Vehicle control method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides a vehicle control method and device, electronic equipment and a computer readable storage medium, and is applied to a vehicle with a steering system, and the steering system comprises a yaw velocity sensor and a steering wheel angle sensor; the method comprises the steps that in the running process of a vehicle, an image of a lane line in front of the vehicle, the yaw velocity sensed by a yaw velocity sensor and a steering wheel rotation angle sensed by a steering wheel rotation angle sensor are obtained; detecting whether a steering system needs to be calibrated or not according to the lane line image, the yaw velocity and the steering wheel angle; under the condition that it is detected that the steering system needs to be calibrated, the numerical value of the yaw velocity sensor is controlled to be reset; and calculating a correction value according to the steering wheel angle and the yaw velocity, and correcting the steering wheel angle sensor according to the correction value. The calibration cost of the steering system can be reduced while the control precision of the vehicle is improved.

Description

Technical Field

[0001] The present application relates to the fields of assisted driving and power steering, and in particular to a vehicle control method, device, electronic device and computer-readable storage medium. Background Art

[0002] With the development of new energy technology and intelligent driving technology, steer-by-wire systems are being used more and more widely in the commercial vehicle field, especially hybrid power steering systems.

[0003] In related technologies, due to the unique spatial layout of hybrid vehicle steering systems and the diverse operating conditions, there may be a significant deviation (>±5°) between the steering wheel zero position and the steering system zero position when the vehicle is traveling in a straight line. The main reasons for this deviation include: first, the front axle wheel center height varies under different vehicle load conditions, which in turn causes hard point interference; second, the large number of steering system components, and the wear and tear after long-term operation may cause the cumulative tolerance of the dimensional chain to gradually increase; third, a variety of factors such as the rear axle thrust angle, vehicle overload, crosswind, road inclination, uneven tire wear, and tire pressure differences can affect the accuracy of the steering system zero position.

[0004] The above-mentioned causes are difficult to avoid during vehicle operation. Therefore, in order to reduce the impact of zero-position deviation on the control accuracy and reliability of the steering system, there is an urgent need for a steering system zero-position intelligent calibration method and system that can adapt to diverse working conditions and has dynamic adaptive capabilities. Summary of the Invention

[0005] In view of this, the present application provides a vehicle control method, device, electronic device and computer-readable storage medium, which can improve the control accuracy of the vehicle while reducing the calibration cost of the steering system.

[0006] A first aspect of an embodiment of the present application provides a vehicle control method, which is applied to a vehicle with a steering system, the steering system including a yaw angular velocity sensor and a steering wheel angle sensor; the vehicle control method includes: during the driving of the vehicle, obtaining a lane line image in front of the vehicle, the yaw angular velocity sensed by the yaw angular velocity sensor, and the steering wheel angle sensed by the steering wheel angle sensor; detecting whether the steering system needs to be calibrated based on the lane line image, the yaw angular velocity and the steering wheel angle; if it is detected that the steering system needs to be calibrated, controlling the value of the yaw angular velocity sensor to be reset; calculating a correction value based on the steering wheel angle and the yaw angular velocity, and correcting the steering wheel angle sensor based on the correction value.

[0007] In one possible implementation, the steering system also includes a wheel speed sensor; the method also includes: obtaining the wheel speed sensed by the wheel speed sensor; detecting whether the steering system needs to be calibrated based on the lane line image, the yaw angular velocity and the steering wheel angle includes: detecting whether the steering system needs to be calibrated based on the lane line image, the yaw angular velocity, the steering wheel angle and the wheel speed; calculating the correction value based on the steering wheel angle and the yaw angular velocity includes: calculating the correction value based on the steering wheel angle, the yaw angular velocity and the wheel speed.

[0008] In one possible implementation, detecting whether the steering system needs to be calibrated based on the lane line image, the yaw angular velocity, the steering wheel angle, and the wheel speed includes: performing image analysis on the lane line image to obtain a lateral offset distance of the vehicle relative to the lane line; calculating a time-domain mean of the lateral displacement of the vehicle within a preset time period based on the lateral offset distance and the steering wheel angle; calculating a time-domain mean of the longitudinal velocity of the vehicle within the preset time period based on the wheel speed; calculating a time-domain mean of the yaw angular velocity of the vehicle within the preset time period based on the yaw angular velocity; calculating a time-domain mean of the wheel speed difference of the vehicle within the preset time period based on the wheel speed; and detecting whether the steering system needs to be calibrated based on the time-domain mean of the lateral displacement, the time-domain mean of the longitudinal velocity, the time-domain mean of the yaw angular velocity, and the time-domain mean of the wheel speed difference.

[0009] In one possible implementation, detecting whether the steering system needs to be calibrated based on the time-domain mean of the lateral displacement, the time-domain mean of the longitudinal velocity, the time-domain mean of the yaw angular velocity, and the time-domain mean of the wheel speed difference includes: inputting the time-domain mean of the lateral displacement, the time-domain mean of the longitudinal velocity, the time-domain mean of the yaw angular velocity, and the time-domain mean of the wheel speed difference into a first network model, and detecting whether the vehicle needs to be calibrated based on an output result of the first network model; wherein, the first network model is trained based on a first loss function, and the first loss function is determined based on the mean square error between the output result of the first network model and the true result.

[0010] In one possible implementation, performing image analysis on the lane line image to obtain the lateral offset distance of the vehicle relative to the lane line includes: inputting the lane line image into a second network model, and using the output result of the second network model as the lateral offset distance; wherein, the second network model is trained according to a second loss function, and the second loss function is determined according to the classification loss for measuring the accuracy of lane category prediction, the structural loss that integrates the similarity loss and the shape constraint loss, and the segmentation loss for measuring the accuracy of the segmentation result.

[0011] In one possible implementation, after detecting that the steering system needs to be calibrated based on the time-domain mean value of the lateral displacement, the time-domain mean value of the longitudinal velocity, the time-domain mean value of the yaw angular velocity, and the time-domain mean value of the wheel speed difference, it also includes: calculating the longitudinal displacement of the vehicle in the vehicle driving direction within the preset time period based on the wheel speed; detecting whether the vehicle is in a stable driving state based on the time-domain mean value of the lateral displacement, the longitudinal displacement, the time-domain mean value of the yaw angular velocity, and the time-domain mean value of the wheel speed difference; and controlling the numerical reset of the yaw angular velocity sensor when detecting that the steering system needs to be calibrated, including: controlling the numerical reset of the yaw angular velocity sensor when detecting that the steering system needs to be calibrated and the vehicle is in a stable driving state.

[0012] In one possible implementation, detecting whether the vehicle is in a stable driving state based on the time-domain mean value of the lateral displacement, the longitudinal displacement, the time-domain mean value of the yaw angular velocity, and the time-domain mean value of the wheel speed difference includes: if it is detected that the time-domain mean value of the lateral displacement is less than or equal to a first threshold, and the longitudinal displacement is greater than or equal to a second threshold, and the time-domain mean value of the yaw angular velocity is less than or equal to a third threshold, and the time-domain mean value of the wheel speed difference is less than or equal to a fourth threshold, detecting that the vehicle is in a stable driving state; otherwise, detecting that the vehicle is in an unstable driving state.

[0013] In a second aspect, an embodiment of the present application further provides a vehicle control device, which is applied to a vehicle having a steering system, wherein the steering system includes a yaw angular velocity sensor and a steering wheel angle sensor; the vehicle control device includes: an acquisition module, a detection module, a first control module and a second control module; the acquisition module is used to acquire the lane line image in front of the vehicle, the yaw angular velocity sensed by the yaw angular velocity sensor, and the steering wheel angle sensed by the steering wheel angle sensor during the driving process of the vehicle; the detection module is used to detect whether the steering system needs to be calibrated based on the lane line image, the yaw angular velocity and the steering wheel angle; when it is detected that the vehicle is currently in an unstable driving state, the first control module is used to control the numerical reset of the yaw angular velocity sensor; the second control module is used to calculate a correction value based on the yaw angular velocity and the steering wheel angle, and correct the steering wheel angle sensor based on the correction value.

[0014] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a processor and a memory, wherein the memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes the vehicle control method described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the vehicle control method as described in the first aspect.

[0016] Compared to related technologies, the present application has at least the following advantages: By detecting whether the steering system requires calibration based on lane line images, yaw rate, and steering wheel angle, the accuracy of detecting whether the vehicle is lateral deviation can be determined based on the lane line images, and whether the vehicle is oversteering or understeering can be determined based on the yaw rate and steering wheel angle. When the need for steering system calibration is detected, the yaw rate sensor is reset, and a correction value is calculated based on the steering wheel angle and yaw rate. This correction is then applied to the steering wheel angle sensor, ensuring the accuracy of steering system calibration. This results in higher control accuracy for the vehicle after the steering system calibration.

[0017] In addition, the above-mentioned vehicle control method, vehicle control device, electronic device and computer-readable storage medium can realize automatic calibration of the steering system without manual intervention, thereby reducing the cost of steering system calibration. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1A flowchart of the steps of a vehicle control method provided in one embodiment of the present application.

[0019] Figure 2 A schematic diagram of the network architecture of the second network model provided in one embodiment of the present application.

[0020] Figure 3 A schematic diagram of the overall structure of a vehicle control system provided in one embodiment of the present application.

[0021] Figure 4 Another step flow chart of a vehicle control method provided in one embodiment of the present application.

[0022] Figure 5 A schematic diagram of the execution logic of a vehicle control method provided in one embodiment of the present application.

[0023] Figure 6 This is a functional module diagram of a vehicle control device provided in one embodiment of the present application.

[0024] Figure 7 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to more clearly understand the above-mentioned objectives, features and advantages of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features therein can be combined with each other in the absence of conflict.

[0026] In the following description, many specific details are set forth to facilitate a full understanding of the present application. The described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0027] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application pertains. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0028] It should be further noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0029] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A alone, A and B together, and B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," and so on (if any) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or precedence.

[0030] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0031] To facilitate understanding, some illustrations of concepts related to the embodiments of the present application are given for reference.

[0032] The yaw rate sensor (EBS) records the vehicle's angular velocity (yaw rate) around its longitudinal axis in real time, providing critical data for the EBS system to determine whether the vehicle is oversteering or understeering. If the actual yaw rate deviates significantly from the expected value, the system triggers the stability control system to intervene.

[0033] Steering wheel angle sensor (SAS): A device used to accurately measure the rotation angle and steering direction of a car's steering wheel. It is a non-contact multi-turn absolute angle measurement sensor.

[0034] Wheel speed sensor: monitors wheel speed in real time, providing data support for the anti-lock braking system (ABS), electronic body stability system (ESP), traction control system (TCS), etc., to ensure vehicle stability during braking, steering or driving on slippery roads.

[0035] Please refer to Figure 1 , Figure 1 This is a flowchart of the steps in one embodiment of the vehicle control method of the present application. Depending on different needs, the order of the steps in this flowchart may be changed, and some steps may be omitted. The vehicle control method of the present application can be applied to a vehicle having a steering system including a yaw rate sensor and a steering wheel angle sensor, but is not limited thereto and is not limited to this embodiment of the present application.

[0036] The specific process of this embodiment is as follows Figure 1 As shown, the following steps are included: S101 , during a vehicle's travel, acquiring a lane line image in front of the vehicle, a yaw rate sensed by a yaw rate sensor, and a steering wheel angle sensed by a steering wheel angle sensor.

[0037] In some embodiments, a high-resolution camera is set behind the front windshield of the cockpit and its installation position is calibrated to ensure that lane line images can be captured clearly and accurately.

[0038] Specifically, the high-resolution camera of this embodiment is configured with a resolution of 1920*1070 and a dynamic range of 120dB, and is transmitted via the RTSP protocol, taking into account both image quality and real-time transmission, ensuring that the transmission delay is ≤50ms.

[0039] In some embodiments, a yaw rate sensor and a steering wheel angle sensor are arranged on the chassis of the vehicle. Specifically, a CAN bus network is constructed to encapsulate and transmit data from the yaw rate sensor and the steering wheel angle sensor.

[0040] S102: Detect whether the steering system needs to be calibrated based on the lane line image, yaw angular velocity, and steering wheel angle.

[0041] In some embodiments, image analysis is performed on the lane line image to obtain a lateral offset distance of the vehicle relative to the lane line.

[0042] In some embodiments, the lane line image is input into a second network model, and the output result of the second network model is used as the lateral offset distance; wherein, the second network model is trained according to a second loss function, and the second loss function is determined according to the classification loss for measuring the accuracy of lane category prediction, the structural loss that integrates similarity loss and shape constraint loss, and the segmentation loss for measuring the accuracy of the segmentation result.

[0043] For ease of understanding, the following Figure 2 How to perform image analysis on lane line images in this embodiment is specifically described: Please refer to Figure 2 , which is a schematic diagram of the network architecture of the second network model provided in an embodiment of the present application.

[0044] The ResNet-34 network is used as the backbone of the second network model, and lane detection is redefined as a row selection method based on global image features. The input image is divided into row anchors and grids, avoiding intensive processing of each pixel. While not affecting the detection effect, the demand for computing resources is greatly reduced, achieving low computing cost and high real-time performance.

[0045] We construct the L_cls classification loss to measure the accuracy of lane category prediction. We introduce the L_str structural loss to leverage lane information priors and fuse similarity loss and shape constraint loss. To help the model train better, we introduce an auxiliary branch and its corresponding segmentation loss, L_seg, to measure the accuracy of the segmentation results. In summary, the overall second loss function is expressed as follows: L_total=L_cls+[αL]_str+[βL]_seg; where α and β are the corresponding weights respectively.

[0046] During the training process, a data set under real road conditions was collected, with a data volume of more than 36,000 images. Data enhancement operations such as rotation, flipping, scaling, and adding noise were performed to expand the data set size and improve the generalization ability of the model.

[0047] The stochastic gradient descent optimization algorithm is used. After 50 cycles of training, the parameters of the second network model are continuously adjusted to minimize the loss function of the second network model on the validation set.

[0048] During inference, the image captured by the camera is first preprocessed and the image size is adjusted to the size required by the second network model input. The preprocessed image is then input into the trained second network model. After network propagation calculation, the position information of the lane line is obtained, and then the lateral offset distance of the vehicle relative to the lane line is calculated using a geometric algorithm with an accuracy of up to 4 cm.

[0049] In some embodiments, the time-domain mean value of the vehicle's lateral displacement within a preset time period is calculated based on the lateral offset distance and the steering wheel angle; the time-domain mean value of the vehicle's longitudinal velocity within a preset time period is calculated based on the wheel speed; the time-domain mean value of the vehicle's yaw angular velocity within a preset time period is calculated based on the yaw angular velocity; the time-domain mean value of the wheel speed difference within a preset time period is calculated based on the wheel speed; and whether the steering system needs to be calibrated is detected based on the time-domain mean value of the lateral displacement, the time-domain mean value of the longitudinal velocity, the time-domain mean value of the yaw angular velocity, and the time-domain mean value of the wheel speed difference.

[0050] It is understandable that this embodiment does not impose any specific limitation on the size of the preset duration, and it can be set according to actual needs.

[0051] Specifically, after obtaining the lateral offset distance, yaw angular velocity, steering wheel angle, and wheel speed, a two-level data fusion architecture is adopted. The Kalman filter algorithm is applied in the primary processing stage to effectively remove noise interference in the above data; the secondary processing constructs a time window mean statistical model, and the mean within a certain time window is taken as the processed result and passed to the decision network, that is, the time domain mean of the lateral displacement, the time domain mean of the longitudinal velocity, the time domain mean of the yaw angular velocity, and the time domain mean of the wheel speed difference.

[0052] It can be understood that, in this embodiment, the longitudinal direction represents the driving direction of the vehicle, and the transverse direction is a direction perpendicular to the driving direction.

[0053] In some embodiments, the time-domain mean of the lateral displacement, the time-domain mean of the longitudinal velocity, the time-domain mean of the yaw angular velocity, and the time-domain mean of the wheel speed difference are input into the first network model, and whether the vehicle needs calibration is detected based on the output result of the first network model; wherein, the first network model is trained based on the first loss function, and the first loss function is determined based on the mean square error between the output result of the first network model and the true result.

[0054] Specifically, the first network model of this embodiment is a BP neural network. The time-domain mean of lateral displacement, longitudinal velocity, yaw rate, and wheel speed difference serves as the input to the first network model. The hidden layer uses a ReLU activation function to introduce nonlinear factors and enhance the network's expressiveness. The output layer uses a Sigmoid function to map the output to the [0, 1] interval, representing the probability of executing the calibration system.

[0055] A real-world vehicle experimental dataset was collected and trained using a backpropagation algorithm to train a BP neural network. The error between the predicted results and the true labels was calculated using a stochastic gradient descent algorithm, with the loss function defined as the mean squared error. After training on 5,000 sets of real-world vehicle data, the model achieved the expected performance. A threshold of τ = 0.68 was used to achieve the optimal F1-score balance, achieving an accuracy of 94.3% on the test set.

[0056] The time-domain mean of lateral displacement, longitudinal velocity, yaw rate, and wheel speed difference is input into the trained BP neural network, and the output is calculated through forward propagation. If the output is greater than the set threshold τ, the steering system is determined to require calibration. If it is less than or equal to the threshold τ, the steering system is determined not to require calibration.

[0057] Please refer to Figure 3 , is a schematic diagram of the overall structure of the vehicle control system provided in an embodiment of the present application.

[0058] Figure 3 The vehicle control system shown uses an embedded development platform as the computing hub to achieve real-time computing with deep coupling of software and hardware. At the sensor hardware level, cameras are deployed in the perception domain, and yaw rate sensors, steering wheel angle sensors, and speed sensors are deployed in the chassis domain. At the software level, a layered architecture integrating the driver layer and the middleware layer is built, and a ROS2-based middleware system is used to build a distributed communication framework to achieve integrated communication between software and hardware.

[0059] Specifically, a collaborative hardware and software environment was built based on the Ubuntu 20.04 LTS operating system. At the driver layer, the GStreamer framework was integrated to handle the visual interface, the SocketCAN driver to manage the CAN bus, and ROS2 components to achieve sensor fusion. At the middleware layer, a ROS2 node network was constructed, a zero-copy communication mechanism was established, and customized message types were designed.

[0060] S103 : When it is detected that the steering system needs to be calibrated, the value of the yaw rate sensor is controlled to be reset.

[0061] In some embodiments, precise pulse signal control or software instruction reset is used to ensure the accuracy and timeliness of the reset operation.

[0062] S104 , calculating a correction value according to the steering wheel angle and the yaw angular velocity, and correcting the steering wheel angle sensor according to the correction value.

[0063] In some embodiments, the average of all sampled values ​​of the steering wheel angle sensor within a period of time is calculated (for example, the period of time is 10 seconds, and the period of the steering wheel angle sensor message is 50 ms, so the average is calculated from a total of 200 steering wheel angles within these 10 seconds), and then based on a preset calibration algorithm, a correction value is calculated according to the average, yaw angular velocity and wheel speed.

[0064] Compared to related technologies, the embodiments of the present application have at least the following advantages: by detecting whether the steering system needs to be calibrated based on the lane line image, yaw angular velocity, and steering wheel angle, the accuracy of detecting whether the steering system needs to be calibrated is improved because the lane line image can be used to determine whether the vehicle has deviated laterally, and the yaw angular velocity and steering wheel angle can be used to determine whether the vehicle is oversteering or understeering. When it is detected that the steering system needs to be calibrated, on the one hand, the numerical reset of the yaw angular velocity sensor is controlled, and on the other hand, a correction value is calculated based on the steering wheel angle and yaw angular velocity, and then the steering wheel angle sensor is corrected. This ensures the accuracy of the steering system calibration, thereby improving the control accuracy of the vehicle after the steering system is calibrated. In addition, the above-mentioned vehicle control method can realize automatic calibration of the steering system without manual intervention, thereby reducing the cost of steering system calibration.

[0065] Please refer to Figure 4 , Figure 4 This is a flowchart of the steps of one embodiment of the vehicle control method of the present application. Depending on different needs, the order of the steps in this flowchart may be changed, and some steps may be omitted. This vehicle control method can be applied to the aforementioned vehicle control device, but is not limited thereto, and this embodiment of the present application is not limited thereto.

[0066] This embodiment further improves upon the previous embodiment. The main improvement is that, after determining that the steering system requires calibration, this embodiment also detects whether the vehicle is in a stable driving state based on the time-domain mean of the lateral displacement, longitudinal displacement, time-domain mean of the yaw rate, and time-domain mean of the wheel speed difference. Steering system calibration is then performed only after the vehicle is in a stable driving state. This approach further improves the accuracy of steering system calibration, thereby further enhancing vehicle control precision.

[0067] The specific process of this embodiment is as follows Figure 4 As shown, the following steps are included: S401 , during the driving process of the vehicle, acquiring a lane line image in front of the vehicle, a yaw rate sensed by a yaw rate sensor, a steering wheel angle sensed by a steering wheel angle sensor, and a wheel speed sensed by a wheel speed sensor.

[0068] S402 : Detect whether the steering system needs to be calibrated based on the lane line image, yaw angular velocity, steering wheel angle, and wheel speed.

[0069] S401 and S402 of this embodiment are similar to S101 and S102 of the aforementioned embodiment, and are not described again here to avoid repetition.

[0070] S403: When it is detected that the steering system needs to be calibrated, the longitudinal displacement of the vehicle in the vehicle driving direction within a preset time period is calculated according to the wheel speed.

[0071] S404 , detecting whether the vehicle is in a stable driving state based on the time-domain mean value of the lateral displacement, the longitudinal displacement, the time-domain mean value of the yaw angular velocity, and the time-domain mean value of the wheel speed difference.

[0072] In some embodiments, whether the vehicle is in a stable driving state is detected according to the following method: when it is detected that the time-domain mean of the lateral displacement is less than or equal to the first threshold, and the longitudinal displacement is greater than or equal to the second threshold, and the time-domain mean of the yaw angular velocity is less than or equal to the third threshold, and the time-domain mean of the wheel speed difference is less than or equal to the fourth threshold, the vehicle is detected to be in a stable driving state; otherwise, the vehicle is detected to be in an unstable driving state.

[0073] This embodiment does not specifically limit the values ​​of the first threshold, the second threshold, the third threshold, and the fourth threshold, and they can be set according to actual needs. For example, in this embodiment, the first threshold can be set to 2 km, the second threshold can be set to 6 cm, the third threshold can be set to 0.01 rad / s, and the fourth threshold can be set to 0.24 m / s.

[0074] S405 : When it is detected that the steering system needs to be calibrated and the vehicle is in a stable driving state, the value of the yaw rate sensor is controlled to be reset.

[0075] S406 , calculating a correction value according to the steering wheel angle, the yaw angular velocity, and the wheel speed, and correcting the steering wheel angle sensor according to the correction value.

[0076] For ease of understanding, the following Figure 5 How to implement zero position calibration of the steering system in this embodiment is described in detail: 1. Use the SAS steering angle sensor to sense the steering wheel's steering angle As in real time and calculate the time domain average of the steering angle within a preset time period. The left and right wheel speed sensors sense the vehicle's wheel speed N in real time, and calculate the vehicle's longitudinal displacement within a preset time period based on the wheel speed N. , and then calculate the time domain mean of the wheel speed difference of the vehicle within the preset time length according to the wheel speed N ; Use the front-view camera to capture the lane line image, and perform image analysis on the lane line image to obtain the lateral displacement of the vehicle ; Real-time sensing of the vehicle's yaw rate through EBS and , and according to the yaw angular velocity Calculate the time domain average of the vehicle's yaw rate within a preset time period , yaw angular velocity Calculate the time domain average of the vehicle's yaw rate within a preset time period , according to the time domain mean of yaw angular velocity and the time domain mean of the yaw rate Get the corrected yaw rate .

[0077] 2. Determine longitudinal displacement Is it greater than 2KM, and the time domain mean of wheel speed difference and yaw rate Is it approaching 0? Greater than 2KM, and the time domain mean of wheel speed difference and yaw rate When both tend to 0, calculate the correction value.

[0078] 3. Check whether the vehicle is stationary, that is, whether the speed is close to 0 and the steering wheel angle is less than the preset , It can be set according to actual needs. For example, It can be set to 15°. When the vehicle is stationary, reset the EBS and correct the SAS steering angle sensor according to the correction value.

[0079] Compared to related technologies, the embodiments of the present application have at least the following advantages: by detecting whether the steering system needs to be calibrated based on the lane line image, yaw angular velocity, and steering wheel angle, the accuracy of detecting whether the steering system needs to be calibrated is improved because the lane line image can be used to determine whether the vehicle has deviated laterally, and the yaw angular velocity and steering wheel angle can be used to determine whether the vehicle is oversteering or understeering. When it is detected that the steering system needs to be calibrated, on the one hand, the numerical reset of the yaw angular velocity sensor is controlled, and on the other hand, a correction value is calculated based on the steering wheel angle and yaw angular velocity, and then the steering wheel angle sensor is corrected. This ensures the accuracy of the steering system calibration, thereby improving the control accuracy of the vehicle after the steering system is calibrated. In addition, the above-mentioned vehicle control method can realize automatic calibration of the steering system without manual intervention, thereby reducing the cost of steering system calibration.

[0080] Based on the same concept as the vehicle control method in the above-mentioned embodiment, the present application also provides a vehicle control device that can be used to execute the above-mentioned vehicle control method. For ease of explanation, the structural diagram of the vehicle control device embodiment only shows the parts relevant to the embodiment of the present application. Those skilled in the art will understand that the illustrated structure does not constitute a limitation of the device, and the device may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0081] like Figure 6 As shown, the vehicle control device 60 includes an acquisition module 601, a detection module 602, a first control module 603, and a second control module 604. In some embodiments, these modules may be programmable software instructions stored in a memory and executed by a processor. It is understood that in other embodiments, these modules may also be program instructions or firmware embedded in the processor.

[0082] An acquisition module 601 is configured to acquire, during the driving process of the vehicle, an image of a lane line in front of the vehicle, a yaw rate sensed by the yaw rate sensor, and a steering wheel angle sensed by the steering wheel angle sensor; A detection module 602 is configured to detect whether the steering system needs to be calibrated based on the lane line image, the yaw angular velocity, and the steering wheel angle; When it is detected that the vehicle is currently in an unstable driving state, the first control module 603 is used to control the value of the yaw rate sensor to be reset; The second control module 604 is configured to calculate a correction value according to the steering wheel angle and the yaw angular velocity, and correct the steering wheel angle sensor according to the correction value.

[0083] Please refer to 7, Figure 7 This is a schematic diagram of an embodiment of an electronic device of the present application.

[0084] In some embodiments, the processor 701 may be a central processing unit (CPU), a microprocessor, or other data processing chip, configured to execute program codes or process data stored in the memory 702 , such as the magnetic resonance image optimization method of the present invention.

[0085] In some embodiments, processor 701 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, processor 701 may be local or remote. In some embodiments, processor 701 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an on-premises cloud, a multi-cloud, or any combination thereof.

[0086] In some embodiments, the memory 702 may be an internal storage unit of the electronic device 700, such as a hard disk or memory of the electronic device 700. In other embodiments, the memory 702 may also be an external storage device of the electronic device 700, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 700.

[0087] Furthermore, the memory 702 may include both an internal storage unit of the electronic device 700 and an external storage device. The memory 702 is used to store application software installed in the electronic device 700 and various data.

[0088] In some embodiments, display 703 can be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 703 is used to display information on electronic device 700 and to display a visual user interface. Components 701-703 of electronic device 700 communicate with each other via a system bus.

[0089] In one embodiment, when the processor 701 executes the vehicle control program in the memory 702, the following steps may be implemented: Acquire a lane line image in front of the vehicle, a yaw rate sensed by a yaw rate sensor, and a steering wheel angle sensed by a steering wheel angle sensor; Detect whether the steering system needs calibration based on lane line images, yaw rate, and steering wheel angle; When it is detected that the steering system needs to be calibrated, the value of the yaw rate sensor is reset; A correction value is calculated based on the steering wheel angle and the yaw rate, and the steering wheel angle sensor is corrected based on the correction value.

[0090] It should be understood that, when the processor 701 executes the vehicle control program in the memory 702 , in addition to the above functions, it can also implement other functions. For details, please refer to the description of the corresponding method embodiment above.

[0091] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 700 mentioned. The electronic device 700 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, or the like. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices equipped with IOS, Android, Microsoft, or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 700 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0092] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions in the vehicle control method provided by the above-mentioned method embodiments.

[0093] Those skilled in the art will appreciate that all or part of the process flow of the above-described method embodiment can be implemented by instructing related hardware (such as a processor, controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0094] The above is a detailed introduction to the vehicle control method, device, electronic device and computer-readable storage medium provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle control method, characterized in that: Applicable to a vehicle having a steering system, the steering system including a yaw rate sensor and a steering wheel angle sensor; The vehicle control method includes: During the driving process of the vehicle, an image of a lane line in front of the vehicle, a yaw angular velocity sensed by the yaw angular velocity sensor, and a steering wheel angle sensed by the steering wheel angle sensor are acquired; detecting whether the steering system needs to be calibrated according to the lane line image, the yaw angular velocity, and the steering wheel angle; When it is detected that the steering system needs to be calibrated, controlling the value of the yaw rate sensor to be reset; A correction value is calculated according to the steering wheel angle and the yaw angular velocity, and the steering wheel angle sensor is corrected according to the correction value.

2. The vehicle control method according to claim 1, characterized in that: The steering system further includes a wheel speed sensor; and the method further includes: Obtaining the wheel speed sensed by the wheel speed sensor; The detecting whether the steering system needs to be calibrated according to the lane line image, the yaw angular velocity, and the steering wheel angle includes: detecting whether the steering system needs to be calibrated according to the lane line image, the yaw angular velocity, the steering wheel angle, and the wheel speed; The calculating the correction value according to the steering wheel angle and the yaw angular velocity includes: The correction value is calculated based on the steering wheel angle, the yaw rate, and the wheel speed.

3. The vehicle control method according to claim 2, characterized in that: The detecting whether the steering system needs to be calibrated according to the lane line image, the yaw angular velocity, the steering wheel angle, and the wheel speed includes: Performing image analysis on the lane line image to obtain a lateral offset distance of the vehicle relative to the lane line; Calculating a time-domain mean of the lateral displacement of the vehicle within a preset time period according to the lateral offset distance and the steering wheel angle; Calculating a time-domain mean longitudinal velocity of the vehicle within the preset time period according to the wheel speed; Calculating a time-domain average of the yaw rate of the vehicle within the preset time period according to the yaw rate; Calculating a time domain mean of the wheel speed difference of the vehicle within the preset time period according to the wheel speed; Whether the steering system needs to be calibrated is detected according to the time-domain mean value of the lateral displacement, the time-domain mean value of the longitudinal velocity, the time-domain mean value of the yaw angular velocity, and the time-domain mean value of the wheel speed difference.

4. The vehicle control method according to claim 3, characterized in that: The detecting whether the steering system needs to be calibrated according to the time-domain mean value of the lateral displacement, the time-domain mean value of the longitudinal velocity, the time-domain mean value of the yaw angular velocity, and the time-domain mean value of the wheel speed difference includes: inputting the time-domain mean of the lateral displacement, the time-domain mean of the longitudinal velocity, the time-domain mean of the yaw angular velocity, and the time-domain mean of the wheel speed difference into a first network model, and detecting whether the vehicle needs calibration based on an output result of the first network model; The first network model is trained according to a first loss function, and the first loss function is determined according to the mean square error between the output result of the first network model and the true result.

5. The vehicle control method according to claim 3, characterized in that: The performing image analysis on the lane line image to obtain a lateral offset distance of the vehicle relative to the lane line includes: Inputting the lane line image into a second network model, and using an output result of the second network model as the lateral offset distance; The second network model is trained according to a second loss function, and the second loss function is determined according to a classification loss for measuring the accuracy of lane category prediction, a structural loss that integrates similarity loss and shape constraint loss, and a segmentation loss for measuring the accuracy of segmentation results.

6. The vehicle control method according to claim 3, characterized in that: After detecting that the steering system needs to be calibrated according to the time-domain mean value of the lateral displacement, the time-domain mean value of the longitudinal velocity, the time-domain mean value of the yaw angular velocity, and the time-domain mean value of the wheel speed difference, the method further includes: calculating the longitudinal displacement of the vehicle in the vehicle travel direction within the preset time period according to the wheel speed; detecting whether the vehicle is in a stable driving state according to the time-domain mean value of the lateral displacement, the longitudinal displacement, the time-domain mean value of the yaw angular velocity, and the time-domain mean value of the wheel speed difference; When it is detected that the steering system needs to be calibrated, controlling the value of the yaw rate sensor to be reset includes: When it is detected that the steering system needs to be calibrated and the vehicle is in a stable driving state, the value of the yaw angular velocity sensor is controlled to be reset.

7. The vehicle control method according to claim 6, characterized in that: The detecting whether the vehicle is in a stable driving state according to the time-domain mean value of the lateral displacement, the longitudinal displacement, the time-domain mean value of the yaw angular velocity, and the time-domain mean value of the wheel speed difference includes: When it is detected that the time-domain mean value of the lateral displacement is less than or equal to a first threshold, the longitudinal displacement is greater than or equal to a second threshold, the time-domain mean value of the yaw angular velocity is less than or equal to a third threshold, and the time-domain mean value of the wheel speed difference is less than or equal to a fourth threshold, it is detected that the vehicle is in a stable driving state; otherwise, it is detected that the vehicle is in an unstable driving state.

8. A vehicle control device, characterized in that: Applicable to a vehicle having a steering system, the steering system including a yaw rate sensor and a steering wheel angle sensor; The vehicle control device includes: an acquisition module, a detection module, a first control module and a second control module; The acquisition module is used to acquire the lane line image in front of the vehicle, the yaw angular velocity sensed by the yaw angular velocity sensor, and the steering wheel angle sensed by the steering wheel angle sensor during the driving process of the vehicle; The detection module is used to detect whether the steering system needs to be calibrated according to the lane line image, the yaw angular velocity and the steering wheel angle; When it is detected that the vehicle is currently in an unstable driving state, the first control module is used to control the value reset of the yaw rate sensor; The second control module is configured to calculate a correction value according to the steering wheel angle and the yaw angular velocity, and correct the steering wheel angle sensor according to the correction value.

9. An electronic device comprising a processor and a memory, characterized in that: The memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the electronic device executes the vehicle control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which, when executed on an electronic device, cause the electronic device to execute the vehicle control method according to any one of claims 1 to 7 .

Images