Vehicle driving stability control method, device, equipment and storage medium
By obtaining and analyzing the vehicle's forward road condition prediction information and current driving road condition information, and adjusting the suspension system in real time, the problem of adjustment lag in the vehicle's stable driving control in the prior art is solved, and riding comfort is improved.
Patent Information
- Application Number
- CN202111589268.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-03-13
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The prior art often experiences adjustment lag in the smooth driving control of vehicles, resulting in unsatisfactory passenger comfort.
By obtaining the road condition prediction information ahead of the vehicle and the current road condition information during driving, using neural network models for data analysis and strategy determination, and adjusting the damping coefficient and suspension height of the suspension system in real time to adapt to the road condition ahead.
Timely adjustment of the vehicle is achieved, riding comfort is improved, the problem of lag in the adjustment in the existing technology is overcome, and the vehicle is driven smoothly under different road conditions.
Smart Images

Figure CN114148137B_ABST
Abstract
Description
[0001] This invention is a divisional application of the invention patent application with application number 202010175377.6 filed on March 13, 2020, and invention name “Vehicle Driving Stability Control Method, Device, Equipment and Storage Medium”. Technical Field
[0002] The present application relates to the field of data processing technology, and specifically to autonomous driving technology. Background Art
[0003] During vehicle driving, smooth driving of the vehicle is a very important factor for the comfort of the passengers in the vehicle.
[0004] At present, in terms of vehicle smooth driving control, the overall height of the vehicle is adjusted by monitoring the vehicle speed. For example, if the current driving speed is too high, the overall height of the vehicle will be lowered to reduce wind resistance. Alternatively, the vehicle's driving bumpiness is monitored and analyzed by the on-board inertial measurement unit to adjust the damping coefficient of the vehicle suspension system. For example, if the current road section is bumpy, the damping coefficient of the vehicle suspension system is lowered.
[0005] However, when the above-mentioned prior art is used to control the vehicle's stable driving, adjustment lag often occurs, resulting in the adjusted comfort often failing to meet the passengers' requirements for stability. Summary of the invention
[0006] In a first aspect, an embodiment of the present application provides a method for controlling vehicle driving stability, comprising: obtaining forward road condition prediction information and current driving road condition information of the vehicle during driving; determining strategy information for adjusting the suspension system of the vehicle based on the forward road condition prediction information and the current driving road condition information; and adjusting the suspension system of the vehicle based on the strategy information.
[0007] The embodiment of the present application obtains the road condition prediction information and current road condition information of the vehicle during driving, and determines the strategy information for adjusting the suspension system of the vehicle according to the road condition prediction information and current road condition information, and adjusts the suspension system of the vehicle according to the strategy information, so as to achieve the purpose of making the vehicle drive smoothly. Not only the current road condition information indicating the vehicle during driving is obtained, but also the prediction information of the road condition ahead during driving is obtained. According to the road condition prediction information, the road condition ahead can be sensed in advance, and combined with the current road condition information, the strategy information for adjusting the suspension system of the vehicle is made in time, so that the suspension system of the vehicle is adjusted to the state of adapting to the road condition ahead in time, so that the vehicle drives smoothly and improves the ride comfort.
[0008] Optionally, obtaining the road condition prediction information ahead of the vehicle during driving includes: obtaining an environmental image of the vehicle's surroundings captured by an image acquisition device on the vehicle; inputting the environmental image into a pre-trained road condition prediction model to obtain the road condition prediction information ahead of the vehicle during driving.
[0009] Optionally, the road condition prediction model is obtained by training a neural network using the following process: obtaining environmental sample images of the surrounding environment of the vehicle during driving and road condition prediction annotation information corresponding to the environmental sample images; using the environmental sample images as input to the neural network, and using the road condition prediction annotation information as output of the neural network, and iteratively training the neural network to obtain the road condition prediction model.
[0010] The embodiment of the present application obtains a road condition prediction model by training a neural network, thereby inputting the environmental image of the vehicle's surrounding environment captured by the image acquisition device on the vehicle into the road condition prediction model to predict the road condition ahead. Since the road condition prediction model is obtained by training the neural network, the road condition prediction model can obtain richer image semantic information, thereby more accurately predicting the road condition ahead.
[0011] Optionally, obtaining the current driving road condition information of the vehicle includes: obtaining posture information of the vehicle collected by an inertial measurement unit on the vehicle; and determining the current driving road condition information of the vehicle based on the posture information of the vehicle.
[0012] Optionally, determining the current driving road condition information of the vehicle based on the posture information of the vehicle includes: determining a change in the posture information based on the posture information of the vehicle within a preset time period; when the change in the posture information is greater than a preset change, determining that the current driving road condition information is an unstable section; when the change in the posture information is less than or equal to a preset change, determining that the current driving road condition information is a stable section.
[0013] The embodiment of the present application determines the current road condition of the vehicle based on the change in the vehicle's posture information over a period of time. The posture information is used to characterize the vehicle's inclination information. If the vehicle is currently on an unstable road section, the change in the inclination information will also be unstable. Based on this principle, the vehicle's current road condition information can be easily determined. In addition, the posture information can be obtained based on the existing inertial measurement unit on the vehicle, without the need to add additional sensors.
[0014] Optionally, determining the current driving road condition information of the vehicle based on the posture information of the vehicle includes: inputting the posture information of the vehicle into a pre-trained road condition detection model to obtain the current driving road condition information of the vehicle.
[0015] Optionally, the road condition detection model is obtained by training a neural network using the following process: obtaining posture sample data of the vehicle during driving and current driving road condition labeling information corresponding to the posture sample data; using the posture sample data as input of the neural network, and using the current driving road condition labeling information as output of the neural network, and iteratively training the neural network to obtain the road condition detection model.
[0016] The embodiment of the present application obtains a road condition detection model by training a neural network, thereby inputting the posture information of the vehicle collected by the inertial measurement unit on the vehicle into the road condition detection model to predict the road condition ahead. Since the road condition detection model is obtained by training the neural network, compared with directly determining the current driving road condition based on the change in posture information, the road condition detection model can detect the current driving road condition more accurately.
[0017] Optionally, determining strategy information for adjusting the suspension system of the vehicle based on the forward road condition prediction information and the current driving road condition information includes: inputting the forward road condition prediction information and the current driving road condition information of the vehicle during driving into a pre-trained strategy determination model to obtain strategy information for adjusting the suspension system of the vehicle.
[0018] Optionally, the strategy determination model is obtained by training a neural network using the following process: obtaining training sample data and adjustment strategy annotation information corresponding to the training sample data, wherein the training sample data includes front road condition sample data and current driving road condition sample data; using the training sample data as input to the neural network, using the adjustment strategy annotation information as output of the neural network, and iteratively training the neural network to obtain the strategy determination model.
[0019] Optionally, the strategy information for adjusting the suspension system of the vehicle is determined based on the road condition prediction information ahead and the current driving road condition information, including: if the road condition prediction information ahead indicates that the road surface is slippery and the current driving road condition information indicates a smooth road section, then determining to lower the suspension height of the suspension system of the vehicle.
[0020] Optionally, the strategy information for adjusting the suspension system of the vehicle is determined based on the road condition prediction information ahead and the current driving road condition information, including: if the road condition prediction information ahead indicates that the road section is bumpy and the current driving road condition information indicates that the bumpiness of the current road section is getting bigger, then determining to lower the damping coefficient of the suspension system and increase the suspension height of the suspension system of the vehicle.
[0021] The embodiment of the present application obtains a strategy determination model by training a neural network, thereby inputting the acquired forward road condition prediction information and current driving road condition information into the strategy determination model to determine the strategy information for adjusting the vehicle's suspension system. Since the strategy determination model is obtained by training the neural network, the determined strategy information has a better effect on adjusting the vehicle.
[0022] Optionally, the method further includes: acquiring wind resistance information of the vehicle; and determining strategy information for adjusting the suspension system of the vehicle based on the forward road condition prediction information, current driving road condition information and wind resistance information.
[0023] Optionally, obtaining the wind resistance information of the vehicle includes: obtaining speed information and shape structure information of the vehicle; inputting the speed information and shape structure information of the vehicle into a preset wind resistance model to obtain the wind resistance information of the vehicle.
[0024] Optionally, determining strategy information for adjusting the suspension system of the vehicle based on the road condition prediction information ahead, current driving road condition information and wind resistance information includes: inputting the road condition prediction information ahead, current driving road condition information and wind resistance information into a pre-trained strategy determination model to obtain strategy information for adjusting the suspension system of the vehicle.
[0025] Optionally, the strategy determination model is obtained by training a neural network using the following process: obtaining training sample data and adjustment strategy annotation information corresponding to the training sample data, the training sample data including front road condition sample data, current driving road condition sample data, speed sample data and vehicle shape structure information; using the training sample data as the input of the neural network, using the adjustment strategy annotation information as the output of the neural network, iteratively training the neural network, and obtaining the strategy determination model.
[0026] Optionally, the strategy information for adjusting the suspension system of the vehicle is determined based on the road condition prediction information ahead, the current driving road condition information and the wind resistance information, including: if the road condition prediction information ahead indicates that the road section is smooth, the current driving road condition information indicates that the road section is smooth and the wind resistance information indicates that the wind resistance continues to increase, then determining to increase the damping coefficient of the suspension system of the vehicle and lower the suspension height.
[0027] The embodiment of the present application can determine the current state of the vehicle from different angles by combining the wind resistance information with the posture information, and then combined with the road condition prediction information ahead, it can make adjustment strategy information for the vehicle that is more suitable for the current scenario to adjust the vehicle. The adjusted comfort level can better meet the passengers' requirements for stability.
[0028] In the second aspect, an embodiment of the present application provides a vehicle driving stability control device, including: an acquisition module, used to obtain the forward road condition prediction information and the current driving road condition information of the vehicle during driving; a strategy determination module, which determines the strategy information for adjusting the suspension system of the vehicle based on the forward road condition prediction information and the current driving road condition information; an adjustment module, which is used to adjust the suspension system of the vehicle based on the strategy information.
[0029] In a third aspect, an embodiment of the present application provides a vehicle driving stability control device, comprising:
[0030] at least one processor; and
[0031] a memory communicatively connected to the at least one processor; wherein,
[0032] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.
[0033] In a fourth aspect, an embodiment of the present application provides a vehicle, comprising the vehicle driving stability control device described in the third aspect.
[0034] Optionally, the vehicle further includes: an image acquisition unit, used to acquire environmental images of the vehicle's surroundings during the vehicle's driving; and an inertial measurement unit, used to acquire posture information of the vehicle during the vehicle's driving.
[0035] Optionally, the vehicle further includes: a speed sensor for collecting speed information of the vehicle during driving of the vehicle.
[0036] In a fifth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.
[0037] One embodiment of the above application has the following advantages or beneficial effects: by obtaining the forward road condition prediction information and the current road condition information of the vehicle during driving, and according to the forward road condition prediction information and the current road condition information, determining the strategy information for adjusting the suspension system of the vehicle, and adjusting the suspension system of the vehicle according to the strategy information, so as to achieve the purpose of making the vehicle drive smoothly. Not only the current road condition information indicating the vehicle during driving is obtained, but also the prediction information of the forward road condition during driving is obtained. According to the forward road condition prediction information, the forward road condition can be perceived in advance, and combined with the current road condition information, the strategy information for adjusting the suspension system of the vehicle is made in time, so that the suspension system of the vehicle is adjusted to the state of adapting to the forward road condition in time, so that the vehicle drives smoothly and improves the ride comfort. Because the method adopts the method of obtaining information that can indicate the current driving road condition of the vehicle during driving, and predicting information about the road condition ahead during driving of the vehicle, and determining strategy information for adjusting the suspension system of the vehicle based on the road condition prediction information ahead and the current driving road condition information, and adjusting the suspension system of the vehicle based on the strategy information, the technical problem that adjustment lag often occurs when the prior art controls the smooth driving of the vehicle, resulting in the adjusted comfort often failing to meet the passengers' requirements for stability is overcome, thereby achieving the technical effect of timely making strategy information for adjusting the suspension system of the vehicle, so that the suspension system of the vehicle is timely adjusted to a state that adapts to the road condition ahead, so that the vehicle can drive smoothly and the ride comfort is improved.
[0038] Other effects of the above optional manner will be described below in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application.
[0040] Figure 1 is a structural diagram of a vehicle suspension system provided in an embodiment of the present application;
[0041] Figure 2 is a flow chart of a vehicle stable driving control method provided by an embodiment of the present application;
[0042] Figure 3 is a control logic diagram of a vehicle provided in an embodiment of the present application;
[0043] Figure 4 is a schematic diagram of a vehicle stable driving control method provided by an example of the present application;
[0044] Figure 5 is a schematic diagram of a vehicle stable driving control method provided by an example of the present application;
[0045] Figure 6 is a flow chart of a vehicle stable driving control method provided by another embodiment of the present application;
[0046] Figure 7 is a schematic diagram of a vehicle stable driving control method provided by an example of the present application;
[0047] Figure 8 is a schematic diagram of the structure of a vehicle stable driving control device provided in an embodiment of the present application;
[0048] Fig. 9 It is a block diagram of a vehicle smooth driving control device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0049] Figure 1 : is a structural diagram of a vehicle suspension system provided in an embodiment of the present application. Figure 1 As shown, a suspension system 11 is provided on the vehicle 10, and the suspension system includes corresponding control parameters. By adjusting the control parameters of the suspension system, the riding comfort can be improved. The control parameters of the suspension system include damping coefficient and suspension height.
[0050] The damping coefficient can be adjusted by adjusting the elastic coefficient of the spring 12 in the suspension system 11. For example, when driving at high speed, the spring of the suspension system can be made harder, that is, the damping coefficient can be increased to improve the stability of the vehicle body. When driving at low speed for a long time, the control unit of the vehicle will think that the vehicle is passing through a bumpy road, and the suspension can be softened, that is, the damping coefficient can be lowered to reduce shock and improve comfort.
[0051] In addition, the suspension height of the suspension system can be understood as the distance between the vehicle chassis and the ground. By adjusting the suspension height of the suspension system, the vehicle chassis can be raised or lowered. In different scenarios, different suspension heights can bring different riding experiences. For example, when driving on a rugged mountain road, the suspension height can be raised to increase the distance between the vehicle chassis and the ground, making the passengers' ride less bumpy. When driving on a highway, the suspension height can be lowered to reduce the distance between the vehicle chassis and the ground, which can increase the tire's grip and reduce wind resistance, which is beneficial to the safety and stability of the vehicle's driving, and fuel consumption will also decrease as wind resistance decreases.
[0052] For the adjustment of the suspension height, different types of suspension systems have different adjustment methods. Taking the air suspension system as an example, the air suspension system generally uses an air spring, and the suspension height of the suspension system can be adjusted by inflating or deflating the air spring. For the adjustment of the suspension height of other types of suspension systems, please refer to the introduction of the prior art, which will not be introduced here one by one.
[0053] In the prior art, the vehicle is adjusted only by relying on the data collected by the speed or inertial measurement unit, and the data collected by the speed and inertial measurement unit can only represent the historical state or current state of the vehicle. When adjusting the vehicle according to the historical state and current state of the vehicle, if the road conditions of the current driving section of the vehicle are consistent with the road conditions of the road ahead, there is no problem with this adjustment method. However, once the road conditions of the road ahead are inconsistent with the road conditions of the current driving section, there will be a phenomenon of adjustment lag, resulting in low vehicle stability, poor passenger riding experience, and low comfort. In the process of controlling the stability of the vehicle during vehicle driving, the present application senses the road conditions ahead in advance, increases the prediction information of the road conditions ahead, and then determines the strategy information for adjusting the state of the vehicle's suspension system at a future moment in combination with the current driving conditions, so that the vehicle can adjust the suspension system of the vehicle according to the strategy information, thereby adjusting the vehicle in time, so that the setting parameters of the vehicle's suspension system can adapt to the road conditions ahead, so as to achieve the effect of making the vehicle drive smoothly.
[0054] The following will be described in detail with reference to the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.
[0055] Figure 2 It is a flow chart of a vehicle driving stability control method provided in an embodiment of the present application.
[0056] In view of the above technical problems in the prior art, the present application provides a vehicle driving stability control method, and the specific steps of the method are as follows:
[0057] Step 201: Obtain the forward road condition prediction information and current road condition information of the vehicle during driving.
[0058] like Figure 3 As shown, the vehicle of this embodiment includes a central control system 31, and also includes various types of sensors: image acquisition device 32, inertial measurement unit (IMU) 33 and speed sensor 34. The vehicle can be an unmanned vehicle or a vehicle equipped with an advanced driving assistance system (ADAS). Both unmanned vehicles and vehicles equipped with ADAS can be applicable to Figure 3 The structure shown.
[0059] Among them, the image acquisition device can be a vehicle-mounted camera, which is used to capture the surrounding environment of the vehicle during driving to obtain an environmental image. By analyzing and processing the environmental image, the predicted road condition information ahead of the vehicle can be obtained.
[0060] The inertial measurement unit is used to collect the attitude information of the vehicle during driving, wherein the attitude information of the vehicle can be understood as the attitude angle of the vehicle, including the roll angle (roll angle), pitch angle (pitch angle) and heading angle (yaw angle) of the vehicle. The attitude angle of the vehicle can characterize the inclination angle between the vehicle and the road surface. According to the current attitude angle and historical attitude angle of the vehicle, the current road condition of the vehicle can be determined. For example, if the vehicle continues to travel on a smooth road section, the change in the inclination angle between the vehicle and the road surface should be a constant value, and if the vehicle continues to travel on a bumpy road section, the change in the inclination angle between the vehicle and the road surface will change. Based on this principle, the current road condition information can be determined based on the attitude angle. Among them, the specific definitions of the roll angle (roll angle), pitch angle (pitch angle) and heading angle (yaw angle) can be found in the introduction of the prior art, which will not be repeated here.
[0061] The executor of this embodiment may be the central control system of the vehicle. In an optional implementation, the central control system of the vehicle may obtain environmental images and attitude angles from the image acquisition device and the IMU, respectively, and determine the forward road condition prediction information and the current road condition information during vehicle driving based on the environmental images and the attitude angles, respectively.
[0062] Step 202: Determine strategy information for adjusting the suspension system of the vehicle based on the forward road condition prediction information and the current driving road condition information.
[0063] In this embodiment, after acquiring the road condition prediction information ahead and the current driving road condition information, the central control system can determine the strategy information for adjusting the damping coefficient and / or suspension height of the vehicle's suspension system according to the road condition prediction information ahead and the current driving road condition information. The strategy information for adjusting the damping coefficient and / or suspension height of the vehicle's suspension system according to the road condition prediction information ahead and the current driving road condition information can include at least the following optional scenarios:
[0064] In the first optional scenario, if the road condition prediction information ahead indicates that the road surface is slippery and the current driving road condition information indicates that the road section is smooth, it is determined to lower the suspension height of the vehicle's suspension system. For example, if the prediction result obtained based on the environmental image collected by the on-board camera indicates that the road surface is slippery, and the detection result obtained based on the posture information collected by the IMU indicates that the current road section is a smooth road section, the central control system will determine the strategy information for lowering the suspension height of the vehicle's suspension system.
[0065] In the second optional scenario, if the road condition prediction information ahead indicates that the road section is bumpy and the current driving road condition information indicates that the bumpiness of the current road section is increasing, it is determined to lower the damping coefficient of the suspension system and increase the suspension height of the suspension system of the vehicle. Exemplarily, if the prediction result obtained based on the environmental image collected by the on-board camera indicates that the road section is bumpy, and the detection result obtained based on the posture information collected by the IMU indicates that the bumpiness of the current road section is increasing, the central control system will determine the strategy information of lowering the damping coefficient of the suspension system and increasing the suspension height of the suspension system of the vehicle.
[0066] In the third optional scenario, if the road condition prediction information indicates that there is a speed bump on the road ahead and the current road condition information indicates that the road is a smooth section, it is determined to lower the suspension height of the vehicle's suspension system. For example, if the prediction result obtained based on the environmental image collected by the on-board camera indicates that there is a speed bump on the road ahead, and the detection result obtained based on the posture information collected by the IMU indicates that the current road is a smooth section, the central control system will determine the strategy information for lowering the suspension height of the vehicle's suspension system.
[0067] Step 203: Adjust the suspension system of the vehicle according to the strategy information.
[0068] After the central control system determines the strategy information for adjusting the damping coefficient and / or suspension height of the vehicle's suspension system, it sends the strategy adjustment information to the adjustment system. After receiving the strategy information for adjusting the vehicle's suspension system, the vehicle's adjustment system, such as the control system of the suspension system, will adjust the damping coefficient and / or suspension height of the vehicle's suspension system according to the strategy information, so that the parameters of the suspension system adapt to the road conditions ahead, so that the vehicle can run smoothly and improve the riding comfort of passengers. The following uses the above three scenarios as examples to illustrate how the adjustment system adjusts the suspension system:
[0069] Corresponding to the first optional scenario mentioned above, the adjustment system will lower the suspension height of the vehicle's suspension system to lower the center of gravity of the vehicle and make the vehicle as a whole closer to the ground, so as to pass smoothly through slippery roads.
[0070] Corresponding to the second optional scenario mentioned above, the adjustment system will lower the damping coefficient of the suspension system and increase the suspension height of the vehicle's suspension system, so that the spring elastic coefficient of the suspension system is lower, the spring is softer, and the height of the vehicle chassis from the ground is greater, so that when the vehicle passes through bumpy sections, the passengers will not feel so bumpy.
[0071] Corresponding to the third optional scenario mentioned above, the adjustment system will lower the suspension height of the vehicle's suspension system, the vehicle's shaking will not be too excessive, the vehicle will be more stable, the passengers will not feel severe shaking, and the comfort will be higher.
[0072] Since the present embodiment makes a strategy for adjusting the suspension system of the vehicle based on the road condition prediction information ahead and the current road condition information, the road condition prediction information ahead is a prediction of the road condition ahead, therefore, in order to avoid early adjustment, the suspension system of the vehicle can also be adjusted after receiving the strategy information at a preset time interval. The preset time can be set according to the distance between the vehicle and the road section ahead, the time for data collection, acquisition and strategy determination, etc.
[0073] The embodiment of the present application obtains the road condition prediction information and current road condition information of the vehicle during driving, and determines the strategy information for adjusting the suspension system of the vehicle according to the road condition prediction information and current road condition information, and adjusts the suspension system of the vehicle according to the strategy information, so as to achieve the purpose of making the vehicle drive smoothly. Not only the current road condition information indicating the vehicle during driving is obtained, but also the prediction information of the road condition ahead during driving is obtained. According to the road condition prediction information, the road condition ahead can be sensed in advance, and combined with the current road condition information, the strategy information for adjusting the suspension system of the vehicle is made in time, so that the suspension system of the vehicle is adjusted to the state of adapting to the road condition ahead in time, so that the vehicle drives smoothly and improves the ride comfort.
[0074] The above embodiments introduce an implementation method in which the central control system of the vehicle obtains environmental images and attitude angles from the image acquisition device and the IMU respectively, and obtains forward road condition prediction information and current road condition information during vehicle driving based on the environmental images and the attitude angles respectively.
[0075] In order to reduce the computing pressure of the central control system and make the vehicle adjustment more timely, in another optional implementation, other module units outside the central control system can also be used to obtain environmental images from the image acquisition device, and determine the forward road condition prediction information during the vehicle's driving process based on the environmental images, and obtain posture information from the IMU, and determine the current road condition information during the vehicle's driving process based on the posture information. For the specific implementation process, please refer to the following content:
[0076] The road condition prediction information ahead of the vehicle during driving can be obtained in the following manner: obtaining an environmental image of the vehicle's surrounding environment captured by an image acquisition device on the vehicle; inputting the environmental image into a pre-trained road condition prediction model to obtain the road condition prediction information ahead of the vehicle during driving. Among them, the road condition prediction model is obtained by obtaining environmental sample images of the surrounding environment of the vehicle during driving and road condition prediction annotation information corresponding to the environmental sample images, and using the environmental sample images as the input of the neural network and the road condition prediction annotation information as the output of the neural network, and iteratively training the neural network. The iterative training process of the neural network in this embodiment can refer to the introduction of the prior art, which will not be repeated here.
[0077] Take the image acquisition device as an example, the vehicle-mounted camera. Figure 4 As shown, the on-board camera continuously collects environmental images of the vehicle's surroundings, which include the road in front of the vehicle, and inputs them into the road condition prediction model. The road condition prediction model will extract the feature map in the environmental image based on the environmental image, and determine the road condition prediction information in front of the vehicle based on the extracted feature map and output it to the central control system.
[0078] The current road condition information of the vehicle during driving can be obtained in the following manner: determine the change in posture information based on the posture information of the vehicle within a preset time period; when the change in posture information is greater than the preset change, determine that the current driving road condition information is an unstable section; when the change in posture information is less than or equal to the preset change, determine that the current driving road condition information is a stable section.
[0079] In this embodiment, the preset change amount can be set to 0. Considering that there may be some errors in actual application, the preset change amount can be set to a value greater than 0. The specific value can be set by technicians in this field according to actual conditions.
[0080] Taking the preset change of 0 as an example, within the T time period, the T time period includes time t1, time t2, time t3, time t4, and time t5 in chronological order. The attitude angles at time t1, time t2, time t3, time t4, and time t5 can be obtained through the IMU. The attitude angles at time t1, time t2, time t3, time t4, and time t5 are analyzed to determine whether the attitude angle change at adjacent moments is 0. If the attitude angles at adjacent moments are all 0 or most of them are 0, it indicates that the current driving condition of the vehicle is a stable section. Otherwise, it indicates that the current driving condition of the vehicle is an unstable section.
[0081] The above-mentioned time t1, time t2, time t3, time t4, and time t5 may be in a continuous time sequence or a discrete time sequence, and this embodiment does not specifically limit this. In addition, the current driving road condition information in this embodiment may be obtained based on one attitude angle analysis, or may be obtained based on two or three attitude angles analysis. In the case where the current driving road condition information is analyzed based on two or three attitude angles, if the change amount of one attitude angle is greater than the preset change amount, it is considered that the current driving road condition is an unstable section.
[0082] In addition to the above method of determining the current road condition information of the vehicle during driving based on the preset change amount, other module units outside the central control system can also be used to obtain the attitude angle from the IMU, and determine the current road condition information of the vehicle during driving based on the attitude angle. For the specific implementation process, please refer to the following introduction:
[0083] Please continue reading Figure 4 , the posture information of the vehicle can be input into the pre-trained road condition detection model to obtain the current driving road condition information of the vehicle. Wherein, the road condition detection model is obtained by obtaining posture sample data of the vehicle during driving and the current driving road condition annotation information corresponding to the posture sample data; and taking the posture sample data as the input of the neural network, taking the current driving road condition annotation information as the output of the neural network, and the neural network is iteratively trained to obtain the information. Wherein, the iterative training process of the neural network can refer to the introduction of the prior art, which will not be repeated here.
[0084] The inertial measurement unit IMU continuously collects the vehicle's attitude angle and inputs it into the road condition detection model. The road condition detection model outputs the vehicle's current driving road condition prediction information to the central control system based on the vehicle's attitude angle over a period of time. During the vehicle's driving process, the vehicle's central control system can continuously obtain the vehicle's forward road condition prediction information from the road condition prediction model, as well as the vehicle's current road condition determined based on the vehicle's attitude angle over a period of time collected by the IMU, or continuously obtain the vehicle's current driving road condition information from the road condition detection model. Compared to the implementation method of directly having the central control system determine the current driving road condition information based on the attitude angle, the use of a road condition detection model can reduce the calculation pressure of the central control system and make vehicle adjustments more timely.
[0085] For autonomous driving, the accuracy of the strategy is crucial in the process of determining the strategy information. The accuracy of the strategy determines the safety of the vehicle. Therefore, in order to improve the accuracy of the strategy, the vehicle's forward road condition prediction information and the current driving road condition information during driving can also be input into the pre-trained strategy determination model to obtain the strategy information for adjusting the vehicle's suspension system. The strategy determination model is obtained by obtaining training sample data and adjustment strategy annotation information corresponding to the training sample data, the training sample data includes forward road condition sample data and current driving road condition sample data; and the training sample data is used as the input of the neural network, and the adjustment strategy annotation information is used as the output of the neural network, and the neural network is iteratively trained.
[0086] For example, Figure 4 As shown, after the central control system obtains the forward road condition prediction information and the current driving road condition information, it inputs the forward road condition prediction information and the current driving road condition information into the strategy determination model, and the strategy determination model will output the corresponding strategy information for adjusting the suspension system of the vehicle. Of course, the strategy determination model can also be independent of the central control system, and those skilled in the art can make corresponding settings according to actual conditions, and this embodiment does not specifically limit this.
[0087] For example, Figure 5 As shown, if the prediction result obtained by the road condition prediction model based on the environmental image collected by the on-board camera indicates that the road surface is slippery, and the detection result obtained by the road condition detection model based on the posture information collected by the IMU indicates that the current road section is a smooth section, the central control system will determine the strategy information for lowering the suspension height of the vehicle's suspension system, and the adjustment system will lower the suspension height of the vehicle's suspension system according to the strategy information.
[0088] On the basis of the above embodiments, more sensor data may be integrated, such as vehicle speed data collected by a speed sensor on the vehicle, to determine strategy information for adjusting the vehicle's suspension system. For details, please refer to the following embodiments:
[0089] Figure 6 This is a flow chart of a vehicle driving stability control method provided by another embodiment of the present application. Based on the above embodiment, the vehicle driving stability control method provided by this embodiment specifically includes the following steps:
[0090] Step 601: Obtain the forward road condition prediction information, current road condition information and wind resistance information of the vehicle during driving.
[0091] Among them, for obtaining the forward road condition prediction information and the current driving road condition information of the vehicle during driving, reference may be made to the introduction of the aforementioned embodiment, which will not be repeated here.
[0092] Compared with the previous embodiment, this embodiment adds wind resistance information, which refers to the resistance from the air during the vehicle's driving process. The wind resistance information can be determined based on the vehicle's speed information and shape and structure information. The vehicle's shape and structure information refers to the vehicle's external structure, such as the vehicle's size (including length, width and height) and streamline structure. The vehicle's shape and structure information can be pre-stored on the vehicle, and the vehicle's speed can be collected by a speed sensor installed on the vehicle.
[0093] Generally speaking, for the same vehicle shape and structure, the higher the vehicle speed, the greater the wind resistance; and for the same vehicle speed, the larger the size of the vehicle shape and structure, the greater the wind resistance.
[0094] In order to conveniently and quickly determine the current wind resistance information of the vehicle, the speed information and shape structure information of the vehicle can be input into a preset wind resistance model to obtain the wind resistance information of the vehicle. The preset wind resistance model is modeled based on the speed information and shape structure information of the vehicle and the corresponding wind resistance information. The central control system can obtain the current wind resistance information of the vehicle from the wind resistance model.
[0095] Step 602: Determine strategy information for adjusting the suspension system of the vehicle based on the forward road condition prediction information, the current driving road condition information, and the wind resistance information.
[0096] In an optional scenario, if the forward road condition prediction information indicates that the road section is smooth, the current driving road condition information indicates that the road section is smooth, and the wind resistance information indicates that the wind resistance continues to increase, it is determined to increase the damping coefficient and suspension height of the vehicle's suspension system.
[0097] On the basis of determining the strategy information by combining the road condition prediction information ahead and the current driving road condition information through the model, the present embodiment can also input the road condition prediction information ahead, the current driving road condition information and the wind resistance information into the pre-trained strategy determination model to obtain the strategy information for adjusting the suspension system of the vehicle. Compared with the strategy determination model of the aforementioned embodiment, the strategy determination model in the present embodiment is obtained by obtaining training sample data and adjustment strategy annotation information corresponding to the training sample data, the training sample data includes road condition sample data ahead, current driving road condition sample data, speed sample data and vehicle shape structure information; and using the training sample data as the input of the neural network, using the adjustment strategy annotation information as the output of the neural network, and iteratively training the neural network. Among them, the specific training process of the neural network can be referred to the introduction of the prior art, and this embodiment will not be described in detail.
[0098] The trained strategy determination model can be stored in the central control system. After the central control system obtains the road condition prediction information, the current driving road condition information and the wind resistance information, the road condition prediction information, the current driving road condition information and the wind resistance information are input into the trained strategy determination model, and the strategy determination model will output the strategy information for adjusting the suspension system of the vehicle. The strategy information will be sent to the adjustment system, such as the control system of the suspension system, to control the suspension system to make corresponding adjustments.
[0099] Step 603: Adjust the suspension system of the vehicle according to the strategy information.
[0100] After receiving the strategy information for adjusting the vehicle's suspension system, the vehicle's adjustment system, such as the control system of the suspension system, will adjust the damping coefficient and / or suspension height of the vehicle's suspension system according to the strategy information, so that the parameters of the suspension system adapt to the road conditions ahead, allowing the vehicle to run smoothly and improving passenger comfort.
[0101] For example, Figure 7 As shown, the environmental image acquired by the image acquisition device is input into the road condition prediction model, the posture information collected by the IMU is input into the road condition detection model, and the vehicle speed is input into the wind resistance model. If the road condition prediction information ahead predicted by the road condition prediction model indicates that the road section is smooth, the current driving road condition information output by the road condition detection model indicates that the road section is smooth, and the wind resistance information output by the wind resistance model indicates that the wind resistance continues to increase, then the strategy determination model determines the strategy information for raising the damping coefficient of the vehicle's suspension system and lowering the suspension height according to the outputs of the road condition prediction model, the road condition detection model and the wind resistance model, and sends it to the adjustment system so that the adjustment system raises the damping coefficient of the vehicle's suspension system and lowers the suspension height. The center of gravity of the vehicle will be lowered and closer to the ground, thereby reducing the wind resistance to the vehicle and allowing the vehicle to travel more smoothly.
[0102] The embodiment of the present application obtains the forward road condition prediction information, the current road condition information and the current wind resistance information of the vehicle during driving, and determines the strategy information for adjusting the suspension system of the vehicle according to the forward road condition prediction information, the current road condition information and the current wind resistance information, and adjusts the suspension system of the vehicle according to the strategy information, so as to achieve the purpose of making the vehicle drive smoothly. Not only the current road condition information indicating the vehicle during driving is obtained, but also the prediction information of the road condition ahead during driving is obtained. According to the forward road condition prediction information, the forward road condition can be perceived in advance, and combined with the current road condition information, the strategy information for adjusting the suspension system of the vehicle is made in time, so that the suspension system of the vehicle is adjusted to the state of adapting to the forward road condition in time, so that the vehicle drives smoothly and improves the riding comfort. In addition, according to the posture information and the wind resistance information, the current state of the vehicle can be determined from different angles, and combined with the forward road condition prediction information, the adjustment strategy information more suitable for the current scene can be made for the vehicle to adjust the vehicle, and the adjusted comfort can better meet the passengers' requirements for stability.
[0103] Figure 8 A flow chart of a vehicle driving stability control device provided in an embodiment of the present application. The vehicle driving stability control device of this embodiment may be a module in the central control system of the above-mentioned embodiment. On the basis of the above-mentioned embodiment, the vehicle driving stability control device provided in this embodiment includes: an acquisition module 81, a strategy determination module 82 and an adjustment module 83; wherein the acquisition module 81 is used to obtain the forward road condition prediction information and the current driving road condition information of the vehicle during driving; the strategy determination module 82 determines the strategy information for adjusting the suspension system of the vehicle according to the forward road condition prediction information and the current driving road condition information; the adjustment module 83 is used to adjust the suspension system of the vehicle according to the strategy information.
[0104] Optionally, the acquisition module 81 acquires the road condition prediction information ahead of the vehicle during driving, including: acquiring an environmental image of the vehicle's surrounding environment captured by an image acquisition device on the vehicle; inputting the environmental image into a pre-trained road condition prediction model to obtain the road condition prediction information ahead of the vehicle during driving.
[0105] Optionally, the device also includes a first training module 84, which uses the following process to train the neural network to obtain a road condition prediction model: obtain environmental sample images of the surrounding environment of the vehicle during driving and road condition prediction annotation information corresponding to the environmental sample images; use the environmental sample images as input of the neural network, use the road condition prediction annotation information as output of the neural network, iteratively train the neural network, and obtain the road condition prediction model.
[0106] Optionally, the acquisition module 81 acquires the current driving road condition information of the vehicle, specifically including: acquiring the posture information of the vehicle collected by an inertial measurement unit on the vehicle; and determining the current driving road condition information of the vehicle based on the posture information of the vehicle.
[0107] Optionally, the acquisition module 81 determines the current driving road condition information of the vehicle based on the posture information of the vehicle, including: determining the change of the posture information based on the posture information of the vehicle within a preset time period; when the change of the posture information is greater than the preset change, determining that the current driving road condition information is an unstable section; when the change of the posture information is less than or equal to the preset change, determining that the current driving road condition information is a stable section.
[0108] Optionally, the acquisition module 81 determines the current driving road condition information of the vehicle according to the posture information of the vehicle, including: inputting the posture information of the vehicle into a pre-trained road condition detection model to obtain the current driving road condition information of the vehicle.
[0109] Optionally, the device also includes a second training module 85, which uses the following process to train the neural network to obtain a road condition detection model: obtain posture sample data during the vehicle's driving process and current driving road condition labeling information corresponding to the posture sample data; use the posture sample data as the input of the neural network, use the current driving road condition labeling information as the output of the neural network, iteratively train the neural network, and obtain the road condition detection model.
[0110] Optionally, the strategy determination module 82 determines the strategy information for adjusting the suspension system of the vehicle based on the forward road condition prediction information and the current driving road condition information, specifically including: inputting the forward road condition prediction information and the current driving road condition information of the vehicle during driving into a pre-trained strategy determination model to obtain the strategy information for adjusting the suspension system of the vehicle.
[0111] Optionally, the device also includes: a third training module 86, which uses the following process to train the neural network to obtain the strategy determination model: obtain training sample data and adjustment strategy annotation information corresponding to the training sample data, the training sample data including front road condition sample data and current driving road condition sample data; use the training sample data as the input of the neural network, use the adjustment strategy annotation information as the output of the neural network, iteratively train the neural network, and obtain the strategy determination model.
[0112] Optionally, the strategy determination module 82 determines strategy information for adjusting the suspension system of the vehicle based on the road condition prediction information ahead and the current driving road condition information, specifically including: if the road condition prediction information ahead indicates that the road surface is slippery and the current driving road condition information indicates a smooth road section, then determining to lower the suspension height of the vehicle's suspension system.
[0113] Optionally, the strategy determination module 82 determines strategy information for adjusting the suspension system of the vehicle based on the road condition prediction information ahead and the current driving road condition information, specifically including: if the road condition prediction information ahead indicates that the road section is bumpy and the current driving road condition information indicates that the bumpiness of the current road section is increasing, then determining to lower the damping coefficient of the suspension system and increase the suspension height of the suspension system of the vehicle.
[0114] Optionally, the acquisition module 81 is also used to acquire the wind resistance information of the vehicle; the strategy determination module 82 is also used to determine the strategy information for adjusting the suspension system of the vehicle based on the front road condition prediction information, the current driving road condition information and the wind resistance information.
[0115] Optionally, the acquisition module 81 acquires the wind resistance information of the vehicle, specifically including: acquiring the speed information and shape structure information of the vehicle; inputting the speed information and shape structure information of the vehicle into a preset wind resistance model to obtain the wind resistance information of the vehicle.
[0116] Optionally, the strategy determination module 82 determines the strategy information for adjusting the suspension system of the vehicle based on the road condition prediction information ahead, the current driving road condition information and the wind resistance information, specifically including: inputting the road condition prediction information ahead, the current driving road condition information and the wind resistance information into a pre-trained strategy determination model to obtain the strategy information for adjusting the suspension system of the vehicle.
[0117] Optionally, the third training module 86 is also used to train the neural network using the following process to obtain the strategy determination model: obtain training sample data and adjustment strategy annotation information corresponding to the training sample data, the training sample data including front road condition sample data, current driving road condition sample data, speed sample data and vehicle shape structure information; use the training sample data as the input of the neural network, use the adjustment strategy annotation information as the output of the neural network, iteratively train the neural network, and obtain the strategy determination model.
[0118] Optionally, the strategy determination module 82 determines the strategy information for adjusting the suspension system of the vehicle based on the road condition prediction information ahead, the current driving road condition information and the wind resistance information, specifically including: if the road condition prediction information ahead indicates that the road section is smooth, the current driving road condition information indicates that the road section is smooth and the wind resistance information indicates that the wind resistance continues to increase, then determine to increase the damping coefficient of the suspension system of the vehicle and lower the suspension height.
[0119] Figure 8 The vehicle stable driving control device of the illustrated embodiment can be used to execute the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effect are similar and will not be repeated here.
[0120] The embodiment of the present application obtains the road condition prediction information and current road condition information of the vehicle during driving, and determines the strategy information for adjusting the suspension system of the vehicle according to the road condition prediction information and current road condition information, and adjusts the suspension system of the vehicle according to the strategy information, so as to achieve the purpose of making the vehicle drive smoothly. Not only the current road condition information indicating the vehicle during driving is obtained, but also the prediction information of the road condition ahead during driving is obtained. According to the road condition prediction information, the road condition ahead can be sensed in advance, and combined with the current road condition information, the strategy information for adjusting the suspension system of the vehicle is made in time, so that the suspension system of the vehicle is adjusted to the state of adapting to the road condition ahead in time, so that the vehicle drives smoothly and improves the ride comfort.
[0121] According to an embodiment of the present application, the present application also provides a vehicle driving stability control device and a readable storage medium. The vehicle driving stability control device may be the central control system of the above embodiment, and the central control system includes a readable storage medium.
[0122] like Fig. 9 , is a block diagram of a vehicle ride stability control device according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, 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 application described and / or required herein.
[0123] like Fig. 9As shown, the vehicle ride stability control device includes: one or more processors 901, a memory 902, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig. 9 A processor 901 is taken as an example.
[0124] The memory 902 is a non-transitory computer-readable storage medium provided in the present application. The memory stores instructions executable by at least one processor to enable the at least one processor to execute the vehicle stable driving control method provided in the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions, which are used to enable a computer to execute the vehicle stable driving control method provided in the present application.
[0125] The memory 902 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the vehicle stable driving control method in the embodiment of the present application (for example, the attached Figure 8 The processor 901 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 902, that is, the vehicle stable driving control method in the above method embodiment is implemented.
[0126] The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created according to the use of electronic devices for vehicle smooth driving control, etc. In addition, the memory 902 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some embodiments, the memory 902 may optionally include a memory remotely arranged relative to the processor 901, and these remote memories may be connected to the vehicle driving stability control device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0127] The vehicle driving stability control device may further include: an input device 903 and an output device 904. The processor 901, the memory 902, the input device 903 and the output device 904 may be connected via a bus or other means. Fig. 9 The example of connecting through bus is taken in the following.
[0128] The input device 903 can receive input digital or character information, and generate key signal input related to user settings and function control of electronic devices for vehicle smooth driving control, such as input devices such as touch screen, keypad, mouse, track pad, touch pad, indicator rod, one or more mouse buttons, trackball, joystick, etc. The output device 904 may include a display device, an auxiliary lighting device (e.g., LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch screen.
[0129] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0130] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or means (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.
[0131] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types 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).
[0132] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.
[0133] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.
[0134] According to the technical solution of the embodiment of the present application, by obtaining the forward road condition prediction information and the current road condition information of the vehicle during driving, and according to the forward road condition prediction information and the current road condition information, determining the strategy information for adjusting the suspension system of the vehicle, and adjusting the suspension system of the vehicle according to the strategy information, the purpose of making the vehicle drive smoothly is achieved. Not only the current road condition information indicating the vehicle during driving is obtained, but also the prediction information of the road condition ahead during driving is obtained. According to the forward road condition prediction information, the forward road condition can be perceived in advance, and combined with the current road condition information, the strategy information for adjusting the suspension system of the vehicle is made in time, so that the suspension system of the vehicle is adjusted to the state of adapting to the road condition ahead in time, so that the vehicle drives smoothly and improves the ride comfort.
[0135] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.
[0136] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.
Claims
1. A vehicle driving stability control method, characterized in that: include: Acquiring the forward road condition prediction information and the current road condition information of the vehicle during driving, wherein the forward road condition prediction information includes any one of a slippery road surface, a bumpy road section, and a speed bump on the road section ahead; Acquiring wind resistance information of the vehicle according to the speed information and shape structure information of the vehicle; Input the road condition prediction information ahead, the current driving road condition information and the wind resistance information into a pre-trained strategy determination model to obtain strategy information for adjusting the suspension system of the vehicle; the strategy determination model is obtained by training a neural network in the following process: obtaining training sample data and adjustment strategy annotation information corresponding to the training sample data, the training sample data including road condition sample data ahead, current driving road condition sample data, speed sample data and vehicle shape and structure information; using the training sample data as the input of the neural network, using the adjustment strategy annotation information as the output of the neural network, and iteratively training the neural network to obtain the strategy determination model; The suspension system of the vehicle is adjusted according to the strategy information.
2. The method according to claim 1, characterized in that The obtaining of the forward road condition prediction information of the vehicle during driving includes: Acquire an environmental image of the vehicle's surroundings captured by an image capture device on the vehicle; The environment image is input into a pre-trained road condition prediction model to obtain the road condition prediction information ahead of the vehicle during driving.
3. The method according to claim 2, characterized in that The traffic condition prediction model is obtained by training the neural network using the following process: Acquire environmental sample images of the surrounding environment during vehicle driving and road condition prediction annotation information corresponding to the environmental sample images; The environment sample image is used as the input of the neural network, the road condition prediction annotation information is used as the output of the neural network, and the neural network is iteratively trained to obtain the road condition prediction model.
4. The method according to any one of claims 1 to 3, characterized in that: The obtaining of the current driving road condition information of the vehicle includes: Acquiring attitude information of the vehicle collected by an inertial measurement unit on the vehicle; The current driving road condition information of the vehicle is determined according to the posture information of the vehicle.
5. The method according to claim 4, characterized in that Determining the current driving road condition information of the vehicle according to the posture information of the vehicle includes: Determining a change amount of the posture information according to the posture information of the vehicle within a preset time period; When the change amount of the posture information is greater than a preset change amount, determining that the current driving road condition information is an unstable road section; When the change amount of the posture information is less than or equal to the preset change amount, it is determined that the current driving road condition information is a smooth road section.
6. The method according to claim 4, characterized in that Determining the current driving road condition information of the vehicle according to the posture information of the vehicle includes: The posture information of the vehicle is input into a pre-trained road condition detection model to obtain the current driving road condition information of the vehicle.
7. The method according to claim 6, characterized in that The road condition detection model is obtained by training the neural network using the following process: Acquire posture sample data of the vehicle during driving and current driving road condition annotation information corresponding to the posture sample data; The posture sample data is used as the input of the neural network, the current driving road condition labeling information is used as the output of the neural network, and the neural network is iteratively trained to obtain the road condition detection model.
8. The method according to any one of claims 1 to 7, characterized in that: The policy information includes: If the forward road condition prediction information indicates that the road surface is slippery and the current driving road condition information indicates that the road is a smooth section, it is determined to lower the suspension height of the suspension system of the vehicle.
9. The method according to any one of claims 1 to 7, characterized in that: The policy information includes: If the forward road condition prediction information indicates that the road section is bumpy and the current driving road condition information indicates that the bumpiness of the current road section is getting bigger and bigger, it is determined to lower the damping coefficient of the suspension system and increase the suspension height of the suspension system of the vehicle.
10. The method according to claim 1, characterized in that The step of obtaining wind resistance information of the vehicle according to the speed information and shape structure information of the vehicle includes: Acquiring speed information and shape structure information of the vehicle; The speed information and shape structure information of the vehicle are input into a preset wind resistance model to obtain the wind resistance information of the vehicle.
11. The method according to any one of claims 1 to 10, characterized in that: The policy information includes: If the forward road condition prediction information indicates that the road section is smooth, the current driving road condition information indicates that the road section is smooth, and the wind resistance information indicates that the wind resistance continues to increase, it is determined to increase the damping coefficient of the suspension system of the vehicle and lower the suspension height.
12. A vehicle driving stability control device, characterized in that: include: an acquisition module, used to acquire the forward road condition prediction information and the current road condition information of the vehicle during driving, wherein the forward road condition prediction information includes any one of a slippery road surface, a bumpy road section, and a speed bump on the forward road section; A strategy determination module, used to obtain wind resistance information of the vehicle according to speed information and shape structure information of the vehicle; Input the road condition prediction information ahead, the current driving road condition information and the wind resistance information into a pre-trained strategy determination model to obtain strategy information for adjusting the suspension system of the vehicle; the strategy determination model is obtained by training a neural network in the following process: obtaining training sample data and adjustment strategy annotation information corresponding to the training sample data, the training sample data including road condition sample data ahead, current driving road condition sample data, speed sample data and vehicle shape and structure information; using the training sample data as the input of the neural network, using the adjustment strategy annotation information as the output of the neural network, and iteratively training the neural network to obtain the strategy determination model; An adjustment module is used to adjust the suspension system of the vehicle according to the strategy information.
13. A vehicle driving stability control device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 11.
14. A vehicle, characterized in that: Includes the vehicle ride stability control device as described in claim 13.
15. The vehicle according to claim 14, characterized in that The vehicle further comprises: An image acquisition unit, used to acquire an environmental image of the vehicle's surroundings during the vehicle's driving process; The inertial measurement unit is used to collect the posture information of the vehicle while the vehicle is traveling.
16. The vehicle according to claim 15, characterized in that The vehicle further comprises: The speed sensor is used to collect speed information of the vehicle while the vehicle is traveling.
17. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 11.
