Vehicle quick escape method and system, medium and electronic equipment

Abstract

The invention provides a vehicle quick escape method and system, a medium and electronic equipment, and relates to the technical field of vehicle brake control, and the method comprises the steps that the running road surface working condition and motion state parameters of a vehicle are acquired in real time, and the running road surface working condition comprises road surface composition materials and distribution of pits in a road surface; predicting a driving track of the vehicle in a preset time period according to the motion state parameters; based on a Bayesian network model, determining the probability that a target wheel of the vehicle falls into the pit at the target moment according to the driving track and the driving road surface working condition; under the condition that the probability is larger than a threshold value, target braking force needed by the target wheel to break away from the potholes is determined; and according to the target braking force, braking control is conducted on the target wheel at the target moment, so that the vehicle is out of order. According to the invention, the problem in the prior art that a long time is delayed when the wheels of the vehicle sink into the pits until the wheels are separated is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle braking control, and in particular to a method, system, medium and electronic equipment for quickly escaping a vehicle. Background Art

[0002] A vehicle's wheels being suspended in the air may cause the vehicle to lose some or all of its traction and stability, causing the suspended wheels to slip, which in turn may cause the vehicle to lose control, become unable to be driven stably, and may even cause catastrophic accidents such as rollovers.

[0003] The vehicle's differential allows the left and right wheels of the vehicle to rotate at different speeds to adapt to the difference in path length between the inner and outer wheels when turning. In special circumstances, such as when one wheel is suspended in the air, the differential allows the wheels to rotate at different speeds, distributing torque to the wheels according to the difference in wheel speeds. The differential will transfer more torque to the suspended wheel, causing it to slip, so it is necessary to reduce the engine's torque output or increase the braking force of the suspended wheel to suppress slip.

[0004] The existing technology can judge the state of the vehicle wheels in real time according to the value of the relevant signal, and then detect whether the vehicle wheels fall into the potholes, causing the vehicle wheels to slip; after determining that the wheels fall into the potholes, the wheel end braking force can be controlled to increase the braking force of the suspended wheels to suppress the slipping, thereby achieving the above-mentioned vehicle escape;

[0005] However, in the process of implementing the above solution, due to the relative delay in data transmission and related information processing, the time it takes for the vehicle wheels to get out of the pothole is relatively long, resulting in a poor user experience. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a method, system, medium and electronic device for quickly escaping a vehicle, which solves the problem in the prior art that it takes a long time for the wheels of a vehicle to get out of a pothole.

[0007] At least one embodiment of the present invention provides a method for quickly escaping a vehicle, comprising:

[0008] Acquire the vehicle's road conditions and motion state parameters in real time, wherein the road conditions include road material and the distribution of potholes on the road;

[0009] Predicting the driving trajectory of the vehicle within a preset time period according to the motion state parameters;

[0010] Based on the Bayesian network model, according to the driving trajectory and the driving road condition, determining the probability that the target wheel of the vehicle falls into the pothole at the target time;

[0011] When the probability is greater than a threshold, determining a target braking force required for the target wheel to escape from the pothole;

[0012] According to the target braking force, the target wheel is braked and controlled at the target moment to achieve the escape of the vehicle.

[0013] The technical solution disclosed in the present invention has at least the following beneficial effects:

[0014] By predicting the vehicle's driving trajectory and combining it with the Bayesian network model, the probability of the vehicle's target wheel falling into a pothole can be determined. Then, when the probability is greater than a threshold, the target braking force can be determined in advance, and at the target moment when the target wheel falls into the pothole, the target wheel can be controlled in advance by the above-mentioned target braking force, avoiding the conventional long delay of braking control after the wheel falls into the pothole, shortening the vehicle's escape process and greatly improving the user's driving experience.

[0015] In a method for quickly escaping a vehicle provided by one embodiment of the present invention, predicting the driving trajectory of the vehicle within a preset time period according to the motion state parameter includes:

[0016] According to the motion state parameters at the current moment, using multiple support vector regression models, single-step recursive prediction of the vehicle position coordinates at each moment within the preset time period;

[0017] For each moment in the preset time period, taking the average value of the position coordinates of each vehicle as the target position coordinate;

[0018] The driving trajectory of the vehicle within the preset time period is determined according to the target position coordinates at each moment within the preset time period.

[0019] The technical solution disclosed in the present invention has at least the following beneficial effects:

[0020] The prediction accuracy of the final driving trajectory is improved by using the predictions of multiple support vector regression models.

[0021] In a method for quickly escaping a vehicle provided in one embodiment of the present invention, the method further includes:

[0022] Acquiring suspension height information of the vehicle and / or wheel speed information of the target wheel at the target time;

[0023] Determining a final result of whether the target wheel falls into the pothole based on the suspension height information and / or the wheel speed information;

[0024] Use the final result as feedback to optimize each of the support vector regression models.

[0025] The technical solution provided by the present invention at least has the following beneficial effects:

[0026] By optimizing the support vector regression model through feedback, the accuracy of the model in subsequent prediction processes is improved.

[0027] In a method for quickly getting a vehicle out of trouble provided by one embodiment of the present invention, determining the target braking force required for the target wheel to get out of the pothole includes:

[0028] Use the preset fixed traction braking force as the target braking force.

[0029] The technical solution provided by the present invention at least has the following beneficial effects:

[0030] By using the fixed traction force as the target braking force, for most cases where a vehicle gets stuck in a pothole, this solution does not require other calculations, saving the corresponding computing resources.

[0031] In a method for quickly getting a vehicle out of trouble provided by one embodiment of the present invention, determining the target braking force required for the target wheel to get out of the pothole includes:

[0032] Real-time obtain the wheel speed information and vehicle speed information of the vehicle;

[0033] Based on the difference between the wheel speed information and the vehicle speed information, determine the slip coefficient of the vehicle on the current road surface composition material;

[0034] Combine the slip coefficient and the preset fixed traction braking force to determine the target braking force.

[0035] The technical solution provided by the present invention at least has the following beneficial effects:

[0036] By combining the slip coefficient of the vehicle and the fixed traction braking force to calculate the target braking force of the vehicle, the target braking force output by the vehicle is made more reasonable, improving the driving experience of the user.

[0037] In a method for quickly getting a vehicle out of trouble provided by one embodiment of the present invention, based on the Bayesian network model, determining the probability that the target wheel of the vehicle falls into the pothole at the target moment according to the driving trajectory and the driving road surface conditions includes:

[0038] Establish a historical database of whether each wheel of the vehicle falls into a pothole under various historical driving road surface conditions and historical driving trajectories;

[0039] Determine, according to the historical database, the probability of the target wheel falling into the pothole under the current driving trajectory and the driving road condition by using the Bayesian network model;

[0040] Based on the current driving trajectory and the distribution of potholes on the road surface, a target time when the target wheel falls into the pothole is determined.

[0041] In a method for quickly escaping a vehicle provided in one embodiment of the present invention, the method further includes:

[0042] Acquiring suspension height information of the vehicle and / or wheel speed information of the target wheel at the target time;

[0043] Determining a final result of whether the target wheel falls into the pothole based on the suspension height information and / or the wheel speed information;

[0044] The driving trajectory, the driving road condition and the final result are added to the historical database.

[0045] The technical solution disclosed in the present invention has at least the following beneficial effects:

[0046] By putting each predicted driving trajectory, driving road condition and the corresponding final result each time into the historical database, the accuracy of the probability estimation of the historical database can be improved.

[0047] At least one embodiment of the present invention further provides a system for quickly escaping a vehicle, comprising:

[0048] A data acquisition module, for acquiring in real time the road conditions and motion state parameters of the vehicle, wherein the road conditions include the road material and the distribution of potholes on the road;

[0049] A driving trajectory prediction module, which predicts the driving trajectory of the vehicle within a preset time period according to the motion state parameters;

[0050] A probability prediction module, based on a Bayesian network model, determines the probability that a target wheel of the vehicle will fall into the pothole at a target time according to the driving trajectory and the driving road condition;

[0051] a braking input module, which determines a target braking force required for the target wheel to escape from the pothole when the probability is greater than a threshold;

[0052] The braking control module performs braking control on the target wheel at the target moment according to the target braking force, so as to achieve the escape of the vehicle.

[0053] The present invention also provides a computer-readable storage medium storing instructions that, when run on a terminal device, cause the terminal device to execute a method for quickly extricating a vehicle as described above.

[0054] The present invention also provides an electronic device, including a memory, a processor, and a program stored on the memory and running on the processor, wherein the processor implements a method for quickly extricating a vehicle as described above when executing the program. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a schematic flow chart of a method for quickly extricating a vehicle according to the present invention;

[0056] Figure 2 is a schematic diagram of the processing logic for checking the validity of input data according to the present invention;

[0057] Figure 3 is a schematic structural diagram of a vehicle quick extrication system according to the present invention;

[0058] Figure 4 is a schematic structural diagram of another embodiment of a vehicle quick extrication system according to the present invention;

[0059] Figure 5 is a schematic structural diagram of the electronic device provided by the present invention.

[0060] In the drawings, the list of components represented by each reference numeral is as follows:

[0061] 10. Electronic device, 11. Processor, 12. Read-only memory (ROM), 13. Random access memory (RAM), 14. Bus, 15. Input / output (I / O) interface, 16. Input unit, 17. Output unit, 18. Storage unit, 19. Communication unit. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] The principles and features of the present invention are described below. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0063] The present invention provides a method for quickly extricating a vehicle. Please refer to Figure 1 as shown, including:

[0064] Obtain the driving road surface conditions and motion state parameters of the vehicle in real time, where the driving road surface conditions include the road surface composition material and the distribution of potholes on the road surface;

[0065] Predict the driving trajectory of the vehicle within a preset time period according to the motion state parameters;

[0066] Based on the Bayesian network model, the probability of the target wheel of the vehicle falling into the pothole at the target time is determined according to the driving trajectory and the driving road conditions;

[0067] When the probability is greater than a threshold, determining a target braking force required for the target wheel to escape from the pothole;

[0068] According to the target braking force, the target wheel is braked and controlled at the target time to achieve the vehicle's escape.

[0069] By predicting the vehicle's driving trajectory and combining it with the Bayesian network model, the probability of the vehicle's target wheel falling into a pothole can be determined. Then, when the probability is greater than a threshold, the target braking force can be determined in advance, and at the target moment when the target wheel falls into the pothole, the target wheel can be controlled in advance by the above-mentioned target braking force, avoiding the conventional long delay of braking control after the wheel falls into the pothole, shortening the vehicle's escape process and greatly improving the user's driving experience.

[0070] In an exemplary embodiment provided by the present invention, please refer to Figure 2 As shown, the steps of obtaining the vehicle's motion state parameters in real time specifically include:

[0071] Obtain relevant motion state parameters from the internal signals of the IBCU (electronically controlled brake system) and the signals provided by other ECU (electronic control unit) nodes, including vehicle speed, wheel speed, steering wheel angle, lateral acceleration and longitudinal acceleration;

[0072] Among them, TCS status signal, reference vehicle speed, etc. are obtained from the internal signal of IBCU; the signals obtained from other ECU nodes include wheel speed, steering wheel angle, lateral acceleration and lateral acceleration, etc. The suspension height information obtained later is also obtained from other ECU nodes.

[0073] After obtaining the above motion state parameters, it is necessary to check the validity of the motion state parameters, including: 1) For signals with linear changes such as corresponding wheel speed, steering wheel angle, lateral acceleration, and suspension height, if the IBCU receives the corresponding signal valid flag bit in the relevant node message, it can be determined whether the valid flag is valid according to whether it is valid. If there is no corresponding requirement, it can be ignored; 2) To prevent the linear signal from mutating due to certain faults (such as sensor faults), resulting in the signals such as wheel speed, steering wheel angle, acceleration, and suspension height being untrustworthy. It is necessary to periodically check the change range of these signals. If the change range of any of the above motion state parameters exceeds the specified threshold within two adjacent periods (for example, the wheel speed change from T0 to T1 is ΔWhlSpd1, and the wheel speed change from T1 to T2 is ΔWhlSpd2, and ΔWhlSpd1 > threshold && ΔWhlSpd2), then the motion state parameter is considered untrustworthy. For the above two validity check results, when all signals are satisfied, it indicates that the signals required by the system are trustworthy, and only then does it meet the precondition for enabling the system function; if not, the function cannot be enabled.

[0074] Under the condition that both of the above two validity check results are satisfied, obtain the driving road conditions of the vehicle. The specific steps include:

[0075] The image collected by the front camera of the vehicle is obtained through the image recognition model algorithm. That is, through the image provided by the front camera, the composition material of the road surface where the vehicle is driving forward and the distribution of potholes can be recognized. Among them, the distribution of potholes includes the position where the potholes appear and the size of the potholes. Currently, the commonly used image recognition methods mainly include traditional algorithms and deep learning algorithms. This solution is not limited to using traditional or deep learning methods. Among them, the convolutional neural network CNN is a method widely used in many fields. Its classic architectures include: LeNet-5 (the pioneer of handwritten digit recognition), AlexNet (the breakthrough of ImageNet in 2012), VGG (standardization of deep network structures), ResNet (residual connections to solve the vanishing gradient), and feature learning mechanism: automatically extract hierarchical features through multiple convolutional kernels. The method for obtaining image feature information is not limited to the traditional feature engineering process and the deep learning feature learning methods. For deep learning feature learning, there are the following methods:

[0076] End-to-end feature learning, transfer learning applications, and feature visualization techniques. Deep learning methods are more suitable for scenarios involving large amounts of data. A typical deep learning toolchain is PyTorch / TensorFlow + MMDetect ion / MONAI. The main processes for identifying the road surface composition materials of vehicle driving based on CNN are as follows: 1) Data preparation and preprocessing (obtaining image datasets, data augmentation to improve model generalization ability, data standardization, dividing the dataset into training set, validation set, and test set), 2) Model construction (design of core components (convolutional layer, pooling layer, activation function, fully connected layer, batch normalization), selection of classic architectures, transfer learning, etc.), 3) Model training (loss function, optimizer, hyperparameter setting, training process, regularization techniques), 4) Model evaluation and tuning (evaluation metrics, visual analysis, tuning strategies).

[0077] Common road surface composition materials for road conditions include: 1) ice, snow, dry and wet asphalt, wet basalt, wet tile road surface;

[0078] Based on the above different road surface composition materials, the following multiple driving situations can be obtained: 1) Entering a low-adhesion road surface from a high-adhesion road surface; 2) Entering a high-adhesion road surface from a low-adhesion road surface; 3) Opposite traffic road surface (the adhesion coefficients of the left and right wheels in contact with the road surface are inconsistent).

[0079] Furthermore, after obtaining the road surface conditions and motion state parameters of the vehicle, it is necessary to perform data preprocessing on the above motion state parameters;

[0080] Among them, the data preprocessing steps include:

[0081] Synchronize sensor signals: Align the timestamps of vehicle speed, wheel speed, steering wheel angle, lateral acceleration, and longitudinal acceleration (interpolation or resampling).

[0082] Outlier handling: Remove sensor noise (such as using moving window mean filtering or median filtering).

[0083] Standardization / normalization: Scale the data to a unified range (such as Z-score standardization or Min-Max normalization).

[0084] In an exemplary embodiment provided by the present invention, after performing data preprocessing, it is necessary to predict the driving trajectory of the vehicle within a preset time period based on the motion state parameters, including:

[0085] According to the motion state parameters at the current moment, use multiple support vector regression models (SVR) to recursively predict the vehicle position coordinates at each moment within the preset time period step by step. SVR maps the input space to a high-dimensional space through a kernel function and searches for the optimal hyperplane to ensure that the deviation between the predicted value and the true value does not exceed ∈;

[0086] Among them, the construction of the support vector regression model includes:

[0087] 1) Determine the objective function as:

[0088]

[0089] Its constraint conditions are:

[0090]

[0091] Among them:

[0092] ω is the weight vector, b is the bias term, φ(x) is the kernel function mapping, C is the regularization parameter, and ∈ is the insensitive loss threshold.

[0093] The above kernel function can be selected as a linear kernel function: Or an RBF kernel function: K(x i , x j ) = exp(-γ||x i - x j || 2 ).

[0094] 2) Perform model training and tuning. Use the historical driving trajectory and motion state parameter data to train the above vector regression model, including:

[0095] Divide the training set (70%), validation set (15%), and test set (15%) in chronological order to avoid future data leakage.

[0096] Use grid search or Bayesian optimization: adjust parameters such as C (regularization strength), ∈ (tolerance deviation), γ (RBF kernel width), etc., and perform cross-validation using time series.

[0097] 3) Perform module evaluation. Among them,

[0098] The evaluation metrics can be:

[0099] Mean squared error (MSE):

[0100] Mean absolute error (MAE):

[0101] Final trajectory error (FDE): The Euclidean distance between the predicted end point and the true end point.

[0102] Dynamic consistency: Check whether the predicted trajectory conforms to vehicle kinematic constraints (such as curvature continuity).

[0103] Exemplary:

[0104] Assume that the vehicle state at the current moment t is: vehicle speed v t , steering wheel angle δ t , lateral acceleration a y ,t, longitudinal acceleration a x ,t, then the SVR model for predicting the position (x t+1 , y t+1 ) at the next moment can be expressed as:

[0105]

[0106] where fSVR x and fSVR y are the displacement increments predicted by SVR, and θ t is the current heading angle, which can be obtained by integrating the angular velocity or the steering wheel angle.

[0107] For each moment within the preset time period, take the average value of each vehicle position coordinate as the target position coordinate;

[0108] Determine the driving trajectory of the vehicle within the preset time period according to the target position coordinates at each moment within the preset time period.

[0109] In an exemplary embodiment provided by the present invention, after predicting the above driving trajectory, based on the Bayesian network model, determine the probability that the target wheel of the vehicle falls into a pothole at the target moment according to the driving trajectory and the driving road condition, specifically including:

[0110] Establish a historical database of whether each wheel of the vehicle falls into a pothole under various historical driving road conditions and historical driving trajectories;

[0111] According to the historical database, use the Bayesian network model to determine the probability that the target wheel falls into a pothole under the current driving trajectory and driving road condition;

[0112] The prediction steps of the above Bayesian network model are as follows:

[0113] First, determine the target variables, that is, the historical database of historical driving road conditions and historical driving trajectories;

[0114] Subsequently, select the observed variables: that is, the current driving trajectory and driving road condition;

[0115] After that, perform learning through the Bayesian network model structure:

[0116] Data-driven learning: Use algorithms (such as K2, PC algorithm) to infer dependency relationships from the data.

[0117] Scoring function (such as Bayesian Information Criterion BIC):

[0118]

[0119] Where D is the current data, d is the number of model parameters, and N is the historical database.

[0120] When the data sample of the current situation is missing in the historical database, the Expectation-Maximization algorithm (EM) is used to iteratively estimate the parameters. Otherwise, the conditional probability P(X i |Pa(X i )) (such as maximum likelihood estimation) is directly calculated.

[0121] Subsequently, the evidence is input: the known variable values (such as X3 = 1, X5 = 0), and the target posterior probability is calculated: P(Y|Evidence) is calculated through joint probability decomposition and marginalization.

[0122] Finally, through the Maximum A Posteriori (MAP) estimation: the state with the maximum posterior probability is selected as the prediction result.

[0123] Y pred = argmax P(Y = y|Evidence).

[0124] After obtaining the probability that the target wheel falls into a pothole, based on the current driving trajectory and the distribution of potholes on the road surface, the target moment when the target wheel falls into a pothole is determined.

[0125] Optionally, when it is determined that the above probability is greater than a threshold (such as 80%), the target braking force required for the target wheel to disengage from the pothole needs to be determined;

[0126] On the one hand, the preset fixed traction braking force can be used as the target braking force. At this time, by using the fixed traction force as the target braking force, for most cases after the vehicle gets stuck in a pothole, this solution does not require other calculations, saving the corresponding computing resources.

[0127] On the other hand, the wheel speed information and vehicle speed information of the vehicle can also be obtained in real time;

[0128] Based on the difference between the wheel speed information and the vehicle speed information, the slip coefficient of the vehicle on the current road surface material is determined;

[0129] Combining the slip coefficient and the preset fixed traction braking force, the target braking force is determined.

[0130] By combining the slip coefficient of the vehicle and the fixed traction braking force to calculate the target braking force of the vehicle, the target braking force output by the vehicle is made more reasonable, improving the user's driving experience.

[0131] Optionally, after the target wheel is braked and controlled at the target moment, this method further includes:

[0132] Acquiring suspension height information of the vehicle and / or wheel speed information of a target wheel at a target time;

[0133] Determine a final result of whether the target wheel falls into a pothole based on the suspension height information and / or the wheel speed information;

[0134] The final results are used as feedback to optimize each support vector regression model.

[0135] The driving trajectory, road conditions and final results are added to the historical database.

[0136] By optimizing the support vector regression model through feedback and putting each predicted driving trajectory, driving road condition and the corresponding final result into the historical database, the accuracy of the method in the subsequent prediction process can be improved.

[0137] In summary, after knowing the detailed wheel status (the specific target wheel will fall into a pothole and slip or spin at a specific target time), this method can calculate the appropriate braking torque for the wheel in advance. When the vehicle reaches the target time, the system will immediately output the target braking force of the wheel. In comparison, the traditional control logic will have a certain control delay, so that the caliper works according to the target braking force. Ultimately, the vehicle obtains sufficient traction to quickly pass through the bumpy road surface, thereby improving the off-road performance of the entire vehicle. At the same time, it can also avoid the failure of the vehicle to escape from the pothole due to sensor failure.

[0138] The present invention also provides a system for quickly escaping a vehicle, please refer to Figure 3 As shown, including:

[0139] A data acquisition module, which acquires the vehicle's driving road conditions and motion state parameters in real time, wherein the driving road conditions include the road surface material and the distribution of potholes on the road surface;

[0140] A driving trajectory prediction module predicts the driving trajectory of the vehicle within a preset time period based on the motion state parameters;

[0141] The probability prediction module, based on the Bayesian network model, determines the probability of the target wheel of the vehicle falling into the pothole at the target time according to the driving trajectory and the driving road conditions;

[0142] a braking input module, determining a target braking force required for the target wheel to escape from the pothole when the probability is greater than a threshold;

[0143] The brake control module controls the braking of the target wheels at the target time according to the target braking force to achieve the vehicle's escape.

[0144] Furthermore, the driving trajectory prediction module specifically includes:

[0145] Based on the motion state parameters at the current moment, using multiple support vector regression models, recursively predict the vehicle position coordinates at each moment within a preset time period in a single step;

[0146] For each moment within the preset time period, take the average value of the vehicle position coordinates as the target position coordinate;

[0147] Based on the target position coordinates at each moment within the preset time period, determine the driving trajectory of the vehicle within the preset time period.

[0148] Furthermore, the braking input module specifically includes:

[0149] Take the preset fixed traction braking force as the target braking force.

[0150] Alternatively, the braking input module may also specifically include:

[0151] Obtain the wheel speed information and vehicle speed information of the vehicle in real time;

[0152] Based on the difference between the wheel speed information and the vehicle speed information, determine the slip coefficient of the vehicle on the current road surface composition material;

[0153] Combine the slip coefficient and the preset fixed traction braking force to determine the target braking force.

[0154] Furthermore, the probability prediction module specifically includes:

[0155] Establish a historical database of whether each wheel of the vehicle falls into a pothole under various historical driving road conditions and historical driving trajectories;

[0156] Based on the historical database, use the Bayesian network model to determine the probability that the target wheel falls into a pothole under the current driving trajectory and driving road conditions;

[0157] Based on the current driving trajectory and the distribution of potholes on the road surface, determine the target moment when the target wheel falls into a pothole.

[0158] Furthermore, the system also includes:

[0159] An optimization module that obtains the suspension height information of the vehicle at the target moment and / or the wheel speed information of the target wheel;

[0160] Based on the suspension height information and / or the wheel speed information, determine the final result of whether the target wheel falls into a pothole;

[0161] Use the final result as feedback to optimize each support vector regression model.

[0162] Optionally, the above optimization module further includes:

[0163] The driving trajectory, driving road conditions and final results are added to the historical database.

[0164] Please refer to here Figure 4 As shown, the system obtains the probability of falling into a pothole according to the data acquisition module, the driving trajectory prediction module and the probability prediction module in turn. Then, in the braking input module, it determines whether the probability of wheel slipping or spinning is greater than the threshold. If so, it is determined that the wheel will slip or spin at the target time. If not, it is determined that the wheel will not slip or spin at the target time. At the same time, the final result of the actual state of the vehicle's wheels at the target time is fed back to the driving trajectory prediction module and the probability prediction module to optimize the support vector regression model and the Bayesian model therein.

[0165] The present invention also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes a method for quickly escaping a vehicle as described above.

[0166] The present invention also provides an electronic device, comprising a memory, a processor, and a program stored in the memory and running on the processor, wherein the method for quickly escaping a vehicle as described above is implemented when the processor executes the program.

[0167] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. An electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. An electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0168] like Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0169] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0170] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for a vehicle to quickly get out of trouble.

[0171] In some embodiments, a method for a vehicle to quickly get out of trouble can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for a vehicle to quickly get out of trouble described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute a method for a vehicle to quickly get out of trouble in any other appropriate way (for example, by means of firmware).

[0172] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0173] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0174] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0175] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or an LCD (liquid crystal display)); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0176] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0177] The computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0178] In addition, 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 quantity of the indicated technical features. Thus, features defined with "first" and "second" can explicitly or implicitly include at least one of the features. In the description of the present invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0179] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0180] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for a vehicle to quickly get out of trouble, characterized in that, include: Acquire the vehicle's road conditions and motion state parameters in real time, wherein the road conditions include road material and the distribution of potholes on the road; Predicting the driving trajectory of the vehicle within a preset time period according to the motion state parameters; Based on the Bayesian network model, according to the driving trajectory and the driving road condition, determining the probability that the target wheel of the vehicle falls into the pothole at the target time; When the probability is greater than a threshold, determining a target braking force required for the target wheel to escape from the pothole; According to the target braking force, the target wheel is braked and controlled at the target moment to achieve the escape of the vehicle.

2. The method for a vehicle to quickly get out of trouble according to claim 1, wherein, The predicting the driving trajectory of the vehicle within a preset time period according to the motion state parameter includes: According to the motion state parameters at the current moment, using multiple support vector regression models, single-step recursive prediction of the vehicle position coordinates at each moment within the preset time period; For each moment in the preset time period, taking the average value of the position coordinates of each vehicle as the target position coordinate; The driving trajectory of the vehicle within the preset time period is determined according to the target position coordinates at each moment within the preset time period.

3. A method for a vehicle to quickly get out of trouble according to claim 2, characterized in that, Also includes: Acquiring suspension height information of the vehicle and / or wheel speed information of the target wheel at the target time; Determining a final result of whether the target wheel falls into the pothole based on the suspension height information and / or the wheel speed information; The final result is used as feedback to optimize each support vector regression model.

4. A method for a vehicle to quickly get out of trouble according to claim 1, characterized in that, The determining of the target braking force required for the target wheel to escape from the pothole comprises: The preset fixed traction braking force is used as the target braking force.

5. A method for a vehicle to quickly get out of trouble according to claim 1, characterized in that The determining of the target braking force required for the target wheel to escape from the pothole comprises: Acquiring wheel speed information and vehicle speed information of the vehicle in real time; Determining a slip coefficient of the vehicle on the current road surface composition material based on a difference between the wheel speed information and the vehicle speed information; The target braking force is determined by combining the slip coefficient and a preset fixed traction braking force.

6. A method for a vehicle to quickly get out of trouble according to any one of claims 1 to 5, characterized in that, The method of determining the probability of a target wheel of the vehicle falling into the pothole at a target time based on the driving trajectory and the driving road condition based on the Bayesian network model includes: Establish a historical database of whether each wheel of the vehicle falls into potholes under various historical driving road conditions and historical driving trajectories; Determine, according to the historical database, the probability of the target wheel falling into the pothole under the current driving trajectory and the driving road condition by using the Bayesian network model; Based on the current driving trajectory and the distribution of potholes on the road surface, a target time when the target wheel falls into the pothole is determined.

7. A method for a vehicle to quickly get out of trouble according to claim 6, characterized in that, Also includes: Acquiring suspension height information of the vehicle and / or wheel speed information of the target wheel at the target time; Determining a final result of whether the target wheel falls into the pothole based on the suspension height information and / or the wheel speed information; The driving trajectory, the driving road condition and the final result are added to the historical database.

8. A system for a vehicle to quickly get out of trouble, characterized in that, include: A data acquisition module, for acquiring in real time the road conditions and motion state parameters of the vehicle, wherein the road conditions include the road material and the distribution of potholes on the road; A driving trajectory prediction module, which predicts the driving trajectory of the vehicle within a preset time period according to the motion state parameters; A probability prediction module, based on a Bayesian network model, determines the probability that a target wheel of the vehicle will fall into the pothole at a target time according to the driving trajectory and the driving road condition; a braking input module, which determines a target braking force required for the target wheel to escape from the pothole when the probability is greater than a threshold; The braking control module performs braking control on the target wheel at the target moment according to the target braking force, so as to achieve the escape of the vehicle.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes a method for quickly escaping a vehicle as described in any one of claims 1 to 7.

10. An electronic device, comprising a memory, a processor, and a program stored on the memory and running on the processor, characterized in that, When the processor executes the program, a method for quickly escaping a vehicle as described in any one of claims 1 to 7 is implemented.

Images