Vehicle control method and device, vehicle and storage medium
By obtaining the vehicle speed and steering wheel angle before the vehicle enters a turn, and controlling the dual-cavity hollow spring and damping continuously adjustable shock absorption system when the threshold is reached, the problem of poor vehicle lateral control in the prior art is solved, and the further improvement is achieved Excellent control effect.
Patent Information
- Application Number
- CN202411318013.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-20
- Publication Date
- 2024-11-26
AI Technical Summary
In the prior art, when the vehicle is lateral control, the trigger of CDC intervention control requires a faster suspension speed, while ordinary steering cannot provide a faster suspension speed, resulting in the inability to meet the control needs and the optimal control effect cannot be achieved.
Get the current speed before the vehicle enters the turning road and determines the required steering wheel angle. If the steering wheel state is steering and the vehicle speed and angle reach the threshold, the dual-cavity air spring and damping continuously adjustable shock absorption system are controlled by the joint controller. Ensure control is performed simultaneously during steering.
When the steering wheel state is steering, the vehicle can be controlled immediately through a dual-cavity hollow spring and a damping continuous adjustable shock absorption system to meet the lateral control needs and achieve the optimal control effect.
Smart Images

Figure CN119017886A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle control technology, and in particular to a vehicle control method, a vehicle control device, a vehicle and a computer-readable storage medium. Background Art
[0002] With the popularization of vehicles, vehicles have become an indispensable tool in daily life. When the vehicle is controlled laterally, it can be controlled by a double-cavity air spring and a damping continuously adjustable shock absorption system, for example, the vehicle is controlled by a closed double-cavity air spring and a CDC (Continuous Damping Control, automatic adjustment and uninterrupted shock absorption control system). However, the triggering of the CDC intervention control requires a faster suspension speed, and ordinary steering cannot provide a faster suspension speed, resulting in the inability to meet the control requirements when the vehicle is controlled laterally in the existing technology, thereby failing to achieve the optimal control effect. Summary of the invention
[0003] In view of the above problems, embodiments of the present invention are proposed to provide a vehicle control method, a vehicle control device, a vehicle, and a computer-readable storage medium that overcome the above problems or at least partially solve the above problems.
[0004] In order to solve the above problems, an embodiment of the present invention discloses a vehicle control method, wherein the vehicle has a double-cavity empty spring, a damping continuously adjustable shock absorption system and a joint controller, and the method comprises:
[0005] Before the vehicle enters a turning road, obtaining the current speed of the vehicle and determining the steering wheel angle required to pass the turning road;
[0006] If the steering wheel state of the vehicle is turning, and the current speed of the vehicle reaches the speed threshold, and the steering wheel angle reaches the steering wheel angle threshold, it is determined that the vehicle is controlled by controlling the dual-chamber air spring and the damping continuously adjustable shock absorption system through the joint controller.
[0007] Optionally, the vehicle speed threshold and the steering wheel angle threshold are determined in the following manner:
[0008] Set up a test group for testing vehicle speed and steering wheel angle;
[0009] According to the test group, the first mode, the second mode and the third mode are tested respectively to obtain test results; the first mode is that neither the double-cavity empty spring nor the damping continuously adjustable shock absorbing system controls the vehicle; the second mode is that only the double-cavity empty spring controls the vehicle; the third mode is that the double-cavity empty spring and the damping continuously adjustable shock absorbing system control the vehicle at the same time;
[0010] According to the test result, a vehicle speed threshold and a steering wheel angle threshold of the vehicle are determined.
[0011] Optionally, the test result includes vehicle body roll angle peak values and overshoot values corresponding to the first mode, the second mode, and the third mode respectively under the same test vehicle speed and the same test steering wheel angle state; and determining the vehicle speed threshold value and the steering wheel angle threshold value of the vehicle according to the test result includes:
[0012] determining a difference between the peak values of the vehicle body roll angle in the second mode and the first mode as a steady-state roll angle difference;
[0013] determining a difference between the peak values of the vehicle body roll angles in the second mode and the third mode as a roll angle peak value difference;
[0014] Determine the difference between the overshoot amounts of the second mode and the third mode as an overshoot difference;
[0015] A vehicle speed threshold and a steering wheel angle threshold of the vehicle are determined according to the roll angle steady-state difference, the roll angle peak difference and the overshoot difference.
[0016] Optionally, determining a vehicle speed threshold and a steering wheel angle threshold of the vehicle according to the roll angle steady-state difference, the roll angle peak difference and the overshoot difference comprises:
[0017] Determining whether the roll angle steady-state difference is greater than a first preset value;
[0018] If the roll angle steady-state difference is greater than the first preset value, determining whether the roll angle peak difference is greater than a second preset value, and whether the overshoot difference is greater than a third preset value;
[0019] If the roll angle peak difference is greater than the second preset value, and the overshoot difference is greater than the third preset value, the corresponding test vehicle speed is determined as the vehicle speed threshold of the vehicle, and the test steering wheel angle is determined as the steering wheel angle threshold of the vehicle.
[0020] Optionally, the vehicle further has an inertial sensor and a monocular camera; the obtaining of the current speed of the vehicle and determining the steering wheel angle required to pass the turning road comprises:
[0021] Acquiring the current speed of the vehicle through the inertial sensor;
[0022] Obtaining road information of the road ahead through the monocular camera; the road information includes: a straight road and / or a turning road;
[0023] If the current road information is a curved road, the steering wheel angle required to pass the curved road is determined by a preset calculation model.
[0024] Optionally, the determining the steering wheel angle required for passing the turning road by using a preset calculation model includes:
[0025] Calculating the turning angle of the turning road by using a preset calculation model;
[0026] Get the steering wheel ratio of the vehicle;
[0027] The turning angle is converted according to the steering wheel steering ratio to obtain the steering wheel angle required to pass the turning road.
[0028] Optionally, the preset calculation model is trained in the following manner:
[0029] Collecting a sample data set; the sample data set includes road images with different vehicle viewing angle changes, different road conditions, and different curve rate curves;
[0030] Preprocessing the sample data set to obtain a processed data set;
[0031] Determine a composite loss function according to a preset classification loss function and a preset regression loss function;
[0032] According to the processed data set, the pre-trained model is trained to obtain an output result;
[0033] Determining a loss value of the output result according to the output result and the composite loss function;
[0034] Performing cyclic training and cyclic verification on the pre-trained model according to the loss value, and evaluating the result of each verification;
[0035] When the result evaluation meets the preset requirements, the corresponding pre-trained model after training is determined as the preset calculation model.
[0036] The embodiment of the present invention discloses a vehicle control device, wherein the vehicle has a double-cavity empty spring, a damping continuously adjustable shock absorption system and a joint controller, and the device comprises:
[0037] A first determination module is used to obtain the current speed of the vehicle before the vehicle enters the turning road, and determine the steering wheel angle required to pass the turning road;
[0038] The second determination module is used to determine that the vehicle is controlled by controlling the dual-chamber air spring and the damping continuously adjustable shock absorption system through the joint controller when the steering wheel state of the vehicle is turning, the current speed of the vehicle reaches the speed threshold, and the steering wheel angle reaches the steering wheel angle threshold.
[0039] Optionally, the vehicle speed threshold and the steering wheel angle threshold are determined in the following manner:
[0040] A setting module is used to set the test group for testing vehicle speed and steering wheel angle;
[0041] The test module is used to test the first mode, the second mode and the third mode respectively according to the test group to obtain test results; the first mode is that neither the double-cavity empty spring nor the damping continuously adjustable shock absorbing system controls the vehicle; the second mode is that only the double-cavity empty spring controls the vehicle; the third mode is that the double-cavity empty spring and the damping continuously adjustable shock absorbing system control the vehicle at the same time;
[0042] The third determination module is used to determine the vehicle speed threshold and steering wheel angle threshold of the vehicle according to the test result.
[0043] Optionally, the test result includes the vehicle body roll angle peak values and overshoot values corresponding to the first mode, the second mode and the third mode respectively under the same test vehicle speed and the same test steering wheel angle state; the third determination module includes:
[0044] A first calculation submodule, configured to determine a difference between the peak values of the vehicle body roll angle in the second mode and the first mode as a steady-state difference of the roll angle;
[0045] A second calculation submodule, configured to determine a difference between the vehicle body roll angle peaks in the second mode and the third mode as a roll angle peak difference;
[0046] A third calculation submodule, configured to determine a difference between the overshoot amounts of the second mode and the third mode as an overshoot difference;
[0047] The first determination submodule is used to determine a vehicle speed threshold and a steering wheel angle threshold of the vehicle according to the roll angle steady-state difference, the roll angle peak difference and the overshoot difference.
[0048] Optionally, the first determining submodule includes:
[0049] A first judging unit, configured to judge whether the roll angle steady-state difference is greater than a first preset value;
[0050] a second judgment unit, configured to judge whether the roll angle peak value difference is greater than a second preset value, and whether the overshoot difference is greater than a third preset value, if the roll angle steady-state difference is greater than the first preset value;
[0051] A determination unit is used to determine the corresponding test vehicle speed as the vehicle speed threshold of the vehicle and the test steering wheel angle as the steering wheel angle threshold of the vehicle if the roll angle peak difference is greater than the second preset value and the overshoot difference is greater than the third preset value.
[0052] Optionally, the vehicle further has an inertial sensor and a monocular camera; the first determination module includes:
[0053] A first acquisition submodule, configured to acquire the current speed of the vehicle through the inertial sensor;
[0054] The second acquisition submodule is used to acquire road information of the road ahead through the monocular camera; the road information includes: a straight road and / or a turning road;
[0055] The second determination submodule is used to determine the steering wheel angle required to pass the turning road through a preset calculation model if the current road information is a turning road.
[0056] Optionally, the second determining submodule includes:
[0057] A calculation unit, which calculates the turning angle of the turning road by using a preset calculation model;
[0058] An acquisition unit, used for acquiring a steering ratio of a steering wheel of a vehicle;
[0059] The conversion unit is used to convert the turning angle according to the steering wheel steering ratio to obtain the steering wheel angle required for passing the turning road.
[0060] Optionally, the preset calculation model is trained in the following manner:
[0061] An acquisition module is used to acquire a sample data set; the sample data set includes road images with different vehicle viewing angle changes, different road conditions, and different curve rate curves;
[0062] A preprocessing module, used to preprocess the sample data set to obtain a processed data set;
[0063] A fourth determination module, used to determine a composite loss function according to a preset classification loss function and a preset regression loss function;
[0064] A training module, used to train the pre-trained model according to the processed data set to obtain an output result;
[0065] A fifth determination module, used to determine a loss value of the output result according to the output result and the composite loss function;
[0066] An evaluation module, used for performing cyclic training and cyclic verification on the pre-trained model according to the loss value, and performing result evaluation on the result of each verification;
[0067] The sixth determination module is used to determine the corresponding pre-trained model after training as the preset calculation model when the result evaluation meets the preset requirements.
[0068] The present invention also discloses a vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the vehicle control method as described above when executing the computer program.
[0069] The present invention also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle control method as described above are implemented.
[0070] The embodiments of the present invention include the following advantages:
[0071] In an embodiment of the present invention, before a vehicle enters a turning road, the current speed of the vehicle is first obtained, and then the steering wheel angle required to pass the turning road is determined; if the steering wheel state of the vehicle is turning, and the current speed of the vehicle reaches the speed threshold, and the steering wheel angle reaches the steering wheel angle threshold, it is determined to control the vehicle by controlling the dual-cavity air spring and the damping continuously adjustable shock absorbing system through a joint controller, so that when the steering wheel state is turning, the vehicle can be immediately controlled simultaneously by the dual-cavity air spring and the damping continuously adjustable shock absorbing system, thereby meeting the needs for lateral control of the vehicle and achieving the optimal control effect. BRIEF DESCRIPTION OF THE DRAWINGS
[0072] Figure 1 is a flow chart of steps of a vehicle control method provided by an embodiment of the present invention;
[0073] Figure 2 is a flowchart of a method for determining a vehicle speed threshold and a steering wheel steering angle threshold provided by an embodiment of the present invention;
[0074] Figure 3 is a flowchart of the steps of a training method of a preset computing model provided by an embodiment of the present invention;
[0075] Figure 4 It is a structural block diagram of a vehicle control device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0076] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0077] In the related art, since the triggering of CDC intervention control requires a faster suspension speed, and ordinary steering cannot provide a faster suspension speed, the prior art cannot meet the control requirements when performing lateral control on the vehicle, and thus cannot achieve the optimal control effect. In order to solve the above technical problems, the present invention provides a vehicle control method. Before the vehicle enters a turning road, the current speed of the vehicle is first obtained, and then the steering wheel angle required to pass the turning road is determined. If the steering wheel state of the vehicle is steering, and the current speed of the vehicle reaches the speed threshold, and the steering wheel angle reaches the steering wheel angle threshold, it is determined to control the vehicle through the joint controller to control the dual-cavity air spring and the damping continuously adjustable shock absorbing system, so that when the steering wheel state is steering, the vehicle can be immediately controlled by the dual-cavity air spring and the damping continuously adjustable shock absorbing system at the same time, meeting the requirements for lateral control of the vehicle and achieving the optimal control effect.
[0078] Reference Figure 1 , shows a flow chart of the steps of a vehicle control method provided by an embodiment of the present invention, wherein the vehicle has a double-cavity empty spring, a damping continuously adjustable shock absorption system and a joint controller, and the method may specifically include the following steps:
[0079] Step 101, before the vehicle enters a turning road, the current speed of the vehicle is obtained, and the steering wheel angle required to pass the turning road is determined.
[0080] In an embodiment of the present invention, a vehicle may have a double-cavity empty spring and a damping continuously adjustable shock absorbing system and a joint controller, wherein the double-cavity empty spring may be a closed double-cavity empty spring, the damping continuously adjustable shock absorbing system may be a CDC, and the joint controller may control the vehicle by controlling the double-cavity empty spring and the damping continuously adjustable shock absorbing system. During the driving process of the vehicle, before entering a curved road, the current speed of the vehicle may be obtained, and the steering wheel angle required to pass the curved road may be determined.
[0081] In one embodiment, the vehicle may also have an inertial sensor and a monocular camera; obtaining the current speed of the vehicle and determining the steering wheel angle required to pass a turning road may include: obtaining the current speed of the vehicle through an inertial sensor; obtaining road information of the road ahead through a monocular camera; the road information includes: a straight road and / or a turning road; if the current road information is a turning road, determining the steering wheel angle required to pass the turning road through a preset calculation model.
[0082] Specifically, when obtaining the vehicle speed, the vehicle can obtain it through the inertial sensor on the vehicle, and the inertial sensor is an IMU (Inertial Measurement Unit) sensor. In the present invention, the vehicle speed can also be obtained by other methods, and the present invention does not specifically limit the specific method. In the present invention, the vehicle can be equipped with a monocular camera, and the monocular camera can also be a driving recorder. When the vehicle is driving, the monocular camera can obtain the road information of the road in front of the vehicle in real time, wherein the road information can include straight roads and / or turning roads, that is, the road information can be a single straight road, a single turning road, or an intersection section with both straight roads and turning roads. When it is detected that the current road information contains a turning road, at this time, the steering wheel steering required by the vehicle for the turning road can be determined by a preset calculation model.
[0083] In one embodiment, determining the steering wheel angle required to pass a turning road through a preset calculation model may include: calculating the turning angle of the turning road through a preset calculation model; obtaining the steering wheel steering ratio of the vehicle; and converting the turning angle according to the steering wheel steering ratio to obtain the steering wheel angle required to pass the turning road.
[0084] Specifically, when determining the steering wheel angle required to pass a curved road, the road image in the road information can be input into a preset calculation model. The preset calculation model can calculate the turning angle of the curved road and the turning direction. After calculating the turning angle, the steering ratio of the vehicle's steering wheel can be obtained. Then, according to the steering ratio of the steering wheel, the turning angle can be converted to obtain the steering wheel angle required to pass the curved road. The present invention can also convert the turning angle and the turning direction according to the steering wheel steering ratio to obtain the steering wheel angle required for the curved road.
[0085] Step 102, if the steering wheel state of the vehicle is turning, and the current speed of the vehicle reaches the speed threshold, and the steering wheel angle reaches the steering wheel angle threshold, determine to control the vehicle by controlling the dual-chamber air spring and the damping continuously adjustable shock absorption system through the joint controller.
[0086] In the embodiment of the present invention, after determining the steering wheel angle required for passing a turning road, the steering wheel state of the vehicle can be detected. If the steering wheel state of the vehicle has not been turned, it indicates that the vehicle is going straight and is not entering a turning road. At this time, the double-chamber air spring and the damping continuously adjustable shock absorption system do not need to control the vehicle at the same time. If the steering wheel state of the vehicle is turning, it indicates that the vehicle is about to enter a turning road. At this time, it can be detected whether the current vehicle speed reaches the vehicle speed threshold and whether the steering wheel angle reaches the steering wheel angle threshold. If the current vehicle speed reaches the vehicle speed threshold and If the steering wheel angle reaches the steering wheel angle threshold, the joint controller can switch the dual-chamber air spring to the high-stiffness mode at the moment the steering wheel is turned, and the control damping continuously adjustable shock absorption system will also input a larger current to increase the damping of the shock absorption system, thereby achieving lateral control of the vehicle during the vehicle turning process. After the vehicle enters the straight road, the joint controller can turn off the control of the dual-chamber air spring and the continuously adjustable damping shock absorption system, thereby avoiding the frequent closing and opening of the dual-chamber air spring and the continuously adjustable damping shock absorption system, affecting the riding and driving experience of the occupants.
[0087] In an embodiment of the present invention, before a vehicle enters a turning road, the current speed of the vehicle is first obtained, and then the steering wheel angle required to pass the turning road is determined; if the steering wheel state of the vehicle is turning, and the current speed of the vehicle reaches the speed threshold, and the steering wheel angle reaches the steering wheel angle threshold, it is determined that the joint controller controls the vehicle simultaneously through the dual-cavity air spring and the damping continuously adjustable shock absorbing system, so that when the steering wheel state is turning, the vehicle can be immediately controlled simultaneously through the dual-cavity air spring and the damping continuously adjustable shock absorbing system, thereby meeting the needs for lateral control of the vehicle and achieving the optimal control effect.
[0088] Reference Figure 2 , shows a flowchart of a method for determining a vehicle speed threshold and a steering wheel steering angle threshold provided by an embodiment of the present invention, and the specific steps are as follows:
[0089] Step 201, setting a test group for testing vehicle speed and testing steering wheel angle;
[0090] In an embodiment of the present invention, when determining the vehicle speed threshold and the steering wheel angle threshold, a test group can be set first, which includes a test vehicle speed and a test steering wheel angle, wherein the test vehicle speed range can be 5Km / h-80km / h, the test steering wheel angle can be 5°-90°, the test vehicle speed can increase step by step by 5Km / h, the test steering wheel angle can increase step by step by 5°, and the test vehicle speed and steering wheel angle are combined in an arrangement and combination manner to obtain a test group.
[0091] Step 202, according to the test group, the first mode, the second mode and the third mode are tested respectively to obtain test results; the first mode is that neither the double-cavity empty spring nor the damping continuously adjustable shock absorbing system controls the vehicle; the second mode is that only the double-cavity empty spring controls the vehicle; the third mode is that the double-cavity empty spring and the damping continuously adjustable shock absorbing system control the vehicle at the same time;
[0092] In an embodiment of the present invention, after the test group is set up, the following three situations can be tested respectively according to the test group: neither the double-cavity empty spring nor the damping continuously adjustable shock absorbing system controls the vehicle, only the double-cavity empty spring controls the vehicle, and both the double-cavity empty spring and the damping continuously adjustable shock absorbing system control the vehicle at the same time. Neither the double-cavity empty spring nor the damping continuously adjustable shock absorbing system controls the vehicle in the first mode, only the double-cavity empty spring controls the vehicle in the second mode, and both the double-cavity empty spring and the damping continuously adjustable shock absorbing system control the vehicle in the third mode.
[0093] It should be noted that the test results in the present invention may include the vehicle body roll angle peak values and overshoot values corresponding to the first mode, the second mode and the third mode respectively under the same test vehicle speed and the same test steering wheel angle state. For example: when the test speed is 5 km / h and the test steering wheel angle is 5°, the vehicle body roll angle peak values and overshoot values corresponding to the first mode, the second mode and the third mode, wherein the vehicle body roll angle peak value includes the transient roll angle peak value and the steady-state roll angle peak value. The overshoot value is calculated by the following formula (1):
[0094] OS= (roll_max-roll_static) / roll_max*100% formula (1)
[0095] Among them, OS is the overshoot, roll_max is the transient roll angle peak, and roll_static is the steady-state roll angle peak.
[0096] Step 203: Determine a vehicle speed threshold and a steering wheel angle threshold of the vehicle according to the test result.
[0097] In the embodiment of the present invention, after the test results are obtained, the vehicle speed threshold and the steering wheel angle threshold of the vehicle can be determined according to the test results.
[0098] In one embodiment, the test results include the body roll angle peak values and overshoot values corresponding to the first mode, the second mode and the third mode respectively under the same test vehicle speed and the same test steering wheel angle state; according to the test results, the vehicle speed threshold and steering wheel angle threshold of the vehicle are determined, including: determining the difference between the body roll angle peak values of the second mode and the first mode as the roll angle steady-state difference; determining the difference between the body roll angle peak values of the second mode and the third mode as the roll angle peak difference; determining the difference between the overshoot values of the second mode and the third mode as the overshoot difference; determining the vehicle speed threshold and steering wheel angle threshold according to the roll angle steady-state difference, the roll angle peak difference and the overshoot difference.
[0099] Specifically, the difference between the steady-state roll angle peak value of the vehicle body roll angle peak value in the second mode and the first mode can be determined first, and determined as the steady-state roll angle difference; the difference between the transient roll angle peak value of the vehicle body roll angle peak value in the second mode and the third mode can be determined, and determined as the roll angle peak difference; the difference between the overshoot in the second mode and the third mode can be determined as the overshoot difference. Then, according to the steady-state roll angle difference, the roll angle peak difference and the overshoot difference, the vehicle speed threshold and the steering wheel angle threshold of the vehicle are determined.
[0100] In one embodiment, determining a vehicle speed threshold and a steering wheel angle threshold of a vehicle based on a steady-state roll angle difference, a roll angle peak difference and an overshoot difference may include: judging whether the steady-state roll angle difference is greater than a first preset value; if the steady-state roll angle difference is greater than the first preset value, judging whether the roll angle peak difference is greater than a second preset value, and whether the overshoot difference is greater than a third preset value; if the roll angle peak difference is greater than the second preset value, and the overshoot difference is greater than the third preset value, determining the corresponding test vehicle speed as the vehicle speed threshold, and determining the test steering wheel angle as the vehicle steering wheel angle threshold.
[0101] Specifically, the first preset value can be 0.3, the second preset value can be 0.2, and the third threshold value can be 10%. If it is judged whether the steady-state difference of the roll angle is less than 0.3, it indicates that the double-cavity empty spring is not needed to control the vehicle at this time, and the stiffness valve does not need to be closed. If it is judged whether the steady-state difference of the roll angle is greater than 0.3, if it is greater than 0.3, it indicates that the double-cavity empty spring should be needed to control the vehicle at this time, and the stiffness valve needs to be closed, and continue to judge whether the peak difference of the roll angle is greater than 0.2 and whether the overshoot difference is greater than 10%. If the peak difference of the roll angle is greater than 0.2 and the overshoot difference is greater than 10%, it can be judged that the stiffness valve needs to be closed, and the damping continuously adjustable shock absorption system is also needed to control the vehicle, and the test vehicle speed and test steering wheel angle threshold at this time are recorded, and the test vehicle speed at this time is determined as the vehicle speed threshold of the vehicle, and the test steering wheel angle is determined as the steering wheel angle threshold of the vehicle. In the present application, specific values of the first preset value, the second preset value and the third preset value can be set according to actual needs, and the present invention does not make specific limitations here.
[0102] It should be noted that, for vehicles of different models, the vehicle speed threshold and steering wheel angle threshold corresponding to the different vehicle models may be determined according to the above method for determining the vehicle speed threshold and steering wheel angle threshold.
[0103] Reference Figure 3 , shows a flowchart of a method for training a preset computing model provided by an embodiment of the present invention, and the specific steps are as follows:
[0104] Step 301, collecting a sample data set; the sample data set includes road images with different vehicle viewing angle changes, different road conditions, and different curve rate curves;
[0105] In an embodiment of the present invention, when training the pre-trained model, sample data may be collected first, wherein the sample data may include road images with different vehicle perspective changes, different road conditions, and different curve rates. Different road conditions may include straight roads, turning roads, clear and blurred lane lines, different road markings and signs, complex urban intersections, rural roads, different lighting environments, dry, slippery, waterlogged, snow-covered, and damaged roads, etc.
[0106] Step 302, preprocessing the sample data set to obtain a processed data set;
[0107] In an embodiment of the present invention, after a sample data set is collected, the sample data set may be preprocessed, wherein the preprocessing may include: screening road images in the sample data set, eliminating road images that do not meet quality standards, adjusting the remaining road images to a uniform size and resolution, ensuring consistency in model training, converting the road images into a color space that is more suitable for feature extraction, enhancing the ability to distinguish brightness and saturation, performing noise elimination and image enhancement on the road images, intelligently adjusting the denoising intensity according to local features of the image, retaining details while reducing environmental interference, automatically adjusting the contrast and brightness of the image, especially under low-light conditions, improving the recognizability of road signs and edges, using edge detection algorithms to enhance key features such as road sign lines and boundaries, ensuring that the model can accurately capture this information, and performing feature encoding on environmental features in the road image, and finely annotating the data, wherein the standards are mainly divided into four categories: lane line standards, turning angle and direction standards, environmental feature standards, and visual auxiliary information annotation, thereby obtaining a processed data set that is helpful for model training.
[0108] Step 303, determining a composite loss function according to a preset classification loss function and a preset regression loss function;
[0109] In the embodiment of the present invention, before training the model, it is also necessary to determine a composite loss function based on a preset classification loss function and a preset regression loss function.
[0110] The preset classification loss function in the present invention can be calculated by the following formula (2):
[0111]
[0112] Among them, L class is the preset classification loss function, C is the total number of categories, and in the present invention, C can be 3, which are straight, left turn and right turn respectively, y class is the real category label of the data, that is, the annotation of the turning angle and direction in the above, straight is 0, right turn is 1, left turn is 2, p is the predicted probability, is the one-hot encoding of the true label, p (c) The probability of the model predicting the Cth class.
[0113] The preset regression loss function in the present invention can be calculated by the following formula (3):
[0114]
[0115] Among them, L regis a preset regression loss function, δ is a threshold used to smoothly transition from square loss to absolute loss. The initial value of δ is usually set to 1.25, and can also vary between 1 and 1.5. The specific value can be set according to data requirements, and the present invention does not make specific limitations here. pred is the turning angle predicted by the model, θ true is the actual turning angle.
[0116] In the present invention, the composite loss function is calculated by the following formula (4):
[0117] L total =αL class +βL reg Formula (4)
[0118] Among them, L total is the composite loss function, L class is the preset classification loss function, L reg is a preset regression loss function, α is the first weight, β is the second weight, and in the present invention, α can be set at about 0.3, and β can be set at about 0.7.
[0119] Step 304, training the pre-trained model according to the processed data set to obtain an output result;
[0120] In an embodiment of the present invention, after obtaining the processed data set and determining that it meets the loss function, the pre-trained model can be trained. The present invention adopts an iterative training method. In each iterative training, a batch of data sets can be randomly selected from the data set for training. Each time the pre-trained model is trained, the pre-trained model can output an output result, which is the turning direction and turning angle predicted by the model.
[0121] Step 305, determining a loss value of the output result according to the output result and the composite loss function;
[0122] In an embodiment of the present invention, after obtaining the output result, the loss value of the output result can be determined based on the output result and the true label, that is, the true turning direction and turning angle, and the determined composite loss function.
[0123] Step 306, performing cyclic training and cyclic verification on the pre-trained model according to the loss value, and evaluating the result of each verification;
[0124] In an embodiment of the present invention, after determining the loss value of the output result, the gradient of the preset classification loss function and the gradient of the preset regression loss function can be calculated, and then the first weight and the second weight for the next iterative training can be determined based on the gradient of the preset classification loss function and the gradient of the preset regression loss function.
[0125] In the present invention, the weight for the next iterative training is determined by the following formula (5):
[0126] Weight1=Weight2-learning_rate*readient formula (5)
[0127] Among them, Weight1 is the weight for the next iterative training, Weight2 is the weight for this training, learning_rate is the learning rate of the model, and readient is the gradient.
[0128] In the present invention, the gradient of the preset classification loss function is calculated by the following formula (6):
[0129]
[0130] in, is the gradient of the preset classification loss function, Z (c) are the inactive outputs of category C (going straight, turning left, and turning right), is the derivative of the Softmax function. The Softmax activation function is a commonly used activation function, mainly used in the output layer of multi-classification problems. Its main function is to convert a set of arbitrary real values into a probability distribution so that the sum of the output values is 1 and each output value is between 0 and 1. (c) is the probability that the model predicts class C.
[0131] In the present invention, the gradient of the preset regression loss function is calculated by the following formula (7):
[0132]
[0133] in, is the gradient of the preset regression loss function, θ pred is the turning angle predicted by the model, θ true is the actual turning angle.
[0134] In the present invention, when the weight calculated in formula (5) for the next iterative training is the first weight, readient is the gradient of the preset classification loss function in formula (6), and Weight1 is α in formula (4); when the weight calculated in formula (5) for the next iterative training is the second weight, readient is the gradient of the preset regression loss function in formula (7), and Weight1 is β in formula (4).
[0135] In an embodiment of the present invention, after iterative training of the pre-trained model, i.e., cyclic training, verification is performed after each training, i.e., cyclic verification, and a result evaluation is performed on each verification result.
[0136] Step 307: When the evaluation result meets the preset requirements, the corresponding pre-trained model after training is determined as the preset calculation model.
[0137] In an embodiment of the present invention, after evaluating the verification results, it can be determined whether the result evaluation meets the preset requirements, for example, whether the prediction accuracy meets the standards, etc. When the result evaluation meets the preset requirements, the corresponding trained model can be determined as the preset calculation model, and the preset calculation model can be adaptively adjusted in subsequent use to make the preset calculation model more perfect.
[0138] In an embodiment of the present invention, before a vehicle enters a turning road, the current speed of the vehicle is first obtained, and then the steering wheel angle required to pass the turning road is determined; if the steering wheel state of the vehicle is turning, and the current speed of the vehicle reaches the speed threshold, and the steering wheel angle reaches the steering wheel angle threshold, it is determined that the joint controller controls the vehicle through the dual-cavity air spring and the damping continuously adjustable shock absorbing system, so that when the steering wheel state is turning, the vehicle can be immediately controlled simultaneously through the dual-cavity air spring and the damping continuously adjustable shock absorbing system, thereby meeting the needs for lateral control of the vehicle and achieving the optimal control effect.
[0139] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.
[0140] Reference Figure 4 , shows a structural block diagram of a vehicle control device provided by an embodiment of the present invention, wherein the vehicle has a double-cavity air spring, a damping continuously adjustable shock absorption system and a joint controller, and the device may specifically include the following modules:
[0141] The first determination module 401 is used to obtain the current speed of the vehicle before the vehicle enters the turning road, and determine the steering wheel angle required to pass the turning road;
[0142] The second determination module 402 is used to determine that the vehicle is controlled by controlling the dual-chamber air spring and the damping continuously adjustable shock absorption system through the joint controller when the steering wheel state of the vehicle is turning, the current speed of the vehicle reaches the speed threshold, and the steering wheel angle reaches the steering wheel angle threshold.
[0143] In one embodiment, the vehicle speed threshold and the steering wheel angle threshold are determined in the following manner:
[0144] A setting module is used to set the test group for testing vehicle speed and steering wheel angle;
[0145] The test module is used to test the first mode, the second mode and the third mode respectively according to the test group to obtain test results; the first mode is that neither the double-cavity empty spring nor the damping continuously adjustable shock absorbing system controls the vehicle; the second mode is that only the double-cavity empty spring controls the vehicle; the third mode is that the double-cavity empty spring and the damping continuously adjustable shock absorbing system control the vehicle at the same time;
[0146] The third determination module is used to determine the vehicle speed threshold and steering wheel angle threshold of the vehicle according to the test result.
[0147] In one embodiment, the test results include vehicle body roll angle peak values and overshoot values corresponding to the first mode, the second mode, and the third mode respectively under the same test vehicle speed and the same test steering wheel angle state; the third determination module includes:
[0148] A first calculation submodule, configured to determine a difference between the peak values of the vehicle body roll angle in the second mode and the first mode as a steady-state difference of the roll angle;
[0149] A second calculation submodule, configured to determine a difference between the vehicle body roll angle peaks in the second mode and the third mode as a roll angle peak difference;
[0150] A third calculation submodule, configured to determine a difference between the overshoot amounts of the second mode and the third mode as an overshoot difference;
[0151] The first determination submodule is used to determine a vehicle speed threshold and a steering wheel angle threshold of the vehicle according to the roll angle steady-state difference, the roll angle peak difference and the overshoot difference.
[0152] In one embodiment, the first determining submodule includes:
[0153] A first judging unit, configured to judge whether the roll angle steady-state difference is greater than a first preset value;
[0154] a second judgment unit, configured to judge whether the roll angle peak value difference is greater than a second preset value, and whether the overshoot difference is greater than a third preset value, if the roll angle steady-state difference is greater than the first preset value;
[0155] A determination unit is used to determine the corresponding test vehicle speed as the vehicle speed threshold of the vehicle and the test steering wheel angle as the steering wheel angle threshold of the vehicle if the roll angle peak difference is greater than the second preset value and the overshoot difference is greater than the third preset value.
[0156] In one embodiment, the vehicle further has an inertial sensor and a monocular camera; the first determination module 401 includes:
[0157] A first acquisition submodule, configured to acquire the current speed of the vehicle through the inertial sensor;
[0158] The second acquisition submodule is used to acquire road information of the road ahead through the monocular camera; the road information includes: a straight road and / or a turning road;
[0159] The second determination submodule is used to determine the steering wheel angle required to pass the turning road through a preset calculation model if the current road information is a turning road.
[0160] In one embodiment, the second determining submodule includes:
[0161] A calculation unit, which calculates the turning angle of the turning road by using a preset calculation model;
[0162] An acquisition unit, used for acquiring a steering ratio of a steering wheel of a vehicle;
[0163] The conversion unit is used to convert the turning angle according to the steering wheel steering ratio to obtain the steering wheel angle required for passing the turning road.
[0164] In one embodiment, the preset computing model is trained in the following manner:
[0165] An acquisition module is used to acquire a sample data set; the sample data set includes road images with different vehicle viewing angle changes, different road conditions, and different curve rate curves;
[0166] A preprocessing module, used to preprocess the sample data set to obtain a processed data set;
[0167] A fourth determination module, used to determine a composite loss function according to a preset classification loss function and a preset regression loss function;
[0168] A training module, used to train the pre-trained model according to the processed data set to obtain an output result;
[0169] A fifth determination module, used to determine a loss value of the output result according to the output result and the composite loss function;
[0170] An evaluation module, used for performing cyclic training and cyclic verification on the pre-trained model according to the loss value, and performing result evaluation on the result of each verification;
[0171] The sixth determination module is used to determine the corresponding pre-trained model after training as the preset calculation model when the result evaluation meets the preset requirements.
[0172] In this embodiment, the first determination module is used to obtain the current speed of the vehicle before the vehicle enters the turning road, and determine the steering wheel angle required to pass the turning road; the second determination module is used to determine to control the vehicle through the joint controller to control the dual-cavity air spring and the damping continuously adjustable shock absorbing system when the vehicle's steering wheel state is turning, the vehicle's current speed reaches the speed threshold, and the steering wheel angle reaches the steering wheel angle threshold. Therefore, when the steering wheel state is turning, the vehicle can be immediately controlled by the dual-cavity air spring and the damping continuously adjustable shock absorbing system at the same time, meeting the needs of lateral control of the vehicle and achieving the optimal control effect.
[0173] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0174] An embodiment of the present invention further provides a vehicle, comprising:
[0175] It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned vehicle control method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0176] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned vehicle control method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0177] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0178] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0179] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0180] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0182] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.
[0183] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.
[0184] The vehicle control method, the vehicle control device, the vehicle and the computer-readable storage medium provided by the present invention are introduced in detail above. The principles and implementation methods of the present invention are explained in this article by using specific examples. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.
Claims
1. A vehicle control method, characterized in that: The vehicle has a double-chamber air spring, a damping continuously adjustable shock absorption system and a joint controller, and the method includes: Before the vehicle enters a turning road, obtaining the current speed of the vehicle and determining the steering wheel angle required to pass the turning road; If the steering wheel state of the vehicle is turning, and the current speed of the vehicle reaches the speed threshold, and the steering wheel angle reaches the steering wheel angle threshold, it is determined that the vehicle is controlled by controlling the dual-chamber air spring and the damping continuously adjustable shock absorption system through the joint controller.
2. The vehicle control method according to claim 1, characterized in that: The vehicle speed threshold and the steering wheel angle threshold are determined in the following manner: Set up a test group for testing vehicle speed and steering wheel angle; According to the test group, the first mode, the second mode and the third mode are tested respectively to obtain test results; the first mode is that neither the double-cavity empty spring nor the damping continuously adjustable shock absorbing system controls the vehicle; the second mode is that only the double-cavity empty spring controls the vehicle; the third mode is that the double-cavity empty spring and the damping continuously adjustable shock absorbing system control the vehicle at the same time; According to the test result, a vehicle speed threshold and a steering wheel angle threshold of the vehicle are determined.
3. The vehicle control method according to claim 2, characterized in that: The test results include the vehicle body roll angle peak values and overshoot values corresponding to the first mode, the second mode and the third mode respectively under the same test vehicle speed and the same test steering wheel angle state; Determining the vehicle speed threshold and steering wheel angle threshold of the vehicle according to the test result includes: determining a difference between the peak values of the vehicle body roll angle in the second mode and the first mode as a steady-state roll angle difference; determining a difference between the peak values of the vehicle body roll angles in the second mode and the third mode as a roll angle peak value difference; Determine the difference between the overshoot amounts of the second mode and the third mode as an overshoot difference; A vehicle speed threshold and a steering wheel angle threshold of the vehicle are determined according to the roll angle steady-state difference, the roll angle peak difference and the overshoot difference.
4. The vehicle control method according to claim 3, characterized in that: The determining of the vehicle speed threshold and the steering wheel angle threshold of the vehicle according to the roll angle steady-state difference, the roll angle peak difference and the overshoot difference comprises: Determining whether the roll angle steady-state difference is greater than a first preset value; If the roll angle steady-state difference is greater than the first preset value, determining whether the roll angle peak difference is greater than a second preset value, and whether the overshoot difference is greater than a third preset value; If the roll angle peak difference is greater than the second preset value, and the overshoot difference is greater than the third preset value, the corresponding test vehicle speed is determined as the vehicle speed threshold of the vehicle, and the test steering wheel angle is determined as the steering wheel angle threshold of the vehicle.
5. The vehicle control method according to claim 1, characterized in that: The vehicle also has an inertial sensor and a monocular camera; the obtaining of the current speed of the vehicle and determining the steering wheel angle required to pass the turning road include: Acquiring the current speed of the vehicle through the inertial sensor; Obtaining road information of the road ahead through the monocular camera; the road information includes: a straight road and / or a turning road; If the current road information is a curved road, the steering wheel angle required to pass the curved road is determined by a preset calculation model.
6. The vehicle control method according to claim 5, characterized in that: The determining the steering wheel angle required for passing the turning road by using a preset calculation model includes: Calculating the turning angle of the turning road by using a preset calculation model; Get the steering wheel ratio of the vehicle; The turning angle is converted according to the steering wheel steering ratio to obtain the steering wheel angle required to pass the turning road.
7. The vehicle control method according to claim 6, characterized in that: The preset calculation model is trained in the following way: Collecting a sample data set; the sample data set includes road images with different vehicle viewing angle changes, different road conditions, and different curve rate curves; Preprocessing the sample data set to obtain a processed data set; Determine a composite loss function according to a preset classification loss function and a preset regression loss function; According to the processed data set, the pre-trained model is trained to obtain an output result; Determining a loss value of the output result according to the output result and the composite loss function; Performing cyclic training and cyclic verification on the pre-trained model according to the loss value, and evaluating the result of each verification; When the result evaluation meets the preset requirements, the corresponding pre-trained model after training is determined as the preset calculation model.
8. A vehicle control device, characterized in that: The vehicle has a double-chamber air spring, a damping continuously adjustable shock absorption system and a joint controller, and the device includes: A first determination module is used to obtain the current speed of the vehicle before the vehicle enters the turning road, and determine the steering wheel angle required to pass the turning road; The second determination module is used to determine that the vehicle is controlled by controlling the dual-chamber air spring and the damping continuously adjustable shock absorption system through the joint controller when the steering wheel state of the vehicle is turning, the current speed of the vehicle reaches the speed threshold, and the steering wheel angle reaches the steering wheel angle threshold.
9. A vehicle, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the vehicle control method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the vehicle control method according to any one of claims 1 to 7 are implemented.
