Vehicle suspension control method, device, equipment, medium, program product and vehicle

Abstract

The invention relates to a vehicle suspension control method, device and equipment, a medium, a program product and a vehicle, and a suspension of the vehicle is controlled to carry out adjustment operation according to vehicle driving road condition information and physiological data of target drivers and passengers on the vehicle. The invention aims to improve the comfort of the vehicle.

Description

Technical Field

[0001] The present application relates to the field of vehicle suspension control, and in particular to a vehicle suspension control method, device, equipment, medium, program product and vehicle. Background Art

[0002] During driving, adjustments to the vehicle's suspension can help the vehicle adapt to road fluctuations, maintain good vehicle ride comfort, and enhance ride comfort. Currently, most suspension control strategies are based on fixed road condition information, but driving comfort still needs to be improved. Summary of the Invention

[0003] The embodiments of the present application provide a vehicle suspension control method, device, equipment, medium, program product and vehicle, which improve vehicle comfort and at least partially solve the above-mentioned technical problems.

[0004] To achieve the above-mentioned object, according to a first aspect of the present application, a vehicle suspension control method is provided, the vehicle suspension control method comprising:

[0005] The suspension of the vehicle is controlled to perform adjustment operations according to the road condition information of the vehicle and the physiological data of the target driver and passenger in the vehicle.

[0006] According to a second aspect of the present application, there is provided a vehicle suspension control device, comprising:

[0007] The control module is used to control the suspension of the vehicle to perform adjustment operations according to the road condition information of the vehicle and the physiological data of the target driver and passenger in the vehicle.

[0008] According to a third aspect of the present application, an electronic device is also provided, comprising a processor connected to a memory, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to execute any of the above-mentioned vehicle suspension control methods.

[0009] According to a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it is any of the above-mentioned vehicle suspension control methods.

[0010] According to a fifth aspect of the present application, a computer program product is provided, which includes a computer program, and the computer program is executed by a processor to implement any of the above-mentioned vehicle suspension control methods.

[0011] According to a sixth aspect of the present application, a vehicle is provided, comprising the electronic device as described above, or comprising the vehicle suspension control device as described above.

[0012] The vehicle suspension control method provided in the embodiment of the present application controls the suspension of the vehicle to perform adjustment operations based on the road condition information of the vehicle and the physiological data of the target driver and passenger on the vehicle, avoiding adjustments based on fixed road condition information. The vehicle suspension can be personalized adjusted according to the individual differences of the target passengers on the vehicle and the differences in their physiological states at different times, which can further improve the comfort of the vehicle during driving and enhance the user experience.

[0013] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] To more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present application. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0015] In order to more completely understand the present application and its beneficial effects, the following description will be given in conjunction with the accompanying drawings, wherein the same drawing numbers represent the same parts in the following description.

[0016] Figure 1 1 is a flow chart of an embodiment of a vehicle suspension control method provided in an embodiment of the present invention;

[0017] Figure 2 is a schematic diagram of the relationship between road condition types and suspension control modes provided in an embodiment of the present invention;

[0018] Figure 3 Schematic diagram of the multi-view fusion algorithm architecture provided in an embodiment of the present invention;

[0019] Figure 4 Schematic diagram of the bilateral semantic segmentation algorithm architecture provided in an embodiment of the present invention;

[0020] Figure 5 is a schematic diagram of the feature fusion process provided in an embodiment of the present invention;

[0021] Figure 6 1 is a schematic diagram of the output optimization process of the bilateral semantic segmentation algorithm provided in an embodiment of the present invention;

[0022] Figure 7 is a schematic diagram of a vehicle suspension control system provided in an embodiment of the present invention;

[0023] Figure 8 is a schematic structural diagram of a vehicle suspension control device provided in an embodiment of the present invention;

[0024] Figure 9 2 is a schematic structural diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0026] During driving, adjustments to the vehicle's suspension can help the vehicle adapt to road fluctuations, maintain good vehicle ride comfort, and enhance ride comfort. Currently, vehicle suspension adjustments are based on fixed road condition information, but driving comfort still needs to be improved.

[0027] The inventors discovered that related suspension control systems primarily adjust suspension stiffness and damping based on preset driving modes (e.g., comfort mode, sport mode) or road condition information (e.g., road bumpiness) detected by vehicle sensors. These adjustments are typically based on universal standards or preset driving preferences, are relatively static, and lack immediate response to the driver or passenger's current physiological state. Consequently, these adjustments present at least the following issues, resulting in low vehicle comfort:

[0028] (1) Lack of personalized adjustment.

[0029] Uniform standards: Adjustments are made based on fixed road condition information, without considering individual differences among passengers and differences in their physiological states at different times, making it impossible to achieve personalized comfort adjustment.

[0030] Unable to respond to passenger needs: Different passengers have different tolerances to vibration and bumps, and the system cannot be adjusted according to the specific needs of passengers, resulting in a poor riding experience.

[0031] (2) Limited road condition information.

[0032] Single data source: Relying on information about the road ahead of the vehicle for prediction and adjustment, the data source is single and may not fully reflect the complexity of actual road conditions.

[0033] Response lag: Only part of the road condition information can be predicted in advance, and the response to sudden changes in road conditions is slow, and the adjustment accuracy and real-time performance are not high.

[0034] (3) Limited data processing capabilities.

[0035] Single data processing: Since it mainly processes road condition data, it lacks the fusion processing of multi-source data and cannot comprehensively evaluate and adjust the suspension system.

[0036] Lack of intelligent optimization: Since preset algorithms are usually used, they lack intelligent optimization and adaptive capabilities, making it difficult to achieve continuous optimization in a dynamic environment.

[0037] In order to solve the above problems, the embodiments of the present application propose a vehicle suspension control method, device, equipment, medium, program product and vehicle. The embodiments of the present application control the suspension of the vehicle for adjustment operations based on the road condition information of the vehicle and the physiological data of the target driver and passengers in the vehicle. The vehicle suspension can be adjusted in a personalized and multi-data fusion manner, thereby improving the vehicle comfort.

[0038] Specifically, the vehicle suspension control method of the present application can be applied to vehicles, such as automobiles, electric vehicles, hybrid vehicles, and the like. The vehicle suspension control method can be implemented by a vehicle suspension control device, which can be installed on the vehicle. The embodiments will be described in detail below, taking the vehicle suspension control device as an example.

[0039] Correspondingly, if Figure 1 As shown, the vehicle suspension control method may include the following steps:

[0040] S10, controlling the suspension of the vehicle to perform an adjustment operation based on road condition information of the vehicle and physiological data of a target driver or passenger in the vehicle;

[0041] In this embodiment, the road condition information of the vehicle refers to relevant information about the road conditions ahead of the vehicle, and is a major factor that affects the driving stability of the vehicle.

[0042] Physiological data of target vehicle occupants can be used to assess their physiological status. Target occupants can be all or some of the vehicle's occupants. Physiological data can be obtained in real time through smart wearable devices worn by the target occupants.

[0043] Optionally, the road condition information includes at least one of navigation information, traffic information, road curvature, road smoothness, obstacle detection results, and weather conditions. Road smoothness, obstacle detection results, and weather conditions all affect vehicle driving stability. Adjusting the stiffness and damping ratio of the vehicle suspension based on this information can achieve smoother vehicle driving.

[0044] Optionally, the physiological data includes at least one of heart rate, body temperature, oxygen saturation, skin conductivity, and body temperature. Heart rate, body temperature, oxygen saturation, skin conductivity, and body temperature are all parameters affected by the target driver's physiological state and can represent the target driver's or passenger's physiological state in real time. Based on these parameters, the vehicle suspension can be personalized and adjusted to provide a better riding experience for the user.

[0045] The vehicle's suspension is an important component of the vehicle. It is installed on the vehicle chassis and connects the vehicle to the wheels. It can absorb the impact and vibration caused by road irregularities to ensure the vehicle's driving stability and ride comfort. Based on road condition information and physiological data, the vehicle's suspension is comprehensively controlled to perform adjustment operations to achieve personalized and fine-tuning of the chassis suspension control.

[0046] Optionally, based on the road condition information of the vehicle and the physiological data of the target driver and passenger in the vehicle, a suspension control strategy and driving strategy that are more suitable for the current road condition and the current physiological state of the target driver and passenger can be determined, and the vehicle suspension is controlled based on the determined suspension control strategy to perform corresponding adjustment operations, such as adjusting the suspension stiffness and damping, so as to provide a riding experience that is more suitable for the vehicle driving environment and the target driver and passenger, thereby improving the comfort of driving the vehicle.

[0047] In the technical solution disclosed in this embodiment, the suspension of the vehicle is controlled to perform adjustment operations based on the road condition information of the vehicle and the physiological data of the target driver and passenger on the vehicle, avoiding adjustments based on fixed road condition information. The suspension of the vehicle can be adjusted in a personalized manner according to the individual differences of the target passengers on the vehicle and the differences in their physiological states at different times, so that the suspension control moves from personalized difference processing for the environment to personalized difference processing for different people and different physiological states, thereby further improving the comfort of the vehicle during driving and improving the user experience.

[0048] Optionally, step S10 may include:

[0049] Controlling the suspension of the vehicle to perform an adjustment operation based on road condition information of the vehicle and physiological data of a target driver or passenger in the vehicle includes:

[0050] determining the physiological state of the target driver or passenger based on the physiological data;

[0051] determining target control parameters according to the physiological state and the road condition information;

[0052] According to the target control parameter, the suspension of the vehicle is controlled to perform an adjustment operation.

[0053] In this embodiment, after preprocessing the physiological data, feature extraction processing is performed. The preprocessing includes signal filtering, format conversion, time synchronization, etc. to ensure data quality and consistency. Physiological data is data on the physiological state of the target driver and passenger. After preprocessing, feature extraction can be performed on the physiological data to obtain physiological features for use in evaluating or classifying the physiological state of the target driver and passenger. Road condition information is data related to the road conditions ahead of the vehicle. It is used to predict the bumps of the vehicle when the vehicle passes through the road ahead, and to determine a better suspension control strategy to deal with the road conditions ahead. Based on the physiological state and road condition information, the target control parameters for the suspension can be comprehensively determined, and then the vehicle suspension can be adjusted according to the target control parameters, thereby realizing a personalized, multi-dimensional suspension control solution and improving user comfort.

[0054] Optionally, determining a target control parameter according to the physiological state and the road condition information includes:

[0055] determining a suspension control mode according to the road condition information;

[0056] determining control parameters according to the suspension control mode;

[0057] The control parameter is adjusted according to the physiological state to obtain the target control parameter.

[0058] In this embodiment, different suspension control modes can be set according to the road condition information. According to the road condition information, multiple road condition types can be obtained. Each road condition type is preset to be associated with multiple suspension control modes. The suspension control mode includes at least one of a smooth adjustment mode, a damping adjustment mode, an enhanced adjustment mode, and an adaptive adjustment mode. Figure 2 If the road condition information determines that the road condition is flat, a smooth adjustment mode can be used. If the road condition information determines that the road condition is bumpy, a damping adjustment mode can be used. If the road condition information determines that the road condition is gravel, an enhanced adjustment mode can be used. If the road condition information determines that the road condition is steep, an adaptive adjustment mode can be used. After determining the suspension control mode, the suspension control mode can judge the current vehicle condition, obtain initial control parameters, and then adjust the control parameters based on the physiological state. The control parameters may include the damping ratio and stiffness of the suspension. The corresponding target control parameters may include a target damping ratio and a target stiffness. For example, when the user is in a nervous state, the initially obtained damping ratio can be increased to adjust the shock absorber to better suppress vehicle body vibration and improve vehicle handling stability.

[0059] In this way, the basic suspension control mode is first determined by the road condition information, and then the control parameters in the suspension control mode are adjusted according to the physiological state. The suspension control can be performed based on the road condition information and combined with the physiological state, which can make the suspension control based on the road condition information more accurate, thereby improving the comfort of the suspension control based on the road condition information.

[0060] Optionally, determining a target control parameter according to the physiological state and the road condition information may further include:

[0061] A target relationship combination including the physiological state and the road condition information is determined from a plurality of relationship combinations, and the target control parameter is determined according to a control parameter corresponding to the target relationship combination.

[0062] In this embodiment, a mapping table can be pre-established. This preset mapping table includes multiple relationship combinations between preset physiological states and preset road condition information, as well as corresponding vehicle suspension control parameters. The control parameters may include at least one of damping ratio and stiffness. Based on the currently acquired physiological state and road condition information, the mapping table is queried to determine the corresponding relationship combination. The preset physiological state for this relationship combination is identical to the current physiological state, and the preset road condition information is identical to the current road condition information. The control constant corresponding to this relationship combination is set as the target control parameter to efficiently and accurately control the vehicle suspension, further improving vehicle comfort.

[0063] Optionally, before determining a target relationship combination including the physiological state and the road condition information from a plurality of relationship combinations, the method further includes:

[0064] Based on the preset physiological state and the preset road condition information, a plurality of relationship combinations are formed, and different relationship combinations are correspondingly set with different fusion weights;

[0065] For each of the relationship combinations, the control parameter corresponding to the relationship combination is obtained by fusion according to the fusion weight corresponding to the relationship combination, the first control parameter of the preset physiological state, and the second control parameter corresponding to the preset road condition information.

[0066] In this embodiment, a mapping table needs to be pre-constructed. The process of constructing the mapping table requires first constructing multiple relationship combinations, with multiple preset road condition information and multiple preset physiological states preset. Each preset road condition information corresponds to a suitable first control parameter, and each preset physiological state corresponds to a suitable second control parameter. Based on the association between the preset road condition information and the preset physiological state, multiple relationship combinations are obtained. Each relationship combination includes a preset physiological state and a preset road condition information. Each relationship combination is different, and different preset physiological states and / or different preset road condition information exist between two relationship combinations. For each relationship combination, a fusion weight is set between the corresponding preset physiological state and the preset road condition information, so that the first control parameter corresponding to the preset physiological state and the second control parameter corresponding to the preset road condition information are fused based on the fusion weight. Specifically, for the same first control parameter and second control parameter, they are weighted according to the fusion weight to obtain the target control parameter. For different control parameters and second control parameters, they are both used as target control parameters, and finally a number of target control parameters are fused.

[0067] In this way, by setting different fusion weights for different relationship combinations and fusing their corresponding first control parameters and second control parameters, control parameters that meet the corresponding fusion requirements of each relationship combination can be obtained in advance, so that the suspension can be controlled more accurately based on road conditions and physiological status, further improving vehicle comfort.

[0068] Optionally, the target control parameter includes at least one of a target damping ratio and a target stiffness, and controlling the suspension of the vehicle to perform an adjustment operation according to the target control parameter includes:

[0069] The damping ratio of the shock absorber of the suspension is adjusted to a target damping ratio, and / or the stiffness of the spring structure of the suspension is adjusted to the target stiffness.

[0070] In this embodiment, adjusting the damping ratio of the suspension shock absorber and the suspension spring structure is key to optimizing the suspension system. The shock absorber can be an adjustable damping shock absorber, while the suspension spring structure can be an air spring with adjustable stiffness. The suspension actuator can be controlled to adjust the shock absorber's damping ratio to a target damping ratio or the spring structure's stiffness to a target stiffness, thereby achieving vehicle height adjustment, damping force control, and spring stiffness control, improving vehicle comfort.

[0071] Optionally, determining the physiological state of the target driver or passenger based on the physiological data includes:

[0072] performing feature extraction on the physiological data to obtain physiological features of the physiological data;

[0073] Based on the physiological characteristics, the physiological state of the target driver is determined.

[0074] In this embodiment, after preprocessing the physiological data, corresponding physiological features can be extracted from the physiological data. The physiological features can be at least one of time domain features, frequency domain features, and nonlinear features. The physiological data can be physiological signals. Time domain features are extracted from continuous physiological signals, such as the mean, minimum, maximum, and standard deviation of heart rate, the average conductance level and response frequency of skin electrical activity, etc. Frequency domain features are extracted from signals through Fourier transform, such as the ratio of low-frequency to high-frequency components of heart rate variability, which helps identify physiological states. Nonlinear features are obtained by analyzing the nonlinear properties of signals, such as fractal dimension or entropy in chaos theory. Time domain features (such as the instantaneous value of heart rate) and nonlinear features (such as heart rate variability) can be very important because they can reflect the emotional state of the target driver or occupant, while frequency domain features can help analyze periodic patterns in physiological signals, such as the rhythm of breathing rate, which can be useful for understanding the long-term impact of the vehicle environment on the target driver or occupant. The above physiological characteristics can be combined to analyze the physiological conditions of the target driver and passenger from different dimensions. Combining these physiological characteristics can more comprehensively characterize the real-time physiological status of the target driver and passenger.

[0075] Optionally, there are physiological characteristics from at least two different perspectives, and determining the physiological state of the target driver or passenger based on the physiological characteristics includes:

[0076] Perform feature fusion processing on the physiological features of different perspectives to obtain fused physiological features;

[0077] A preset physiological state among multiple preset physiological states that matches the fused physiological feature is determined as the physiological state of the target driver or passenger.

[0078] In this embodiment, there are at least two physiological features from different perspectives, and different perspectives indicate that the data sources of these physiological features are different. In this embodiment, a variety of physiological features can be obtained based on physiological data of multiple dimensions or different feature extraction methods. These physiological features may be different physiological features from the same physiological data, such as the time domain features and nonlinear features of heart rate, or they may be the same physiological features from different physiological data, such as the time domain features of body temperature and the time domain features of heart rate. Since these physiological features belong to different dimensions, in order to retain more effective information during fusion and remove redundant and invalid information, the physiological features can be input into a multi-view fusion algorithm to obtain fused physiological features. The multi-view fusion algorithm can integrate information from different views or data sources to obtain a more comprehensive and in-depth understanding. To avoid the possibility that a single data source may not be sufficient to provide sufficient information, refer to Figure 4The multi-view fusion algorithm can make full use of the advantages of different data sources and improve the depth and breadth of data analysis. Based on the fused physiological characteristics, it can more accurately classify the physiological conditions of the target driver and passenger, make the suspension adjustment more in line with the needs of the target driver and passenger, and further improve vehicle comfort.

[0079] Optionally, the multi-view fusion algorithm is constructed based on physiological data sets corresponding to at least two perspectives, and determines a fusion matrix between the at least two perspectives.

[0080] In this embodiment, physiological data sets corresponding to at least two different perspectives are obtained in advance. The fusion method between the two perspectives is determined through the physiological data sets corresponding to these two perspectives. The fusion matrix between the data corresponding to the two perspectives can be determined. The fusion matrix constructs a multi-view fusion algorithm, which can be used to fuse the physiological features corresponding to the two perspectives, thereby improving the fusion accuracy.

[0081] Optionally, the process of determining the fusion matrix includes the following steps:

[0082] Obtaining a similarity measure between sample physiological data in the physiological dataset;

[0083] Determining a similarity matrix of the physiological dataset corresponding to the perspective according to the similarity metric;

[0084] The fusion matrix is obtained according to the similarity matrices of the at least two perspectives.

[0085] In this embodiment, a complete physiological data set is set, which includes V perspectives and n sample physiological data, and defines is the data matrix of the vth perspective. v is the number of dimensions, is the sample physiological data in the vth perspective and samples The similarity measure between them. v It's X v The similarity matrix of , we get the following formula:

[0086]

[0087] stS1=1,0≤s ij ≤1

[0088] in, is the i-th sample of the v-th view, γ is the regularization parameter, S v Is the similarity matrix of view V. Based on the similarity matrix of each view in the physiological dataset Substitute the following formula to obtain the objective function. By solving the objective function, a fusion matrix Z can be adaptively learned through vector weights.

[0089]

[0090] stS1=1,0≤s ij ≤1, rank(L z ) = nc,

[0091] Z1=1,0≤z ij ≤1,

[0092] in, is the weight of the similarity of the jth column in the vth view.

[0093] Solving the above objective function yields the optimal fusion matrix. Based on this fusion matrix, a multi-view fusion algorithm is constructed to quickly and accurately fuse multiple distinct physiological features. The physiological condition of the target driver and occupant is then classified based on the fused physiological features. This allows for a real-time classification of the target driver and occupant's physiological state, based on the combined effects of each physiological feature.

[0094] During classification, corresponding multi-perspective physiological data can be obtained in advance for different preset physiological states. After fusion using the above method, the preset physiological characteristics corresponding to the different preset physiological states can be obtained. The current fused physiological characteristics are matched with each preset physiological characteristic, and the preset physiological state corresponding to the matched preset physiological characteristics is determined as the current physiological state, thereby realizing the classification of the physiological condition of the target driver and passenger through physiological characteristics and obtaining the physiological state of the target driver and passenger.

[0095] Optionally, obtaining the fusion matrix according to the similarity matrices of the at least two perspectives includes:

[0096] constructing an objective function based on the similarity matrices of the at least two perspectives, wherein a norm constraint is imposed on the similarity matrix of each perspective;

[0097] Solve the objective function to obtain the fusion matrix.

[0098] In this embodiment, when constructing the objective function based on the similarity matrices of at least two perspectives, a non-convex approximation method using the Gamma norm as the matrix rank function is used to apply the Gamma norm to the similarity matrices corresponding to each perspective. This can better approximate the rank. For large singular values, the Gamma norm greatly weakens the contribution; for small singular values, the Gamma norm brings their contribution close to zero, thereby improving the convergence of the objective function and enhancing construction efficiency and accuracy. Specifically, after applying the norm constraint to the similarity matrices of each perspective, the objective function is updated to the following objective function formula.

[0099]

[0100] stS1=1,0≤s ij ≤1,rank(L z )=nc,

[0101] Z1=1,0≤z ij ≤1,

[0102] Solve the updated objective function: define σ i (L s ) is L s The i-th smallest eigenvalue of s is positive semidefinite, that is, σ i (L s )≥0, so the constraint rank(L s ) = nc will ensure According to Ky Fan's theorem, we can get the following formula:

[0103]

[0104] Then solving the objective function is equivalent to solving the following formula:

[0105]

[0106] stS1=1,0≤s ij ≤1,

[0107] Z1=1,0≤z ij ≤1,

[0108] Then the augmented Lagrangian function of this formula is as follows:

[0109]

[0110] Among them, C is the Lagrange multiplier and ρ is the penalty parameter.

[0111] For a better understanding, the following provides a specific construction scenario:

[0112] In this scenario, the alternating direction multiplier method is used to calculate the optimal solution of the above formula, using the K nearest neighbor graph of each event to initialize S v , αv = 1 / number of viewing angles, ρ0 = 10 8 , ρ = 0.1, δ = 1.5, by updating the variables in the above formula until the above objective function converges, the final fusion matrix and connected component results are obtained.

[0113] Optionally, the vehicle is communicatively connected to the drone, and before controlling the suspension of the vehicle to perform an adjustment operation based on the road condition information of the vehicle and the physiological data of the target driver and passenger on the vehicle, the method further includes:

[0114] receiving a road condition image in front of the vehicle collected by the drone, and determining road condition information based on the road condition image; or

[0115] Receive road condition information sent by the drone, where the road condition information is determined by the drone based on the road condition image.

[0116] In this embodiment, the vehicle can also be connected to a drone for communication. The drone can be a companion drone of the vehicle, such as a small drone mounted on the vehicle. During driving, the drone is started, and the high-definition camera and sensors on board are used to collect real-time images of the road conditions in front of the vehicle. The high-definition camera and other devices on board the drone capture road surface images at a fixed frequency. The image resolution and frame rate should be high enough to ensure the accuracy and real-time performance of subsequent image processing. The road surface flatness, obstacles, weather conditions, etc. can be identified as road condition information through the road condition images. This process can be completed by the vehicle or by the drone. That is, the drone can send the vehicle either road condition information processed based on the road condition images or road condition images.

[0117] Using drones to capture road imagery provides vehicles with a broader and more flexible field of view. Real-time images of the road ahead are captured and classified using image processing technology to generate road condition information. This helps vehicles anticipate and adapt to upcoming road conditions, enabling them to select appropriate control strategies and adjust the vehicle's suspension, further improving safety and comfort.

[0118] Optionally, determining the road condition information based on the road condition image includes:

[0119] Performing semantic segmentation processing on the road condition image to obtain segmented image features;

[0120] The road condition information is determined according to the segmented image features.

[0121] In this embodiment, after a drone captures road condition images, the images can be preprocessed. This preprocessing includes at least one of image correction, illumination and color correction, and image enhancement. Image correction can geometrically correct the captured road condition images to eliminate image distortion caused by changes in the drone's flight attitude. Illumination and color correction can adjust the brightness and contrast of the road condition images based on ambient light variations, ensuring image consistency under varying lighting conditions. Image enhancement can enhance the clarity and contrast of road condition images through techniques such as sharpening and noise reduction, improving the accuracy of subsequent image analysis.

[0122] Optionally, semantic segmentation is performed on the preprocessed road condition information to obtain segmented image features. Based on these segmented image features, edge detection and texture analysis are performed on the road condition image. Edge detection algorithms such as Canny and Sobel are used to identify edge features in the image to highlight the texture and structure of the road surface. Texture features of the road surface are extracted using methods such as gray-level co-occurrence matrix (GLCM) and local binary pattern (LBP). Target detection is performed based on edge and texture features to identify specific targets in the image, such as potholes, cracks, and waterlogging, to determine road condition information.

[0123] Furthermore, the road condition image can be semantically segmented according to a lightweight bilateral semantic segmentation algorithm. The bilateral semantic segmentation algorithm can be a real-time semantic segmentation network BiSeNet. Figure 4 , the bilateral part includes the simplified spatial path on the left side of the figure and the context path on the right side. The green part on the left is the spatial path (Spatial Path), which consists of a three-layer network structure. Each layer contains a convolution layer Conv with a stride of 2, followed by a BN layer and a ReLU activation function. Feature extraction is performed through three convolutional layers. Each convolutional layer can retain the spatial detail information in the image as much as possible and generate a high-resolution feature map. The yellow and blue parts on the right are the context path (Context path). Through lightweight four-layer fast downsampling, the largest possible receptive field is obtained. The last two downsamplings are optimized using the attention refinement module ARM. ARM uses global average pooling to capture the output features of each stage and calculates an attention vector to guide feature learning, so that the features output by each layer are more accurate. The context path enables the output features to have texture information in a large area and rich global spatial context information.

[0124] Since the features of the two paths are different in the feature expression level, they cannot be simply added together. Therefore, the feature fusion module FFM is used to fuse the features of the two parts. Figure 5As shown in the figure, the input of the two parts uses batch normalization to balance the feature scale, and then the features are globally pooled to obtain the feature vector. Next, two layers of convolution and ReLU functions are used to obtain the weight parameters with the attention mechanism. Finally, the normalized weights are weighted to the features of each channel through the Sigmoid activation function. Feature selection and combination are performed to obtain the fused image features. Based on the fused image features, the mapping processing of the fully connected layer is performed to achieve segmentation of different areas of the road condition image and obtain the segmented image features.

[0125] Optionally, the back end of the bilateral semantic segmentation algorithm is connected to an optimization network based on a mean approximate field, and the optimization network is used to optimize the output of the bilateral semantic segmentation algorithm.

[0126] In this embodiment, since the lightweight bilateral semantic segmentation algorithm BiSeNet has poor edge prediction results in different data categories, on the basis of the main algorithm, an optimization network CRF based on the average approximate field is added to its back end to optimize the output, that is, to optimize the image features after segmentation and improve the prediction accuracy. Figure 4 CRF is a Markov chain model that uses global observations for prediction. It leverages the correlation information between pixels to enhance edges and details, making the segmentation results more detailed and preventing blurring of object edges. Furthermore, the introduction of conditional random fields allows for global image analysis, improving segmentation consistency.

[0127] The output of the optimized bilateral semantic segmentation algorithm based on the optimized network of the average approximate field includes the following processing steps:

[0128] (1) Initialization: For each pixel i, let:

[0129]

[0130] Among them, Q i (l) is an independent marginal distribution, Z i =exp(U i (l)), As can be seen from the above expression, initialization actually involves performing a Softmax operation on the unary potential energy passed by the convolutional neural network. This compresses the unary potential function value to the range [1, 0], thereby initializing the model's probability distribution. The Softmax operation is a common operation in convolutional neural networks, and the error generated by this step can be passed to the convolutional neural network through backpropagation.

[0131] (2) Information transfer: Before the network model converges, let:

[0132]

[0133] Among them, k (m) is a Gaussian kernel used to measure the eigenvector f i and f j This step actually performs Gaussian blur on the image after the initialization operation through the Gaussian kernel, which is equivalent to the convolution operation of the neural network. Therefore, this step can also be used as part of the convolutional neural network.

[0134] (3) Weighted summation: After the first two steps are completed, the output of the Gaussian filter is weighted summed, that is,

[0135]

[0136] Its role is to give a certain penalty when different labels are assigned to similar pixels. The correlation conversion step can be completed with a convolutional layer.

[0137] (4) Add unary potential energy. This step directly subtracts the unary potential energy obtained by the convolutional neural network from the output obtained in the previous step, that is,

[0138]

[0139] (4) Normalizing: The regularization process can be regarded as a softmax operation, that is,

[0140]

[0141] Reference Figure 6 , Figure 6 This is a complete iterative process of the average approximate field CRF: for an image I, the unary potential energy U and the edge probability estimate Qin generated by the historical iteration are adjusted through the average approximate field CRF to obtain a new edge probability estimate Qout, which is used to obtain the segmented image features. Then, the current road condition information is output based on the updated segmented image features.

[0142] Alternatively, the process of obtaining road condition information based on drone-generated images of the road ahead of the vehicle can be performed on the drone itself. The generated road condition information, such as the codes for different identified road condition types, can be output in a standardized format. The drone's wireless communication module can then transmit the road condition classification results to the vehicle in real time for use in controlling the suspension.

[0143] Optionally, the vehicle communicates with a smart wearable device, and the method further includes:

[0144] Receive physiological data sent by the smart wearable device; the smart wearable device includes at least one of a smart watch or a smart helmet.

[0145] In this embodiment, the vehicle can communicate with smart wearable devices, which are new types of daily wearable mobile smart terminals that realize functions such as user interaction, life entertainment, and human body monitoring. These devices are mostly in the form of portable accessories with partial computing functions that can be connected to mobile phones, vehicles, and various terminals. In the vehicle driving scenario of this embodiment, the smart wearable device may include at least one of a smart watch or a smart helmet. The smart wearable device is worn on the target driver and can collect at least one of the target driver's heart rate, body temperature, oxygen saturation, skin conductivity, and body temperature. By analyzing the above physiological data, the current physiological state of the target driver, such as relaxation, tension, fatigue, or wakefulness, is identified and used to control the adjustment of the vehicle suspension.

[0146] In addition to the physiological data such as heart rate and body temperature that can be collected by the smart watches mentioned above, other smart devices such as smart helmets and smart seats can also be integrated to collect more physiological indicators to more comprehensively reflect the comfort and health status of passengers.

[0147] For example, the smart watch's built-in heart rate monitor (such as photoplethysmography (PPG), blood oxygen sensor (SpO2), conductivity skin response sensor (EDA), and temperature sensor respectively collect physiological data such as heart rate, blood oxygen saturation, skin conductivity, and body temperature data, and then transmit them to the vehicle to improve the accuracy of subsequent analysis.

[0148] After acquiring physiological data, the vehicle can apply a bandpass filter to remove high-frequency noise (such as motion artifacts) and low-frequency drift from the signal while maintaining the key characteristics of the physiological signal, achieving both filtering and noise removal. Signal processing techniques, such as wavelet transforms or Fourier transforms, can be used to enhance signal clarity, highlight the characteristics of physiological signals, and achieve signal enhancement. If there is a slight time delay between different sensors, time synchronization correction can also be performed to ensure that all physiological signals are accurately aligned in time, achieving time synchronization correction.

[0149] Optionally, indicators for evaluating the effectiveness of suspension control, such as driving smoothness, ride comfort, and vehicle stability, can be defined to continuously monitor the effectiveness of suspension control, collect driving experience feedback, and evaluate the effectiveness of suspension control under different road conditions and physiological states. Specifically, after controlling the vehicle's suspension for adjustment based on road condition information and the physiological data of the target driver and passenger on the vehicle, the physiological data of the target driver and passenger can be recollected as post-feedback physiological data. Based on the post-feedback physiological data, a ride comfort index can be determined to adjust the control strategy for adjusting the suspension based on road condition information and physiological state, thereby further improving vehicle comfort.

[0150] Optionally, the method further includes:

[0151] According to the road condition information and the physiological data, the assisted driving strategy of the steering system and / or the assisted driving strategy of the braking system of the vehicle is adjusted.

[0152] In this embodiment, the target occupant can be the driver of the vehicle. By monitoring the driver's physiological data (such as heart rate and galvanic skin response), the vehicle's steering and / or braking systems can be adjusted. For example, the intensity of the steering assist can be adjusted. If the driver is nervous or fatigued, more steering assistance can be provided to reduce the driver's operating burden. Drones and vehicle-mounted sensors can also sense road curvature and possible obstacles in advance and use this as road condition information to adjust the steering system's response speed and sensitivity to improve safety and controllability.

[0153] Monitoring passengers' physiological reactions can help the system determine the need for sudden braking and adjust the braking force. For example, in an emergency, braking force can be increased to maximize safety. Traffic information provided by drones, as road condition information, can help vehicles slow down or stop before potential danger or congestion, optimizing braking response time and force.

[0154] Based on the above vehicle suspension control method, this embodiment further provides a vehicle suspension control system, which can be integrated into a vehicle. The vehicle suspension control system can include:

[0155] Vehicle-mounted drone module: used to collect real-time traffic information.

[0156] Smart wearable device monitoring module: used to collect physiological data of drivers and passengers.

[0157] Central control module: Used to control the vehicle suspension and perform adjustment operations through algorithm analysis based on the road condition information collected by the vehicle-mounted accompanying drone system and the physiological data collected by the smart wearable device monitoring system.

[0158] The vehicle suspension control system Figure 7 As shown. Includes:

[0159] The perception layer is used to collect environmental and vehicle status information. The perception layer includes an on-board companion drone module, a smart wearable device monitoring module, and vehicle sensors.

[0160] The data processing layer receives data from the perception layer and performs preprocessing, feature extraction, and preliminary analysis. It includes a data processing module and a feature extraction and fusion module. The data processing module performs preprocessing such as signal filtering, format conversion, and time synchronization to ensure data quality and consistency. The feature extraction and fusion module extracts meaningful features from the raw data and fuses data from multiple sources to form a unified input.

[0161] The decision-making control layer is used to conduct comprehensive analysis and decision-making based on the output of the data processing layer, including the central control module, performance evaluation and optimization module, etc.

[0162] The execution layer implements the commands generated by the decision-making and control layer to adjust the suspension state. This layer includes suspension actuators, which can include electric hydraulic suspension, active shock absorbers, air springs, and other mechanisms for dynamic suspension adjustment. The feedback mechanism collects execution results and forms a closed-loop control loop to ensure command execution accuracy and system stability.

[0163] Optionally, the vehicle's suspension control system can be integrated with the navigation system. By integrating the suspension control system with the navigation system, the suspension settings can be adjusted based on navigation information. The vehicle's suspension control system can also be integrated with the entertainment system: By integrating with the in-vehicle entertainment system, the in-vehicle atmosphere can be adjusted based on physiological state, such as adjusting music and lighting, to provide a better riding experience.

[0164] This embodiment also provides a vehicle suspension control device, which can be integrated into a vehicle, for example, Figure 8 As shown, the vehicle suspension control device may include:

[0165] The control module 1001 is used to control the suspension of the vehicle to perform adjustment operations according to the road condition information of the vehicle and the physiological data of the target driver and passenger in the vehicle.

[0166] Optionally, the control module 1001 is further configured to:

[0167] determining the physiological state of the target driver or passenger based on the physiological data;

[0168] determining target control parameters according to the physiological state and the road condition information;

[0169] According to the target control parameter, the suspension of the vehicle is controlled to perform an adjustment operation.

[0170] Optionally, the control module 1001 is further configured to:

[0171] determining the physiological state of the target driver or passenger based on the physiological data;

[0172] determining target control parameters according to the physiological state and the road condition information;

[0173] According to the target control parameter, the suspension of the vehicle is controlled to perform an adjustment operation.

[0174] Optionally, the suspension control mode includes at least one of a smooth adjustment mode, a vibration reduction adjustment mode, an enhanced adjustment mode, and an adaptive adjustment mode, and the control parameter includes at least one of a damping ratio and stiffness.

[0175] Optionally, the target control parameter includes at least one of a target damping ratio and a target stiffness, and the control module 1001 is further used to: adjust the damping ratio of the shock absorber of the suspension to the target damping ratio, and / or adjust the stiffness of the spring structure of the suspension to the target stiffness.

[0176] Optionally, the control module 1001 is further configured to: perform feature extraction on the physiological data to obtain physiological features of the physiological data;

[0177] Based on the physiological characteristics, the physiological state of the target driver is determined.

[0178] Optionally, there are at least two physiological features from different perspectives, and the control module 1001 is further configured to: perform feature fusion processing on the physiological features from different perspectives to obtain fused physiological features;

[0179] A preset physiological state among multiple preset physiological states that matches the fused physiological feature is determined as the physiological state of the target driver or passenger.

[0180] Optionally, the physiological data includes at least one of heart rate, body temperature, oxygen saturation, skin conductivity and body temperature.

[0181] Optionally, the control module 1001 is further used to: receive physiological data sent by the smart wearable device; the smart wearable device includes at least one of a smart watch or a smart helmet.

[0182] Optionally, the road condition information includes at least one of navigation information, traffic information, road curvature, road flatness, obstacle detection results and weather conditions.

[0183] Optionally, the vehicle is provided with a vehicle sensor, and the control module 1001 is further configured to collect the road condition information through the vehicle sensor.

[0184] Optionally, the control module 1001 is further configured to: receive a road condition image of the vehicle ahead collected by the drone, and determine road condition information based on the road condition image; or

[0185] Receive road condition information sent by the drone, where the road condition information is determined by the drone based on the road condition image.

[0186] Optionally, the control module 1001 is further configured to: perform semantic segmentation processing on the road condition image to obtain post-segmentation image features; and determine the road condition information based on the post-segmentation image features.

[0187] Optionally, the control module 1001 is further configured to adjust the assisted driving strategy of the steering system and / or the assisted driving strategy of the braking system of the vehicle according to the road condition information and the physiological data.

[0188] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0189] In this embodiment, the suspension of the vehicle is controlled to perform adjustment operations based on the road condition information of the vehicle and the physiological data of the target driver and passenger on the vehicle, avoiding adjustments based on fixed road condition information. The suspension of the vehicle can be adjusted in a personalized manner based on the individual differences of the target passengers on the vehicle and the differences in their physiological states at different times, which can further improve the comfort of the vehicle during driving and enhance the user experience.

[0190] Accordingly, an embodiment of the present application further provides an electronic device, such as Figure 9 As shown, Figure 9 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 1100 also includes a processor 1101 having one or more processing cores, a memory 1102 having one or more computer-readable storage media, and a computer program stored on the memory 1102 and executable on the processor. The processor 1101 is electrically connected to the memory 1102. Those skilled in the art will understand that the electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0191] The processor 1101 is the control center of the electronic device 1100. It connects the various parts of the entire electronic device 1100 using various interfaces and lines. By running or loading software programs and / or units stored in the memory 1102 and calling data stored in the memory 1102, it executes various functions of the electronic device 1100 and processes data, thereby monitoring the entire electronic device 1100. The processor 1101 can be a processor CPU, a graphics processor GPU, a network processor (NP), etc., and can implement or execute the various methods, steps, and logic blocks disclosed in the embodiments of this application.

[0192] In the embodiment of the present application, the processor 1101 in the electronic device 1100 loads instructions corresponding to one or more application processes into the memory 1102 according to the following steps, and the processor 1101 runs the application stored in the memory 1102 to implement various functions, such as:

[0193] The suspension of the vehicle is controlled to perform adjustment operations according to the road condition information of the vehicle and the physiological data of the target driver and passenger in the vehicle.

[0194] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0195] Optional, such as Figure 9 As shown, the electronic device 1100 further includes: a touch screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106, and a power supply 1107. Among them, the processor 1101 is electrically connected to the touch screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106, and the power supply 1107 respectively. Those skilled in the art will understand that Figure 9 The electronic device structure shown in the figure does not constitute a limitation to the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0196] The touch display screen 1103 can be used to display a graphical user interface and receive user actions on the operation instructions generated by the graphical user interface. The touch display screen 1103 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the electronic device, and these graphical user interfaces can be composed of graphics, text, icons, videos and any combination thereof. Optionally, a liquid crystal display (LCD), an organic light emitting diode (OLED, Organic Light-Emitting Diode) and the like can be used to configure the display panel. The touch panel can be used to collect the user's touch operation on or near it (such as the user uses any suitable object or accessory such as a finger, a stylus on the touch panel or near the touch panel) and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch direction, detects the signal caused by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into touch point coordinates, and then sends it to the processor 1101, and can receive commands sent by the processor 1101 and execute them. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 1101 to determine the type of touch event. The processor 1101 then provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present invention, the touch panel and the display panel can be integrated into the touch display screen 1103 to realize input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize input and output functions. That is, the touch display screen 1103 can also be used as part of the input unit 1106 to realize the input function.

[0197] The radio frequency circuit 1104 may be used to transmit and receive radio frequency signals, thereby establishing wireless communication with network medical devices or other electronic devices through wireless communication, and transmitting and receiving signals between network medical devices or other electronic devices.

[0198] The audio circuit 1105 can be used to provide an audio interface between the user and the electronic device through a speaker and a microphone. The audio circuit 1105 can convert the received audio data into an electrical signal and transmit it to the speaker, which then converts it into a sound signal for output. On the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 1105 and converted into audio data. The audio data is then output to the processor 1101 for processing, and then sent to another electronic device through the radio frequency circuit 1104, or the audio data is output to the memory 1102 for further processing. The audio circuit 1105 may also include an earphone jack to provide communication between external headphones and the electronic device.

[0199] The input unit 1106 may be configured to receive input digital, character information, or user feature information (such as fingerprint, iris, or facial information), and to generate keyboard, mouse, joystick, optical, or trackball signal input related to user settings and function control.

[0200] Power supply 1107 is used to supply power to various components of electronic device 1100. Optionally, power supply 1107 can be logically connected to processor 1101 via a power management device, thereby enabling the power management device to manage charging, discharging, and power consumption. Power supply 1107 can also include one or more DC or AC power supplies, a recharging device, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0201] although Figure 9 Not shown, the electronic device 1100 may further include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.

[0202] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0203] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0204] To this end, an embodiment of the present application provides a computer-readable storage medium storing a plurality of computer programs. The computer programs can be loaded by a processor to execute any one of the vehicle suspension control methods provided in the embodiments of the present application. The computer programs can execute the following steps of the vehicle suspension control method:

[0205] The suspension of the vehicle is controlled to perform adjustment operations according to the road condition information of the vehicle and the physiological data of the target driver and passenger in the vehicle.

[0206] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0207] The computer-readable storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0208] Since the computer-readable storage medium can implement the beneficially stored computer program that can implement any vehicle suspension control method provided in the embodiments of the present application, any vehicle suspension control method provided in the embodiments of the present application can be executed, the effect can be seen in detail in the previous embodiments and will not be repeated here.

[0209] Optionally, an embodiment of the present application may also provide a vehicle, which may be provided with the above-mentioned vehicle suspension control device, vehicle suspension control system, electronic equipment, computer-readable storage medium, computer program product, etc.

[0210] In the above-described vehicle suspension control method, vehicle suspension control device, electronic device, vehicle suspension control system, vehicle, computer-readable storage medium, computer program product, etc., the descriptions of various embodiments each have their own emphasis. For portions not described in detail in a particular embodiment, reference can be made to the relevant descriptions of other embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific operating processes and beneficial effects of the above-described vehicle suspension control device, vehicle, computer-readable storage medium, computer program product, and their corresponding units can be referred to in the description of the vehicle suspension control method in the above embodiments, and the details will not be repeated here.

[0211] The above is a detailed introduction to a vehicle suspension control method, a vehicle suspension control device, an electronic device, a vehicle suspension control system, a vehicle, a computer-readable storage medium, and a computer program product provided in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle suspension control method, characterized in that: The vehicle suspension control method comprises: The suspension of the vehicle is controlled to perform adjustment operations according to the road condition information of the vehicle and the physiological data of the target driver and passenger in the vehicle.

2. The vehicle suspension control method according to claim 1, wherein: The controlling of the suspension of the vehicle to perform an adjustment operation based on the road condition information of the vehicle and the physiological data of the target driver or passenger in the vehicle includes: determining the physiological state of the target driver or passenger based on the physiological data; determining target control parameters according to the physiological state and the road condition information; According to the target control parameter, the suspension of the vehicle is controlled to perform an adjustment operation.

3. The vehicle suspension control method according to claim 2, wherein: The determining of target control parameters according to the physiological state and the road condition information includes: determining a suspension control mode according to the road condition information; determining control parameters according to the suspension control mode; The control parameter is adjusted according to the physiological state to obtain the target control parameter.

4. The vehicle suspension control method according to claim 3, wherein: The suspension control mode includes at least one of a smooth adjustment mode, a vibration reduction adjustment mode, an enhanced adjustment mode, and an adaptive adjustment mode, and the control parameter includes at least one of a damping ratio and a stiffness.

5. The vehicle suspension control method according to claim 2, wherein: The target control parameter includes at least one of a target damping ratio and a target stiffness, and the controlling the suspension of the vehicle to perform an adjustment operation according to the target control parameter includes: The damping ratio of the shock absorber of the suspension is adjusted to the target damping ratio, and / or the stiffness of the spring structure of the suspension is adjusted to the target stiffness.

6. The vehicle suspension control method according to claim 2, wherein: Determining the physiological state of the target driver or passenger based on the physiological data includes: performing feature extraction on the physiological data to obtain physiological features of the physiological data; Based on the physiological characteristics, the physiological state of the target driver is determined.

7. The vehicle suspension control method according to claim 6, wherein: There are at least two physiological characteristics from different perspectives, and determining the physiological state of the target driver or passenger based on the physiological characteristics includes: Perform feature fusion processing on the physiological features of different perspectives to obtain fused physiological features; A preset physiological state among multiple preset physiological states that matches the fused physiological feature is determined as the physiological state of the target driver or passenger.

8. The vehicle suspension control method according to claim 1, wherein: The physiological data includes at least one of heart rate, body temperature, oxygen saturation, skin conductivity and body temperature.

9. The vehicle suspension control method according to claim 1, wherein: The vehicle communicates with the smart wearable device, and the method further includes: Receive physiological data sent by the smart wearable device; the smart wearable device includes at least one of a smart watch or a smart helmet.

10. The vehicle suspension control method according to claim 1, wherein: The road condition information includes at least one of navigation information, traffic information, road curvature, road flatness, obstacle detection results and weather conditions.

11. The vehicle suspension control method according to claim 1, wherein: The vehicle is provided with a vehicle sensor, and the road condition information is collected by the vehicle sensor.

12. The vehicle suspension control method according to claim 1, wherein: The vehicle is in communication with the drone, and before controlling the suspension of the vehicle to perform an adjustment operation based on the road condition information of the vehicle and the physiological data of the target driver and passenger in the vehicle, the method further includes: receiving a road condition image in front of the vehicle collected by the drone, and determining road condition information based on the road condition image; or Receive road condition information sent by the drone, where the road condition information is determined by the drone based on the road condition image.

13. The vehicle suspension control method according to claim 12, wherein: The determining of the road condition information based on the road condition image includes: Performing semantic segmentation processing on the road condition image to obtain segmented image features; The road condition information is determined according to the segmented image features.

14. The vehicle suspension control method according to any one of claims 1 to 13, characterized in that: The target occupant is a driver of the vehicle, and the method further includes: According to the road condition information and the physiological data, the assisted driving strategy of the steering system and / or the assisted driving strategy of the braking system of the vehicle is adjusted.

15. A vehicle suspension control device, characterized in that: include: The control module is used to control the suspension of the vehicle to perform adjustment operations according to the road condition information of the vehicle and the physiological data of the target driver and passenger in the vehicle.

16. An electronic device, characterized in that: The method comprises a processor connected to a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program in the memory to execute the vehicle suspension control method according to any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle suspension control method according to any one of claims 1 to 14 is implemented.

18. A computer program product, characterized in that The invention comprises a computer program, wherein the computer program is executed by a processor to implement the vehicle suspension control method according to any one of claims 1 to 14.

19. A vehicle, characterized in that: The method comprises the vehicle suspension control device according to claim 15 or the electronic device according to claim 16.

Images