle safety and comfort. Furthermore, by optimizing the deep learning model using basic control parameters and active suspension excitation, the model can achieve better and more accurate control of the active suspension.

[0092] It should be noted that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion having one or more wires (electronic device), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0093] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0094] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0095] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0096] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0097] In the present invention, unless otherwise specified or limited, the terms "installed," "connected," "connect," "fixed," etc. should be understood in a broad sense. For example, they can refer to fixed connection, detachable connection, or integration; mechanical connection, electrical connection; direct connection, or indirect connection through an intermediate medium; internal communication between two components, or interaction between two components, unless otherwise specified. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0098] In the present invention, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediary. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0099] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. An active suspension control method, characterized in that: include: Acquiring multi-source data, wherein the multi-source data includes vehicle information, perception information, and control information; generating, using a deep learning model, recommended control parameters for advance control of the active suspension based on the multi-source data; The active suspension is controlled based on the suggested control parameters.

2. The active suspension control method according to claim 1, characterized in that: The method further comprises: Obtaining basic control parameters according to the perception information; The controlling of the active suspension based on the recommended control parameters includes: The basic control parameters are updated based on the recommended control parameters to obtain target control parameters, and the active suspension is controlled according to the target control parameters.

3. The active suspension control method according to claim 2, characterized in that: The updating of the basic control parameters based on the recommended control parameters to obtain target control parameters includes: A weighted sum is performed on the recommended control parameter and the basic control parameter to obtain the target control parameter.

4. The active suspension control method according to claim 2, characterized in that: The method further comprises: Utilize the basic control parameters to optimize the parameters of the deep learning model.

5. The active suspension control method according to claim 2, characterized in that: The active suspension includes four suspension assemblies, each of which corresponds to one of the four wheels of the vehicle. The target control parameters include four target spring stiffnesses and four target shock absorber damping values ​​corresponding to the four suspension assemblies. The controlling the active suspension of the vehicle according to the target control parameter includes: The elastic components of the four suspension assemblies are controlled according to the four target spring stiffnesses, and the shock absorbing dampers of the four suspension assemblies are controlled according to the four target shock absorbing dampings.

6. The active suspension control method according to claim 1, characterized in that: The vehicle information includes at least one of on-board processor information, on-board memory information, localization information, information perception, path planning information, system controller information, on-board map, and vehicle mode; the perception information includes multiple of radar system acquisition information, displacement sensor acquisition information, acceleration sensor acquisition information, camera acquisition information, microphone acquisition information, and surrounding environment acquisition information; the control information includes at least one of internal visual information, internal audio information, external visual information, external audio information, communication connection information, switch connection information, and drive module information.

7. The active suspension control method according to any one of claims 1 to 6, characterized in that: The method further comprises: Sending the multi-source data to a data center so that the data center optimizes parameters of the deep learning model; Receive the deep learning model with optimized parameters sent by the data center.

8. The active suspension control method according to claim 7, characterized in that: Part of the multi-source data is obtained from the data center via a mobile network.

9. An active suspension control system, characterized in that: include: A data acquisition device for acquiring multi-source data, wherein the multi-source data includes vehicle information, perception information, and control information; active suspension; and A controller, configured to execute the active suspension control method according to any one of claims 1 to 8.

10. A vehicle, characterized in that: include: The active suspension control system as claimed in claim 9.

Images