Drive-by-wire steering wheel control method and device and vehicle

Abstract

The invention relates to the technical field of auxiliary driving, provides a drive-by-wire steering wheel control method and device and a vehicle, and can improve the recognition accuracy of misoperation of a drive-by-wire steering wheel. Rotation-related data of a drive-by-wire steering wheel of a vehicle is obtained in real time, and when it is judged that a first abnormal rotation event occurs in the drive-by-wire steering wheel according to the rotation-related data, driving state-related data of a driver and vehicle surrounding environment-related data are obtained; inputting the rotation related data, the driving state related data and the vehicle surrounding environment related data into a pre-constructed steering wheel misoperation identification model; and when it is determined that the drive-by-wire steering wheel is wrongly operated according to an output result of the steering wheel misoperation identification model, a rotation control strategy for the drive-by-wire steering wheel is determined according to the vehicle surrounding environment safety condition determined by the vehicle surrounding environment related data.

Description

Technical Field

[0001] The present application relates to the field of assisted driving technology, and in particular to a wire-controlled steering wheel control method, device, vehicle, storage medium, and computer program product. Background Art

[0002] A steer-by-wire system is a vehicle steering system that transmits steering commands via electronic signals, rather than relying on traditional mechanical connections (such as steering columns or racks and pinions). While vehicles can be equipped with steer-by-wire systems, drivers may make mistakes while driving, such as misoperating the steer-by-wire system. Misoperation of the steer-by-wire system is a dangerous behavior, potentially leading to a range of hazards depending on the timing, force, and circumstances of the operation.

[0003] In traditional assisted driving technology for misoperation of the wire-controlled steering wheel, the accuracy of misoperation recognition is low due to the limited data used for analysis. Summary of the Invention

[0004] Based on this, it is necessary to provide a wire-controlled steering wheel control method, device, vehicle, storage medium and computer program product to address the above technical problems.

[0005] The present application provides a method for controlling a wire-controlled steering wheel, the method comprising:

[0006] acquiring, in real time, rotation data related to a by-wire steering wheel of the vehicle, and acquiring, when it is determined based on the rotation data that a first abnormal rotation event has occurred in the by-wire steering wheel, data related to the driver's driving state and data related to the vehicle's surrounding environment;

[0007] Inputting the rotation-related data, the driving state-related data, and the vehicle surrounding environment-related data into a pre-built steering wheel misoperation recognition model;

[0008] When the by-wire steering wheel is determined to be misoperated according to the output result of the steering wheel misoperation recognition model, a rotation control strategy for the by-wire steering wheel is determined according to the safety condition of the vehicle surrounding environment determined by the vehicle surrounding environment related data.

[0009] In one embodiment, determining a rotation control strategy for the wire-controlled steering wheel based on a safety condition of the vehicle's surrounding environment determined by data related to the vehicle's surrounding environment includes:

[0010] When it is determined based on the data related to the vehicle's surrounding environment that the vehicle's surrounding environment is safe, a secondary intervention strategy is determined;

[0011] According to the secondary intervention strategy, a strategy for limiting the steering input angle of the wire-controlled steering wheel or locking the steering angle of the wire-controlled steering wheel is obtained to form a rotation control strategy for the wire-controlled steering wheel.

[0012] In one embodiment, when the vehicle is in a curve scenario, the turning control strategy is formed based on a strategy of limiting the steering input angle of the wire-controlled steering wheel.

[0013] In one embodiment, determining a rotation control strategy for the wire-controlled steering wheel based on a safety condition of the vehicle's surrounding environment determined by vehicle surrounding environment-related data includes:

[0014] When the vehicle surrounding environment is determined to be dangerous based on the data related to the vehicle surrounding environment, a three-level intervention strategy is determined;

[0015] According to the three-level intervention strategy, a lane keeping or brake cooperative control strategy is obtained to form a rotation control strategy for the wire-controlled steering wheel.

[0016] In one embodiment, the method further comprises:

[0017] determining a primary intervention strategy when it is determined based on the rotation-related data that a second abnormal rotation event occurs in the wire-controlled steering wheel;

[0018] According to the first-level intervention strategy, a strategy for increasing torque or vibration on the wire-controlled steering wheel is obtained to form a rotation control strategy for the wire-controlled steering wheel.

[0019] In one embodiment, determining, based on the rotation-related data, that the second abnormal rotation event of the steering-by-wire wheel occurs includes:

[0020] determining, based on the rotation-related data, whether a rotation amplitude of the wire-controlled steering wheel within a set time is greater than a first rotation amplitude threshold and less than a second rotation amplitude threshold; the first rotation amplitude threshold is less than the second rotation amplitude threshold;

[0021] If so, it is determined that a second abnormal rotation event occurs in the wire-controlled steering wheel.

[0022] In one embodiment, determining, based on the rotation-related data, that a first abnormal rotation event occurs in the steering-by-wire wheel includes:

[0023] determining, based on the rotation-related data, whether a rotation amplitude of the wire-controlled steering wheel within a set time is greater than or equal to a second rotation amplitude threshold;

[0024] If so, it is determined that a first abnormal rotation event occurs in the wire-controlled steering wheel.

[0025] In one embodiment, inputting the rotation-related data, the driving state-related data, and the vehicle surrounding environment-related data into a pre-built steering wheel misoperation recognition model includes:

[0026] Obtaining a first confidence level corresponding to the rotation-related data, a second confidence level corresponding to the driving state-related data, and a third confidence level corresponding to the vehicle surrounding environment-related data;

[0027] The rotation-related data, the driving state-related data, the vehicle surrounding environment-related data, the first confidence level, the second confidence level and the third confidence level are input into a pre-built steering wheel misoperation recognition model.

[0028] The present application provides a wire-controlled steering wheel control device, the device comprising:

[0029] a data acquisition module for acquiring, in real time, rotation-related data of a vehicle's steering-by-wire wheel, and acquiring, upon determining, based on the rotation-related data, a first abnormal rotation event of the steering-by-wire wheel, data related to the driver's driving state and data related to the vehicle's surrounding environment;

[0030] A model prediction module, configured to input the rotation-related data, the driving state-related data, and the vehicle surrounding environment-related data into a pre-built steering wheel misoperation recognition model;

[0031] A control strategy determination module is used to determine a rotation control strategy for the wire-controlled steering wheel based on the vehicle surrounding environment safety situation determined by the vehicle surrounding environment related data when it is determined that the wire-controlled steering wheel is misoperated based on the output result of the steering wheel misoperation recognition model.

[0032] The present application provides a vehicle, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the above method.

[0033] The present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program is used by a processor to execute the above method.

[0034] The present application provides a computer program product having a computer program stored thereon, wherein the computer program is used by a processor to execute the above method.

[0035] The above-mentioned wire-controlled steering wheel control method, device, vehicle, storage medium and computer program product obtain the rotation-related data of the wire-controlled steering wheel of the vehicle in real time. When it is determined that the wire-controlled steering wheel has a first abnormal rotation event based on the rotation-related data, the driver's driving state-related data and the vehicle's surrounding environment-related data are obtained; the rotation-related data, driving state-related data and vehicle's surrounding environment-related data are input into a pre-constructed steering wheel misoperation recognition model; when it is determined that the wire-controlled steering wheel has been misoperated based on the output result of the steering wheel misoperation recognition model, the rotation control strategy for the wire-controlled steering wheel is determined based on the safety status of the vehicle's surrounding environment determined by the vehicle's surrounding environment-related data. The solution provided in this application forms multi-dimensional data based on the rotation-related data of the wire-controlled steering wheel, the driver's driving state-related data and the vehicle's surrounding environment-related data, thereby performing identification and analysis of misoperated wire-controlled steering wheels and improving the recognition accuracy of misoperated wire-controlled steering wheels. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 Schematic diagram of a flow chart of a wire-controlled steering wheel control method in one embodiment;

[0038] Figure 2 A system architecture diagram of a wire-controlled steering wheel control method in one embodiment;

[0039] Figure 3 is an interactive flow chart of a wire-controlled steering wheel control method in one embodiment;

[0040] Figure 4 A scene verification diagram of a wire-controlled steering wheel control method in one embodiment;

[0041] Figure 5 is a structural block diagram of a wire-controlled steering wheel control device in one embodiment;

[0042] Figure 6 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0044] The wire-controlled steering wheel control method provided in this application can be executed by a vehicle processor, and the method may include: Figure 1 Steps shown.

[0045] Step S101 , obtaining rotation-related data of the vehicle's wire-controlled steering wheel in real time, and when it is determined based on the rotation-related data that a first abnormal rotation event occurs in the wire-controlled steering wheel, obtaining driving state-related data of the driver and vehicle surrounding environment-related data.

[0046] The vehicle may be equipped with a wire-controlled steering wheel, the steering of which may be controlled by software. During vehicle operation, data related to the rotation of the wire-controlled steering wheel may be acquired in real time. The rotation-related data primarily includes data describing the rotation of the wire-controlled steering wheel, such as the steering angular rate of the wire-controlled steering wheel.

[0047] The vehicle may also be equipped with a sensor for monitoring the steering angular rate of the wire-controlled steering wheel. To distinguish this sensor from other sensors equipped on the vehicle, this sensor may be referred to as a first sensor. The first sensor obtains the steering angular rate of the wire-controlled steering wheel, thereby generating data related to the rotation of the wire-controlled steering wheel.

[0048] After obtaining the rotation data related to the steering-by-wire wheel, it can be determined based on the rotation data (e.g., steering angular rate) whether the steering-by-wire wheel has experienced a sudden large rotation. If so, it can be determined that an abnormal steering-by-wire rotation event has occurred. To distinguish this abnormal rotation event from other abnormal rotation events, this abnormal rotation event is referred to as a first abnormal rotation event. When determining whether the steering-by-wire wheel has experienced a sudden large rotation, it can be determined whether the steering angular rate is greater than a preset steering angular rate threshold (e.g., 90° / s). If so, it can be determined that a sudden large rotation has occurred.

[0049] After determining that the first abnormal rotation event of the wire-controlled steering wheel occurs, data related to the driver's driving state and data related to the vehicle's surrounding environment can be obtained.

[0050] The driver's driving state data primarily includes data describing the driver's current driving state, such as the driver's driving posture, driving line of sight, and the steering torque applied to the by-wire steering wheel. The vehicle may be equipped with an in-vehicle visual sensor (Driver Monitoring System (DMS)) for the driver. This in-vehicle visual sensor is primarily used to capture an image of the driver (referred to as a driving image). The driving image captured by the in-vehicle visual sensor includes the driver's driving posture and driving line of sight. Therefore, the driver's driving state data can be generated based on the driving image. The vehicle may also be equipped with a pressure sensor for monitoring the steering wheel. This pressure sensor can determine the force applied by the driver on the steering wheel. The steering torque applied by the driver to the steering wheel can be determined by multiplying the force by the lever arm. The lever arm can be the radius of the steering wheel.

[0051] Data related to the vehicle's surroundings primarily includes data describing the vehicle's surroundings. Vehicles may be equipped with at least one of a lidar sensor, a millimeter-wave radar sensor, and an exterior vision sensor. The lidar sensor can collect point cloud data of the vehicle's surroundings, which can be used to determine the vehicle's surrounding conditions. The millimeter-wave radar sensor can monitor for obstacles near the vehicle and can complement and integrate with the lidar sensor. The exterior vision sensor can capture images of the vehicle's surroundings, which can be used to determine the presence of obstacles and lane relationships.

[0052] Step S102 : inputting the rotation-related data, the driving state-related data, and the vehicle surrounding environment-related data into a pre-built steering wheel misoperation recognition model.

[0053] The pre-built steering wheel misoperation recognition model can analyze the probability of misoperation of the wire-controlled steering wheel based on the input data. The steering wheel misoperation recognition model can be a hybrid deep learning model built based on a convolutional neural network and a long short-term memory network.

[0054] A steering wheel misoperation recognition model can be pre-built through training. After obtaining rotation-related data, driving status-related data, and vehicle surrounding environment-related data, input data can be obtained based on these data and input into the steering wheel misoperation recognition model.

[0055] Step S103 , when it is determined that the by-wire steering wheel is misoperated according to the output result of the steering wheel misoperation recognition model, a rotation control strategy for the by-wire steering wheel is determined according to the vehicle surrounding environment safety condition determined by the vehicle surrounding environment related data.

[0056] After inputting the input data into the steering wheel misoperation recognition model, the output result of the steering wheel misoperation recognition model can be obtained, and the output result may include the wire-controlled steering wheel misoperation confidence; if the wire-controlled steering wheel misoperation confidence is greater than the misoperation confidence threshold, it can be determined that the wire-controlled steering wheel is misoperated.

[0057] After determining that the wire-controlled steering wheel has been operated incorrectly, the safety status of the vehicle's surrounding environment can be determined based on relevant data about the vehicle's surrounding environment. The safety status of the vehicle's surrounding environment describes whether the vehicle's surrounding environment is safe. Based on the safety status of the vehicle's surrounding environment, the rotation control strategy of the wire-controlled steering wheel is determined. The rotation control strategy of the wire-controlled steering wheel is mainly used to control whether the wire-controlled steering wheel is rotated and how it is rotated.

[0058] In the above-mentioned wire-controlled steering wheel control method, rotation-related data of the vehicle's wire-controlled steering wheel is acquired in real time. When it is determined based on the rotation-related data that the wire-controlled steering wheel has a first abnormal rotation event, data related to the driver's driving state and data related to the vehicle's surrounding environment are acquired; the rotation-related data, driving state-related data, and vehicle's surrounding environment-related data are input into a pre-constructed steering wheel misoperation recognition model; when it is determined based on the output result of the steering wheel misoperation recognition model that the wire-controlled steering wheel has been misoperated, a rotation control strategy for the wire-controlled steering wheel is determined based on the safety status of the vehicle's surrounding environment determined by the vehicle's surrounding environment-related data. The solution provided in this application forms multi-dimensional data based on the rotation-related data of the wire-controlled steering wheel, the driver's driving state-related data, and the vehicle's surrounding environment-related data, thereby performing identification and analysis of misoperated wire-controlled steering wheels and improving the accuracy of identifying misoperated wire-controlled steering wheels.

[0059] In one embodiment, determining a rotation control strategy for a wire-controlled steering wheel based on a safety condition of the vehicle's surrounding environment determined by data related to the vehicle's surrounding environment includes:

[0060] When the vehicle's surroundings are determined to be safe based on data related to the vehicle's surroundings, a secondary intervention strategy is determined; based on the secondary intervention strategy, a strategy for limiting the steering input angle of the wire-controlled steering wheel and locking the wire-controlled steering wheel angle is obtained to form a rotation control strategy for the wire-controlled steering wheel.

[0061] During vehicle operation, data related to the by-wire steering wheel's rotation can be monitored in real time. When a sudden, large rotation of the steering wheel is detected based on the rate of the data, a first abnormal steering wheel rotation event is determined, indicating a serious driver error. To ensure driving safety, the steering wheel rotation data, data related to the driver's driving status, and data related to the vehicle's surrounding environment are input into a steering wheel error recognition model.

[0062] When the output of the steering wheel misoperation recognition model indicates that the by-wire steering wheel has been misoperated, the vehicle's surrounding safety status can be determined based on data related to the vehicle's surrounding environment. The vehicle's surrounding safety status describes whether the vehicle's surrounding environment is safe. When the vehicle's surrounding environment is safe, a secondary intervention strategy can be determined. The secondary intervention strategy describes a strategy for limiting the by-wire steering input angle and locking the steering wheel's rotation angle. Based on the strategy for limiting the by-wire steering input angle or locking the steering wheel's rotation angle, a rotation control strategy for the by-wire steering wheel can be derived, and the steering wheel can be controlled according to this rotation control strategy.

[0063] In this embodiment, when it is determined based on the output result of the steering wheel misoperation identification model that the wire-controlled steering wheel is misoperated and the vehicle surrounding environment is safe, the steering input angle of the wire-controlled steering wheel can be limited or the wire-controlled steering wheel angle can be locked to ensure driving safety.

[0064] In one embodiment, when the vehicle is in a curve scenario, the turning control strategy is formed based on a strategy of limiting the steering input angle of the steer-by-wire wheel.

[0065] This embodiment can determine whether the vehicle is on a curve using sensors installed on the vehicle. The navigation map pre-stores road data, including the location, curvature radius, length, and turning direction of the curve. Therefore, after determining the vehicle's position on the navigation map, the vehicle can determine whether it is on a curve based on the location and the pre-stored road data in the navigation map.

[0066] To address incorrect operation of the wire-controlled steering wheel, software control is used to limit the steering input angle of the wire-controlled steering wheel or lock the steering angle when the vehicle's surrounding environment is safe. When it is determined that the vehicle is in a curve, the steering input angle of the wire-controlled steering wheel can be limited through software control to improve driving safety.

[0067] If a strategy of locking the steering angle is used to control the wire-controlled steering wheel, the authority level can also be dynamically adjusted according to the risk level of the vehicle's surrounding environment. For example, the threshold for locking the steering angle can be lowered when the vehicle is in a curve. Compared with the solution of outputting a fixed control amount from the reinforcement learning model, this processing method can improve adaptability to various environments.

[0068] In one embodiment, determining a rotation control strategy for a wire-controlled steering wheel based on a safety condition of the vehicle's surrounding environment determined by data related to the vehicle's surrounding environment includes:

[0069] When the vehicle's surrounding environment is determined to be dangerous based on relevant data about the vehicle's surrounding environment, a three-level intervention strategy is determined; based on the three-level intervention strategy, a lane keeping or brake coordinated control strategy is obtained to form a rotation control strategy for the wire-controlled steering wheel.

[0070] During vehicle operation, data related to the by-wire steering wheel's rotation can be monitored in real time. When a sudden, large rotation of the steering wheel is detected based on the data, a first abnormal steering wheel rotation event is determined, indicating a serious driver error. To ensure driving safety, the steering wheel's rotation data, data related to the driver's driving status, and data related to the vehicle's surrounding environment are input into a steering wheel error recognition model.

[0071] When the steering wheel misoperation identification model outputs a false positive, the vehicle's surrounding safety status can be determined based on the vehicle's surrounding environment data. This status describes whether the vehicle's surrounding environment is safe. If the vehicle's surrounding environment is dangerous, indicating that sharp turns are not suitable, a three-level intervention strategy can be determined. These three-level intervention strategies describe lane keeping and brake coordination control strategies. Based on these lane keeping and brake coordination control strategies, a steering control strategy for the steering wheel can be developed.

[0072] In this embodiment, when it is determined based on the output result of the steering wheel misoperation recognition model that the wire-controlled steering wheel is misoperated and the vehicle surrounding environment is dangerous, emergency lane keeping or brake cooperative control can be triggered to ensure driving safety.

[0073] In one embodiment, the method provided in the present application also includes: when it is determined based on the rotation-related data that a second abnormal rotation event occurs in the wire-controlled steering wheel, determining a first-level intervention strategy; based on the first-level intervention strategy, obtaining a strategy for increasing the torque or vibration of the wire-controlled steering wheel to form a rotation control strategy for the wire-controlled steering wheel.

[0074] During vehicle driving, the rotation-related data of the wire-controlled steering wheel can be monitored in real time. When the wire-controlled steering wheel is determined to have a sudden small rotation based on the rotation-related data, it is determined that the wire-controlled steering wheel has a second abnormal rotation event, and the driver may have made a minor misoperation. At this time, a first-level intervention strategy can be determined. The first-level intervention strategy describes a strategy for increasing torque or vibration on the wire-controlled steering wheel. Based on the strategy for increasing torque or vibration on the wire-controlled steering wheel, a rotation control strategy for the wire-controlled steering wheel can be formed. Increasing torque on the wire-controlled steering wheel can specifically apply a reverse steering torque to the wire-controlled steering wheel, and prompt the driver by increasing damping. Applying vibration to the wire-controlled steering wheel can specifically control the vibration of the vibration sensor deployed on the wire-controlled steering wheel, and prompt the driver by vibration.

[0075] In this embodiment, when it is determined that the second abnormal rotation event of the wire-controlled steering wheel occurs, the second abnormal rotation event reflects that the wire-controlled steering wheel has a sudden small rotation, and the driver may have made a slight misoperation. By increasing the torque or vibration of the wire-controlled steering wheel, the driver is reminded to pay attention to the wire-controlled steering wheel, thereby improving driving safety.

[0076] In one embodiment, determining that a second abnormal rotation event of the steering-by-wire wheel occurs according to the rotation-related data includes:

[0077] Based on the rotation-related data, determine whether the rotation amplitude of the wire-controlled steering wheel within the set time is greater than the first rotation amplitude threshold and less than the second rotation amplitude threshold; the first rotation amplitude threshold is less than the second rotation amplitude threshold; if so, it is determined that a second abnormal rotation event of the wire-controlled steering wheel has occurred.

[0078] During vehicle operation, real-time monitoring of steering-by-wire wheel rotation data is possible. This rotation data reflects the steering wheel's rotation status. Therefore, based on this rotation data, it can be determined whether the steering wheel's rotation amplitude within a set timeframe exceeds a first rotation amplitude threshold. If so, abnormal steering wheel rotation can be determined. The first rotation amplitude threshold represents a normal rotation amplitude threshold.

[0079] Abnormal rotation events include a first abnormal rotation event and a second abnormal rotation event. The first abnormal rotation event corresponds to a sudden large rotation of the wire-controlled steering wheel, and the second abnormal rotation event corresponds to a sudden small rotation of the wire-controlled steering wheel. Therefore, after determining that an abnormal rotation event has occurred in the wire-controlled steering wheel, it is possible to further judge whether the rotation amplitude of the wire-controlled steering wheel within the set time is less than the second rotation amplitude threshold based on the rotation-related data; the second rotation amplitude threshold is greater than the first rotation amplitude threshold.

[0080] If the rotation amplitude of the steering-by-wire wheel within the set time is less than the second rotation amplitude threshold, it is determined that a second abnormal rotation event of the steering-by-wire wheel occurs.

[0081] In this embodiment, by setting the first rotation amplitude threshold, normal rotation events and abnormal rotation events can be more clearly distinguished. By setting the second rotation amplitude threshold, the first abnormal rotation event and the second abnormal rotation event can be more clearly distinguished. This can provide a clear basis for the hierarchical processing mechanism, avoiding misjudgment and overreaction of normal operations, and timely capturing potential risks and taking targeted measures to improve the accuracy and reliability of the response.

[0082] In one embodiment, determining that a first abnormal rotation event of the steering-by-wire wheel occurs based on the rotation-related data includes:

[0083] Based on the rotation-related data, it is determined whether the rotation amplitude of the wire-controlled steering wheel within the set time is greater than or equal to a second rotation amplitude threshold; if so, it is determined that a first abnormal rotation event of the wire-controlled steering wheel occurs.

[0084] During vehicle operation, real-time monitoring of steering-by-wire wheel rotation data is possible. This rotation data reflects the steering wheel's rotation status. Therefore, based on this rotation data, it can be determined whether the steering wheel's rotation amplitude within a set timeframe exceeds a first rotation amplitude threshold. If so, abnormal steering wheel rotation can be determined. The first rotation amplitude threshold represents a normal rotation amplitude threshold.

[0085] Abnormal rotation events include a first abnormal rotation event and a second abnormal rotation event. The first abnormal rotation event corresponds to a sudden large rotation of the wire-controlled steering wheel, and the second abnormal rotation event corresponds to a sudden small rotation of the wire-controlled steering wheel. Therefore, after determining that an abnormal rotation event has occurred in the wire-controlled steering wheel, it is possible to further determine whether the rotation amplitude of the wire-controlled steering wheel within the set time is greater than the second rotation amplitude threshold based on the rotation-related data; the second rotation amplitude threshold is greater than the first rotation amplitude threshold.

[0086] If the rotation amplitude of the wire-controlled steering wheel within the set time is greater than the second rotation amplitude threshold, it is determined that the wire-controlled steering wheel has a first abnormal rotation event. Then, the rotation-related data, driving state-related data, and vehicle surrounding environment-related data can be input into the steering wheel misoperation recognition model to obtain the output result of the steering wheel misoperation recognition model, which can include the wire-controlled steering wheel misoperation confidence level; if the wire-controlled steering wheel misoperation confidence level is greater than the misoperation confidence level threshold, it can be determined that the wire-controlled steering wheel has been misoperated. After determining that the wire-controlled steering wheel has been misoperated, the vehicle surrounding environment safety status can be determined based on the vehicle surrounding environment-related data. The vehicle surrounding environment safety status describes whether the vehicle surrounding environment is safe; based on the vehicle surrounding environment safety status, the wire-controlled steering wheel rotation control strategy is determined; the wire-controlled steering wheel rotation control strategy is mainly used to control whether the wire-controlled steering wheel rotates and how it rotates.

[0087] In this embodiment, by setting a second rotation amplitude threshold, the situation where the steering wheel rotates by an amplitude greater than or equal to the second rotation amplitude threshold within a set time is defined as a first abnormal rotation event, which clarifies the judgment criteria for severe abnormal rotation and forms a clearer distinction from abnormal rotation of a slight abnormal degree. This allows the system to quickly identify serious risks that may directly threaten driving safety, provide an accurate basis for immediately triggering high-level safety responses (such as activating emergency avoidance mechanisms, cutting off dangerous power output, etc.), and minimize the accident risks caused by severe abnormal rotation.

[0088] In one embodiment, inputting the rotation-related data, the driving state-related data, and the vehicle surrounding environment-related data into a pre-built steering wheel misoperation recognition model includes:

[0089] Obtain a first confidence level corresponding to the rotation-related data, a second confidence level corresponding to the driving state-related data, and a third confidence level corresponding to the vehicle surrounding environment-related data; and input the rotation-related data, the driving state-related data, the vehicle surrounding environment-related data, the first confidence level, the second confidence level, and the third confidence level into a pre-built steering wheel misoperation recognition model.

[0090] The rotation-related data of the wire-controlled steering wheel includes data used to describe the rotation condition of the wire-controlled steering wheel, such as the steering angular rate of the wire-controlled steering wheel; the rotation-related data of the wire-controlled steering wheel can be collected by a first sensor, and the collection accuracy of the first sensor will affect the accuracy of the rotation-related data. Therefore, the confidence level corresponding to the rotation-related data can be determined based on the collection accuracy of the first sensor. To distinguish it from other confidence levels, this confidence level is called the first confidence level.

[0091] The driver's driving state data primarily includes data describing the driver's current driving state, such as the driver's driving posture, driving line of sight, and the steering torque applied to the drive-by-wire steering wheel. The driver's driving posture and driving line of sight can be captured by in-vehicle visual sensors. Whether the driving posture and driving line of sight can be accurately captured depends on the conditions of the in-vehicle visual sensors. For example, if the in-vehicle camera (which is a member of the in-vehicle visual sensor) is obstructed, the driving posture and driving line of sight may not be accurately captured in the driving picture. Therefore, the confidence level corresponding to the driving posture and driving line of sight can be determined based on the conditions of the in-vehicle visual sensors. The steering torque applied by the driver to the drive-by-wire steering wheel is related to the force applied by the driver to the drive-by-wire steering wheel as monitored by the pressure sensor. The accuracy of the steering torque is related to the pressure sensor's acquisition accuracy. Therefore, the confidence level corresponding to the steering torque can be determined based on the pressure sensor's acquisition accuracy. The confidence levels corresponding to the driving posture and driving line of sight, as well as the confidence level corresponding to the steering torque, are combined to obtain the confidence level corresponding to the driving state data. This confidence level can be referred to as the second confidence level.

[0092] Data related to the vehicle's surroundings primarily includes data describing the vehicle's surroundings. The accuracy of this data is affected by weather conditions. For example, during heavy rain, the accuracy of the point cloud data collected by the LiDAR sensor regarding the vehicle's surroundings is lower, while during clear skies, the accuracy of the point cloud data is higher. Therefore, the confidence level corresponding to the vehicle's surroundings data can be determined based on the weather conditions at the vehicle's location. This confidence level is referred to as the third confidence level.

[0093] Input data can be formed based on the data related to the rotation of the wire-controlled steering wheel and its first confidence, the data related to the driver's driving state and its second confidence, and the data related to the vehicle's surrounding environment and its third confidence, and thus input into the steering wheel misoperation recognition model. In this way, the steering wheel misoperation recognition model can determine the contribution of various types of data to the output result according to the relative size of the confidence of each type of data when identifying wire-controlled steering wheel misoperation. The greater the confidence, the greater the contribution, so that a more accurate output result can be obtained, which can improve the recognition accuracy of wire-controlled steering wheel misoperation.

[0094] In one embodiment, obtaining a first confidence level corresponding to the rotation-related data includes:

[0095] The tire rotation theoretical data is obtained based on the wire-controlled steering wheel rotation observation data collected by the first sensor during the historical rotation of the wire-controlled steering wheel; the collection accuracy of the first sensor is obtained based on the difference between the tire rotation theoretical data and the tire rotation observation data to determine the first confidence level.

[0096] Before an abnormal rotation event of the wire-controlled steering wheel is detected, during vehicle driving, the wire-controlled steering wheel rotation observation data collected by the first sensor when the wire-controlled steering wheel rotates can be obtained. Since the rotation event occurs before the abnormal rotation event, the rotation event can be called a historical rotation event, that is, the wire-controlled steering wheel rotation observation data collected by the first sensor during the historical rotation of the wire-controlled steering wheel can be obtained.

[0097] After obtaining the observed steering wheel rotation data, the theoretical tire rotation data of the vehicle can be calculated. The observed tire rotation data can be obtained using the corresponding sensor. The difference between the observed tire rotation data and the theoretical tire rotation data can be used to determine the acquisition accuracy of the first sensor. The smaller the difference, the higher the acquisition accuracy. A first confidence level can also be determined based on the acquisition accuracy of the first sensor. The higher the acquisition accuracy, the higher the first confidence level.

[0098] In this embodiment, the theoretical tire rotation data is inferred from the observed steering wheel rotation data collected by the first sensor during the historical rotation of the steering wheel. Based on the difference between the theoretical tire rotation data and the observed tire rotation data, the collection accuracy of the first sensor can be quantified more reasonably and accurately, thereby obtaining a more accurate first confidence level and improving the accuracy of identifying incorrect operations of the steering wheel.

[0099] In one embodiment, when the driving state-related data includes a driving picture collected by an in-vehicle visual sensor of the driver, obtaining a second confidence level corresponding to the driving state-related data includes:

[0100] Obtain calibration images collected by the in-vehicle visual sensor in different calibration scenarios; compare the driving image with each calibration image, determine the calibration image that matches the driving image, and obtain a target calibration image; and obtain a second confidence level based on the confidence level associated with the target calibration image.

[0101] For example, before leaving the factory, the camera can be subjected to varying degrees of occlusion, with each degree of occlusion considered a calibration scenario. When the camera is obscured to a certain degree, the camera captures an image of the driver's seat, which is considered a calibration image. A confidence level is assigned to this image. This allows us to obtain the calibration images captured by the in-vehicle vision sensor in different calibration scenarios, along with the confidence level associated with each calibration image.

[0102] After obtaining the driver's driving image, the driving image can be compared with each calibration image based on dimensions such as clarity and contrast to determine a calibration image that matches the driving image. This calibration image is then used as the target calibration image. A second confidence level can be obtained based on the confidence level associated with the target calibration image.

[0103] In this embodiment, the calibration images collected by the in-vehicle visual sensor in different calibration scenarios are compared with the driving images to determine a matching target calibration image. The confidence level associated with the target calibration image can more accurately reflect the confidence level corresponding to the driving posture and driving line of sight, and thus a more accurate second confidence level can be obtained, thereby improving the accuracy of identifying incorrect operations of the wire-controlled steering wheel.

[0104] In order to better understand the above method, an application example of the wire-controlled steering wheel control method of the present application is described in detail below. In this application example, when the wire-controlled steering wheel turns abnormally due to driver misoperation (such as sudden disability or external interference), it can be determined whether it is necessary to take over the steering control in combination with multi-dimensional data to ensure that the vehicle remains in the lane. The multi-dimensional data may include: data related to the rotation of the wire-controlled steering wheel, data related to the driver's driving status, and data related to the vehicle's surrounding environment, wherein the data related to the vehicle's surrounding environment belongs to environmental perception data, and the data related to the vehicle's surrounding environment may include lane line information and obstacle information. Among them, the wire-controlled steering wheel can be dynamically controlled by the wire-controlled steering system, and the wire-controlled steering wheel input can be limited by electronic signals or the steering actuator can be directly taken over.

[0105] This application example involves multi-sensor fusion decision-making, which verifies the feasibility of lane keeping with the help of data collected by visual sensors, radar sensors, inertial navigation sensors, etc.

[0106] The solution provided in this application example involves the triggering conditions for steering failure, which are related to whether an abnormal steering event occurs and whether the vehicle's surrounding environment is safe.

[0107] When monitoring whether an abnormal steering event occurs, it can be achieved by monitoring the steering angular rate, steering torque or continuous unilateral input of the wire-controlled steering wheel; for example, when the monitored steering angular rate of the wire-controlled steering wheel indicates that the wire-controlled steering wheel has a sudden large turn, it can be determined that a first abnormal steering event has occurred; for another example, when the monitored steering torque of the wire-controlled steering wheel indicates that the wire-controlled steering wheel is suddenly subjected to a large steering torque, it can be determined that a first abnormal steering event has occurred; for another example, when the monitored steering angular rate of the wire-controlled steering wheel indicates that the wire-controlled steering wheel has a sudden small turn, it can be determined that a second abnormal steering event has occurred; for another example, when the monitored steering torque of the wire-controlled steering wheel indicates that the wire-controlled steering wheel is suddenly subjected to a small steering torque, it can be determined that a second abnormal steering event has occurred.

[0108] In addition, the need for steering is determined through a combination of external visual sensors, lidar sensors, and high-precision maps, with lidar and ultrasonic radar sensors used as redundant backups. The images captured by the external visual sensors are relevant for determining lane clarity, while data collected by the lidar sensors can indicate obstacle distances, and high-precision maps are relevant for determining lane type.

[0109] During vehicle driving, the steering angular rate of the wire-controlled steering wheel can be monitored in real time. When it is determined based on the steering angular rate that the wire-controlled steering wheel has a sudden small turn, the driver may have made a slight misoperation. At this time, a first-level intervention strategy can be executed to apply a reverse steering torque to the wire-controlled steering wheel, and the driver can be prompted by increasing the damping or by vibration.

[0110] When it is determined based on the steering angular rate of the wire-controlled steering wheel that the wire-controlled steering wheel has suddenly turned sharply, the driver may have made a serious misoperation. The data related to the rotation of the wire-controlled steering wheel, the data related to the driver's driving status, and the data related to the vehicle's surrounding environment can be input into the steering wheel misoperation recognition model.

[0111] When it is determined that the wire-controlled steering wheel is misoperated based on the output result of the steering wheel misoperation recognition model, the safety status of the vehicle's surrounding environment can be determined based on the relevant data of the vehicle's surrounding environment. The safety status of the vehicle's surrounding environment describes whether the vehicle's surrounding environment is safe.

[0112] When the vehicle's surroundings are safe, a secondary intervention strategy may be executed; in the secondary intervention strategy, a steering-by-wire steering wheel rotation control strategy may be obtained based on strategies for limiting the steering input angle of the steering-by-wire steering wheel and locking the steering angle of the steering-by-wire steering wheel.

[0113] When the lane is clear of obstacles, a decoupling command is triggered between the steer-by-wire system and the mechanical steering system, disabling any erroneous steering wheel operation and providing interactive feedback via the HMI. The lane-keeping system then maintains the vehicle's lane. HMI stands for Human-Machine Interface.

[0114] When the vehicle's surroundings are dangerous, it means that sharp turns are not suitable at the moment, and a three-level intervention strategy can be executed at this time. In the three-level intervention strategy, the steering wheel rotation control strategy can be obtained based on the lane keeping and brake coordinated control strategies.

[0115] This application example provides a solution that uses multi-sensor cross-validation to avoid single-sensor misjudgments. For example, if the exterior visual sensor indicates an obstacle ahead, but the radar sensors indicate no obstacle ahead, the data collected by the exterior visual sensor and the radar sensors can be fed into an AI model for anomaly analysis to determine if there is an obstacle. AI stands for Artificial Intelligence.

[0116] This application example also provides a failsafe switching mechanism, which includes a mechanical backup link to ensure that basic steering capabilities are maintained in the event of an electronic system failure. For example, if the electronic steering system fails, the wire-controlled steering wheel is released within one second, allowing the driver to regain control and perform steering control through normal mechanical steering.

[0117] This application example has made some optimizations in terms of user interaction, including:

[0118] (1) HMI prompt: When taking over, a "steering restricted" reminder message can be displayed on the vehicle's dashboard, and a voice warning message can be issued; (2) Authority recovery logic: The driver can regain control by long pressing the wire-controlled steering wheel function key or stepping on the brake.

[0119] Figure 2 The following is the system architecture diagram for this application example. The sensor layer includes multiple sensors. The data collected by the sensor layer is fed into the steering wheel misoperation recognition model, which belongs to the AI ​​decision-making layer. Based on the output of the steering wheel misoperation recognition model and the safety conditions of the vehicle's surrounding environment, a rotation control strategy for the wire-controlled steering wheel is derived. Based on the rotation control strategy, dynamic permission instructions are generated and input into the execution layer to control the vehicle's lateral movement by turning the steering motor and providing feedback to the driver through the HMI to promptly take over.

[0120] Figure 3This is the interactive flow chart for this application example. While the vehicle is in motion, the steering angular rate of the wire-controlled steering wheel can be monitored in real time. If the wire-controlled steering wheel's steering angular rate indicates a sudden, large turn, the driver may have made a serious misoperation. Input data can be generated based on data related to the wire-controlled steering wheel's rotation, the driver's driving status, and the vehicle's surroundings, and then fed into a steering wheel misoperation recognition model. When the output of the steering wheel misoperation recognition model indicates a misoperation of the wire-controlled steering wheel, the safety of the vehicle's surroundings can be determined based on the vehicle's surroundings data. If the vehicle's surroundings are safe, the wire-controlled steering can be disabled, maintaining the current steering angle and prompting the driver to intervene. Otherwise, normal steering is performed to avoid obstacles.

[0121] Figure 4 This is a scenario verification diagram for this application example. The test scenarios covered in this application example include: a straight road accidental steering-by-wire operation scenario, a curve accidental steering-by-wire operation scenario, and a nighttime low-light scenario. In the straight road accidental steering-by-wire operation scenario, the steering can be locked to maintain the lane. In the curve accidental steering-by-wire operation scenario, the locking threshold can be dynamically adjusted based on the curvature of the curve to achieve a smooth transition. In the nighttime low-light scenario, an infrared camera can be used for enhanced accuracy to identify lane markings.

[0122] This application example combines multi-dimensional data to determine whether the wire-controlled steering wheel has been misoperated, which can improve the accuracy of misoperation identification and reduce the false trigger rate. In addition, this application example combines AI and a rule engine to implement dynamic hierarchical control, improve takeover flexibility, and can better adapt to curves or night scenes. In addition, this application example adopts "software virtual locking" (that is, torque limitation through the motor), which can extend the life of the steering system and better protect related hardware compared to the hard locking solution using an electromagnetic mechanical lock. This application example adopts a control method with progressive prompts and recoverable permissions, which is easy for users to accept and more interactive.

[0123] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0124] Based on the same inventive concept, embodiments of the present application also provide a wire-steering wheel control device for implementing the aforementioned wire-steering wheel control method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more wire-steering wheel control device embodiments provided below can be found in the aforementioned limitations of the wire-steering wheel control method and will not be further elaborated here.

[0125] In one embodiment, Figure 5 As shown, a wire-controlled steering wheel control device is provided, comprising:

[0126] a data acquisition module 501 for acquiring, in real time, rotation data related to the vehicle's steering-by-wire wheel, and acquiring, upon determining, based on the rotation data, a first abnormal rotation event of the steering-by-wire wheel, data related to the driver's driving state and data related to the vehicle's surrounding environment;

[0127] A model prediction module 502 is configured to input the rotation-related data, the driving state-related data, and the vehicle surrounding environment-related data into a pre-built steering wheel misoperation recognition model;

[0128] The control strategy determination module 503 is used to determine the rotation control strategy for the wire-controlled steering wheel according to the vehicle surrounding environment safety situation determined by the vehicle surrounding environment related data when it is determined that the wire-controlled steering wheel is misoperated according to the output result of the steering wheel misoperation recognition model.

[0129] In one embodiment, the control strategy determination module 503 is configured to:

[0130] When the vehicle's surrounding environment is determined to be safe based on data related to the vehicle's surrounding environment, a secondary intervention strategy is determined; based on the secondary intervention strategy, a strategy for limiting the steering input angle of the wire-controlled steering wheel or locking the wire-controlled steering wheel angle is obtained to form a rotation control strategy for the wire-controlled steering wheel.

[0131] In one embodiment, when the vehicle is in a curve scenario, the turning control strategy is formed based on a strategy of limiting the steering input angle of the wire-controlled steering wheel.

[0132] In one embodiment, the control strategy determination module 503 is configured to:

[0133] When the vehicle surrounding environment is determined to be dangerous based on the data related to the vehicle surrounding environment, a three-level intervention strategy is determined; based on the three-level intervention strategy, a lane keeping or brake coordinated control strategy is obtained to form a rotation control strategy for the wire-controlled steering wheel.

[0134] In one embodiment, the control strategy determination module 503 is configured to:

[0135] When it is determined based on the rotation-related data that the wire-controlled steering wheel has a second abnormal rotation event, a first-level intervention strategy is determined; based on the first-level intervention strategy, a strategy for increasing torque or vibration on the wire-controlled steering wheel is obtained to form a rotation control strategy for the wire-controlled steering wheel.

[0136] In one embodiment, the device further includes an abnormal rotation event determination module, which is configured to:

[0137] Based on the rotation-related data, determine whether the rotation amplitude of the wire-controlled steering wheel within a set time is greater than a first rotation amplitude threshold and less than a second rotation amplitude threshold; if the first rotation amplitude threshold is less than the second rotation amplitude threshold; if so, determine that the wire-controlled steering wheel has a second abnormal rotation event.

[0138] In one embodiment, the device further includes an abnormal rotation event determination module, which is configured to:

[0139] Based on the rotation-related data, it is determined whether the rotation amplitude of the wire-controlled steering wheel within a set time is greater than or equal to a second rotation amplitude threshold; if so, it is determined that a first abnormal rotation event of the wire-controlled steering wheel occurs.

[0140] In one embodiment, the model prediction module 502 is used to:

[0141] Obtain a first confidence level corresponding to the rotation-related data, a second confidence level corresponding to the driving state-related data, and a third confidence level corresponding to the vehicle surrounding environment-related data; and input the rotation-related data, driving state-related data, vehicle surrounding environment-related data, the first confidence level, the second confidence level, and the third confidence level into a pre-built steering wheel misoperation recognition model.

[0142] Each module in the aforementioned steering-by-wire control device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor within a computer device in the form of hardware, or may be stored in a computer device's memory in the form of software, allowing the processor to call and execute the corresponding operations of each module.

[0143] In an exemplary embodiment, a vehicle is provided, which may include a computer device. The internal structure diagram of the computer device may be as follows: Figure 6As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data involved in the above method. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a wire-controlled steering wheel control method is implemented.

[0144] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0145] In one embodiment, a vehicle is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above-mentioned various method embodiments when executing the computer program.

[0146] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0147] In one embodiment, a computer program product is provided, on which a computer program is stored. The computer program is used by a processor to execute the steps in the above-mentioned various method embodiments.

[0148] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0149] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0150] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0151] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for controlling a wire-controlled steering wheel, characterized in that: The method comprises: acquiring, in real time, rotation data related to a steering-by-wire wheel of the vehicle, and when determining, based on the rotation data, that a first abnormal rotation event has occurred in the steering-by-wire wheel, acquiring data related to the driver's driving state and data related to the vehicle's surrounding environment; Inputting the rotation-related data, the driving state-related data, and the vehicle surrounding environment-related data into a pre-built steering wheel misoperation recognition model; When the by-wire steering wheel is determined to be misoperated according to the output result of the steering wheel misoperation recognition model, a rotation control strategy for the by-wire steering wheel is determined according to the safety condition of the vehicle surrounding environment determined by the vehicle surrounding environment related data.

2. The method according to claim 1, characterized in that Determining a rotation control strategy for the wire-controlled steering wheel based on a safety condition of the vehicle's surrounding environment determined by data related to the vehicle's surrounding environment includes: When it is determined based on the data related to the vehicle's surrounding environment that the vehicle's surrounding environment is safe, a secondary intervention strategy is determined; According to the secondary intervention strategy, a strategy for limiting the steering input angle of the wire-controlled steering wheel or locking the steering angle of the wire-controlled steering wheel is obtained to form a rotation control strategy for the wire-controlled steering wheel.

3. The method according to claim 2, characterized in that When the vehicle is in a curve scenario, the turning control strategy is formed based on a strategy of limiting the steering input angle of the wire-controlled steering wheel.

4. The method according to claim 1, wherein Determining a rotation control strategy for the wire-controlled steering wheel based on a safety condition of the vehicle's surrounding environment determined by data related to the vehicle's surrounding environment includes: When the vehicle surrounding environment is determined to be dangerous based on the data related to the vehicle surrounding environment, a three-level intervention strategy is determined; According to the three-level intervention strategy, a lane keeping or brake cooperative control strategy is obtained to form a rotation control strategy for the wire-controlled steering wheel.

5. The method according to claim 1, wherein The method further comprises: determining a primary intervention strategy when it is determined based on the rotation-related data that a second abnormal rotation event occurs in the wire-controlled steering wheel; According to the first-level intervention strategy, a strategy for increasing torque or vibration on the wire-controlled steering wheel is obtained to form a rotation control strategy for the wire-controlled steering wheel.

6. The method according to claim 5, characterized in that Determining, based on the rotation-related data, that a second abnormal rotation event occurs in the steering-by-wire wheel includes: determining, based on the rotation-related data, whether a rotation amplitude of the wire-controlled steering wheel within a set time is greater than a first rotation amplitude threshold and less than a second rotation amplitude threshold; the first rotation amplitude threshold is less than the second rotation amplitude threshold; If so, it is determined that a second abnormal rotation event occurs in the wire-controlled steering wheel.

7. The method according to claim 1, characterized in that Determining, based on the rotation-related data, that a first abnormal rotation event occurs in the steering-by-wire wheel includes: determining, based on the rotation-related data, whether a rotation amplitude of the wire-controlled steering wheel within a set time is greater than or equal to a second rotation amplitude threshold; If so, it is determined that a first abnormal rotation event occurs in the wire-controlled steering wheel.

8. The method according to claim 1, characterized in that Inputting the rotation-related data, driving state-related data, and vehicle surrounding environment-related data into a pre-built steering wheel misoperation recognition model, including: Obtaining a first confidence level corresponding to the rotation-related data, a second confidence level corresponding to the driving state-related data, and a third confidence level corresponding to the vehicle surrounding environment-related data; The rotation-related data, the driving state-related data, the vehicle surrounding environment-related data, the first confidence level, the second confidence level and the third confidence level are input into a pre-built steering wheel misoperation recognition model.

9. A wire-controlled steering wheel control device, characterized in that: The device comprises: a data acquisition module for acquiring, in real time, rotation-related data of a vehicle's steering-by-wire wheel, and acquiring, upon determining, based on the rotation-related data, a first abnormal rotation event of the steering-by-wire wheel, data related to the driver's driving state and data related to the vehicle's surrounding environment; A model prediction module, configured to input the rotation-related data, the driving state-related data, and the vehicle surrounding environment-related data into a pre-built steering wheel misoperation recognition model; A control strategy determination module is used to determine a rotation control strategy for the wire-controlled steering wheel based on the vehicle surrounding environment safety situation determined by the vehicle surrounding environment related data when it is determined that the wire-controlled steering wheel is misoperated based on the output result of the steering wheel misoperation recognition model.

10. A vehicle comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images