Steering wheel zero angle updating method and device, computer device and storage medium

Abstract

This application relates to a method, apparatus, computer device, and storage medium for updating the zero-angle of a steering wheel. The method includes: determining the vehicle's driving state; if the vehicle is driving in a straight line, determining the driving mode triggered by the vehicle based on the difference between the latest predicted steering wheel angle and the current steering wheel angle; if the vehicle has not triggered a human-machine co-driving mode and the delay counter has reached the additional delay duration, updating the zero-angle of the steering wheel based on a lateral offset error integrator; the additional delay duration is acquired each time the vehicle switches from the human-machine co-driving mode to the normal driving mode; the delay counter starts timing each time the vehicle switches from the human-machine co-driving mode to the normal driving mode; if the vehicle has not switched driving modes, acquiring the latest predicted steering wheel angle and returning to the step of determining the vehicle's driving state. This method can improve the measurement accuracy of the zero-angle of the steering wheel.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a steering wheel zero-angle update method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] In autonomous driving systems, steering wheel angle control significantly impacts a vehicle's ability to follow a predetermined trajectory. Even for vehicles of the same model, there are slight mechanical differences in the steering wheels installed at the factory. This means that when the vehicle is traveling strictly in a straight line, the steering wheel angle is not zero; this angle (steering wheel zero-offset angle) varies from vehicle to vehicle. If this angle is not accurately calibrated, it can cause lateral deviations from the trajectory during cruising (especially at high speeds), increasing the safety risks of autonomous driving. Furthermore, the zero-offset angle can also change slightly due to factors such as the aging of steering components, load conditions, and road inclines. If the steering wheel zero-offset angle is not updated in real time, these safety risks cannot be avoided. Additionally, when the vehicle is in autonomous driving mode, even slight driver interference triggers the human-machine co-driving function, causing the vehicle to deviate from the planned trajectory, potentially affecting the recognition of the zero-offset angle.

[0003] In traditional technologies, to eliminate the safety risks posed by the steering wheel zero-off angle to the autonomous driving control system, it is necessary to update the accurate steering wheel zero-off angle in real time. Many previous steering wheel zero-off angle calibration or measurement methods required the vehicle to travel strictly in a straight line, with manual steering wheel control. This process was subject to human error in steering angle, making it difficult to guarantee the accuracy of the measurement results, and lacking real-time performance; therefore, these methods have gradually fallen out of use.

[0004] The current accuracy of zero-offset steering wheel measurement is relatively low. Summary of the Invention

[0005] Therefore, it is necessary to provide a steering wheel zero-off angle update method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the measurement accuracy of steering wheel zero-off angle in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a method for updating the zero-angle of a steering wheel, including:

[0007] The system determines the vehicle's driving status. When the vehicle is driving in a straight line, it determines the driving mode triggered by the vehicle based on the difference between the latest predicted steering wheel angle and the current steering wheel angle. The driving mode includes human-machine co-driving mode or normal driving mode.

[0008] If the vehicle does not trigger the human-machine co-driving mode and the delay counter reaches the additional delay duration, the steering wheel zero-offset angle is updated according to the lateral offset error integrator; the additional delay duration is obtained by the vehicle each time it switches from the human-machine co-driving mode to the normal driving mode, based on the duration of the human-machine co-driving mode trigger; the delay counter starts counting down each time the vehicle switches from the human-machine co-driving mode to the normal driving mode.

[0009] If the vehicle does not switch driving modes, the system obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of determining the vehicle's driving status.

[0010] In one embodiment, the method further includes:

[0011] When the vehicle is not traveling in a straight line, stop updating the steering wheel zero angle and keep the latest updated steering wheel zero angle unchanged.

[0012] If the vehicle does not switch driving modes, the system obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of determining the vehicle's driving status.

[0013] In one embodiment, the method further includes:

[0014] When the vehicle triggers the human-machine co-driving mode, stop updating the steering wheel zero-off angle and keep the latest updated steering wheel zero-off angle unchanged.

[0015] If the vehicle does not switch driving modes, the system obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of determining the vehicle's driving status.

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

[0017] When the vehicle switches from normal driving mode to human-machine co-driving mode, obtain the initial moment of human-machine co-driving;

[0018] Based on the vehicle's autonomous driving system, obtain the latest predicted steering wheel angle and return to execute the steps to determine the vehicle's driving status.

[0019] In one embodiment, the method further includes:

[0020] When the vehicle switches from human-machine co-driving mode to normal driving mode, the trigger duration of the human-machine co-driving mode is obtained based on the initial moment of human-machine co-driving, and the additional delay duration is updated based on the trigger duration.

[0021] Based on the vehicle's autonomous driving system, obtain the latest predicted steering wheel angle and return to execute the steps to determine the vehicle's driving status.

[0022] In one embodiment, the lateral offset error integrator is obtained by means of:

[0023] The integral gain is obtained based on the vehicle's speed and curvature.

[0024] Based on the vehicle-based autonomous driving system, the lateral offset error of the vehicle is obtained; the lateral offset error is used to characterize the degree of difference between the planned driving route of the autonomous driving system and the actual driving route of the vehicle.

[0025] A lateral offset error integrator is constructed based on the product of the integral gain and the lateral offset error.

[0026] Secondly, this application also provides a steering wheel zero-off-angle updating device, comprising:

[0027] The determination module is used to determine the vehicle's driving status. When the vehicle is driving in a straight line, it determines the driving mode triggered by the vehicle based on the degree of difference between the latest predicted steering wheel angle and the current steering wheel angle. The driving mode includes human-machine co-driving mode or normal driving mode.

[0028] The update module is used to update the steering wheel zero angle based on the lateral offset error integrator when the vehicle has not triggered the human-machine co-driving mode and the delay counter has reached the additional delay duration. The additional delay duration is obtained by the vehicle each time it switches from the human-machine co-driving mode to the normal driving mode, based on the duration of the human-machine co-driving mode trigger. The delay counter starts counting down each time the vehicle switches from the human-machine co-driving mode to the normal driving mode.

[0029] The iteration module is used to obtain the latest predicted steering wheel angle based on the vehicle's autonomous driving system, and return to the steps for judging the vehicle's driving status, when the vehicle has not changed driving modes.

[0030] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0031] The system determines the vehicle's driving status. When the vehicle is driving in a straight line, it determines the driving mode triggered by the vehicle based on the difference between the latest predicted steering wheel angle and the current steering wheel angle. The driving mode includes human-machine co-driving mode or normal driving mode.

[0032] If the vehicle does not trigger the human-machine co-driving mode and the delay counter reaches the additional delay duration, the steering wheel zero-offset angle is updated according to the lateral offset error integrator; the additional delay duration is obtained by the vehicle each time it switches from the human-machine co-driving mode to the normal driving mode, based on the duration of the human-machine co-driving mode trigger; the delay counter starts counting down each time the vehicle switches from the human-machine co-driving mode to the normal driving mode.

[0033] If the vehicle does not switch driving modes, the system obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of determining the vehicle's driving status.

[0034] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0035] The system determines the vehicle's driving status. When the vehicle is driving in a straight line, it determines the driving mode triggered by the vehicle based on the difference between the latest predicted steering wheel angle and the current steering wheel angle. The driving mode includes human-machine co-driving mode or normal driving mode.

[0036] If the vehicle does not trigger the human-machine co-driving mode and the delay counter reaches the additional delay duration, the steering wheel zero-offset angle is updated according to the lateral offset error integrator; the additional delay duration is obtained by the vehicle each time it switches from the human-machine co-driving mode to the normal driving mode, based on the duration of the human-machine co-driving mode trigger; the delay counter starts counting down each time the vehicle switches from the human-machine co-driving mode to the normal driving mode.

[0037] If the vehicle does not switch driving modes, the system obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of determining the vehicle's driving status.

[0038] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0039] The system determines the vehicle's driving status. When the vehicle is driving in a straight line, it determines the driving mode triggered by the vehicle based on the difference between the latest predicted steering wheel angle and the current steering wheel angle. The driving mode includes human-machine co-driving mode or normal driving mode.

[0040] If the vehicle does not trigger the human-machine co-driving mode and the delay counter reaches the additional delay duration, the steering wheel zero-offset angle is updated according to the lateral offset error integrator; the additional delay duration is obtained by the vehicle each time it switches from the human-machine co-driving mode to the normal driving mode, based on the duration of the human-machine co-driving mode trigger; the delay counter starts counting down each time the vehicle switches from the human-machine co-driving mode to the normal driving mode.

[0041] If the vehicle does not switch driving modes, the system obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of determining the vehicle's driving status.

[0042] The aforementioned steering wheel zero-off angle update method, device, computer equipment, storage medium, and computer program product determine the vehicle's driving state. When the vehicle is traveling in a straight line, it determines the triggered driving mode based on the difference between the latest predicted steering wheel angle and the current steering wheel angle. The driving mode includes a human-machine co-driving mode or a normal driving mode. If the vehicle has not triggered the human-machine co-driving mode and the delay counter reaches the additional delay duration, the steering wheel zero-off angle is updated based on the lateral offset error integrator. The additional delay duration is obtained each time the vehicle switches from the human-machine co-driving mode to the normal driving mode, based on the duration of the human-machine co-driving mode trigger. The delay counter starts counting each time the vehicle switches from the human-machine co-driving mode to the normal driving mode. If the vehicle has not switched driving modes, it obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of determining the vehicle's driving state. This improves the measurement accuracy of the steering wheel zero-off angle. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is an application environment diagram of the steering wheel zero-off-angle update method in one embodiment;

[0045] Figure 2 This is a flowchart illustrating a steering wheel zero-off-angle update method in one embodiment;

[0046] Figure 3 This is a schematic diagram of the logic flow of the steering wheel zero-off-angle update method in one embodiment;

[0047] Figure 4This is a schematic diagram illustrating normal steering wheel angle tracking in one embodiment;

[0048] Figure 5 This is a schematic diagram illustrating an anomaly in steering wheel angle tracking in one embodiment;

[0049] Figure 6 This is a schematic diagram of a first-order inertial element in one embodiment;

[0050] Figure 7 This is a structural block diagram of a steering wheel zero-off-angle update device in one embodiment;

[0051] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] The steering wheel zero-off-angle update method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, the vehicle-mounted terminal 102 communicates with the server 104 via a network. A data storage system can store the data that the server 104 needs to process. The data storage system can be integrated onto the server 104, or it can be located in the cloud or on other network servers. The vehicle-mounted terminal 102 can be, but is not limited to, various vehicle-mounted processors. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0054] In one exemplary embodiment, such as Figure 2 As shown, a method for updating the zero-angle of the steering wheel is provided, which is then applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 202 to 206. Wherein:

[0055] Step 202: Determine the vehicle's driving status. If the vehicle is driving in a straight line, determine the driving mode triggered by the vehicle based on the difference between the latest predicted steering wheel angle and the current steering wheel angle. The driving mode includes human-machine co-driving mode or normal driving mode.

[0056] Among them, the human-machine co-driving mode means that the vehicle's steering wheel is interfered with by the driver and is not completely controlled by the autonomous driving algorithm.

[0057] Optionally, if the vehicle is not traveling in a straight line, the update of the steering wheel zero angle is stopped, and the latest updated steering wheel zero angle remains unchanged; if the vehicle does not switch driving modes, the latest predicted steering wheel angle is obtained based on the vehicle's autonomous driving system, and the process returns to the step of judging the vehicle's driving status.

[0058] Specifically, before the algorithm is executed, it needs to be initialized, including setting the initial zero deflection angle and the additional delay counter to 0, setting the previous steering angle control command and predicted steering wheel angle to the current actual steering wheel angle, initializing the steering angle tracking status to normal, and setting the initial time of triggering human-machine co-driving (steering angle tracking abnormality) to the current time.

[0059] The algorithm begins execution, determining whether the vehicle is traveling in a straight line. If so, it uses the difference between the latest predicted steering wheel angle and the current steering wheel angle to determine whether the vehicle is in human-machine co-driving mode or normal driving mode. In human-machine co-driving mode, if the state machine does not determine that the vehicle has taken over, the steering wheel angle is affected by the driver and cannot track control commands. The vehicle gradually deviates from its trajectory, causing the lateral error to change in an undesirable direction during this stage. This leads to the steering wheel zero-angle being updated in the wrong direction, therefore, this judgment must be performed before updating the zero-angle.

[0060] If the vehicle is not traveling in a straight line, keep the previously updated steering wheel zero angle unchanged. If the vehicle does not switch driving modes, obtain the latest predicted steering wheel angle through the vehicle's automatic driving system, execute the steps to determine the vehicle's driving status again, and continue execution.

[0061] The method for determining whether a vehicle is traveling in a straight line is as follows: If the vehicle speed is less than 25 m / s, the curvature of a reference point on the current planned trajectory is extracted. If the absolute value of this curvature is less than a set threshold, it is considered a straight-line driving condition; otherwise, it is a curve. If the vehicle speed exceeds 25 m / s, the lateral acceleration (vehicle speed * yaw rate) at the reference point and the actual vehicle is calculated. If either of the two absolute acceleration values ​​exceeds a set threshold, it is considered a curve; otherwise, it is a straight-line driving condition. The curvature and lateral acceleration thresholds used in the above judgment conditions can be selected by observing test data of actual vehicles in straight-line and curve conditions. Vehicle speed is used first here because the curvature is very small during high-speed straight-line driving, and the curvature accuracy of the reference point on the planned trajectory is insufficient; therefore, lateral acceleration is used instead.

[0062] The method for determining the triggered driving mode is to check if the current steering wheel angle is within a reasonable range, i.e., calculating the upper and lower bounds of the angle. If the current steering wheel angle is detected to be within this range, it is considered that human-machine co-driving has not been triggered (the algorithm is controlling the vehicle normally); otherwise, human-machine co-driving has been triggered. The most direct way to calculate the upper and lower bounds is to add or subtract a value (minimum bandwidth) from the previous cycle's command. However, in practice, due to the delay in the actuator (when responding to high-speed conditions, the difference between the angle and the command is proportional to the speed), simply calculating the upper and lower bounds according to a fixed bandwidth (that is, the value mentioned above that is added / subtracted) (using it as the initial value) is insufficient. At this point, it is necessary to calculate an additional predicted steering wheel angle, compare the predicted angle with the initial upper and lower bounds, and select the larger value for the upper bound and the smaller value for the lower bound.

[0063] Step 204: If the vehicle does not trigger the human-machine co-driving mode and the delay counter reaches the additional delay duration, update the steering wheel zero-offset angle according to the lateral offset error integrator; the additional delay duration is obtained by the vehicle each time it switches from the human-machine co-driving mode to the normal driving mode, based on the trigger duration of the human-machine co-driving mode; the delay counter starts counting each time the vehicle switches from the human-machine co-driving mode to the normal driving mode.

[0064] The lateral offset error integrator is obtained as follows: the integral gain is obtained based on the vehicle speed and curvature; the lateral offset error of the vehicle is obtained based on the vehicle's autonomous driving system; the lateral offset error is used to characterize the degree of difference between the planned driving route of the autonomous driving system and the actual driving route of the vehicle; the lateral offset error integrator is constructed based on the product of the integral gain and the lateral offset error.

[0065] Optionally, when the vehicle triggers the human-machine co-driving mode, the update of the steering wheel zero angle is stopped, and the latest updated steering wheel zero angle remains unchanged; when the vehicle does not switch driving modes, the latest predicted steering wheel angle is obtained based on the vehicle's autonomous driving system, and the process returns to the step of judging the vehicle's driving status.

[0066] Specifically, if the vehicle does not trigger the human-machine co-driving mode and the delay counter reaches the additional delay duration, it is determined that the update condition for the straight-line zero-angle is met. The lateral offset error integrator is then called to update the straight-line steering wheel zero-angle, as shown in the following formula:

[0067] δ offset =δ offset +l e *gain,

[0068] Among them, l eLet 'gain' represent the lateral offset error. The above formula is essentially a simplified integrator, where the integral gain is designed to be proportional to vehicle speed and curvature. The formula shows that the greater the vehicle speed and curvature, the faster the zero-offset angle is updated; the greater the lateral offset, the more the zero-offset angle is integrated. Initially, the zero-offset angle is set to 0, and the car will gradually deviate from its trajectory. However, the integral effect of the lateral error will cause the steering wheel angle to gradually approach the true zero-offset angle until the vehicle is driving stably with no error (or very little error). This is the principle behind the integrator's adaptive zero-offset angle update.

[0069] If the update conditions for zero-angle are not met, i.e., the human-machine co-driving mode is triggered or the delay counter has not reached the additional delay duration, the steering wheel zero-angle remains unchanged. When human-machine co-driving is detected (steering wheel angle cannot properly track the command), the remedial logic is to freeze the zero-angle instead of resetting it directly to 0, to prevent the zero-angle from changing abruptly.

[0070] The method to determine when the delay counter reaches the additional delay duration is that whenever the additional delay duration is acquired, the delay counter will start from the beginning and automatically decrement by 1 in each cycle. Simply monitor whether the value of the delay counter is 0. As long as the additional delay duration is acquired, the delay counter will start and automatically decrement by 1 in each cycle.

[0071] Step 206: If the vehicle does not switch driving modes, obtain the latest predicted steering wheel angle based on the vehicle's autonomous driving system, and return to the step of determining the vehicle's driving status.

[0072] Optionally, when the vehicle switches from normal driving mode to human-machine co-driving mode, the initial moment of human-machine co-driving is obtained; based on the vehicle's autonomous driving system, the latest predicted steering wheel angle is obtained, and the process returns to the step of judging the vehicle's driving status.

[0073] Alternatively, when the vehicle switches from human-machine co-driving mode to normal driving mode, based on the initial moment of human-machine co-driving, obtain the trigger duration of the human-machine co-driving mode, update the additional delay duration based on the trigger duration; based on the vehicle's autonomous driving system, obtain the latest predicted steering wheel angle, and return to execute the step of judging the vehicle's driving status.

[0074] Specifically, the system determines whether the vehicle has switched from normal driving mode to human-machine co-driving mode, i.e., whether the steering wheel tracking command has switched from normal to abnormal, where the previous steering wheel angle tracking command was recognized as normal, but the current one is abnormal. Alternatively, the system determines whether the vehicle has switched from human-machine co-driving mode to normal driving mode, i.e., whether the steering wheel tracking command has switched from abnormal to normal, where the previous steering wheel angle tracking command was recognized as abnormal, but the current one is normal.

[0075] If the vehicle switches from normal driving mode to human-machine co-driving mode, the current time is recorded as the initial moment when human-machine co-driving is triggered.

[0076] If the vehicle switches from human-machine co-driving mode to normal driving mode, the trigger duration of the human-machine co-driving mode is calculated based on the latest recorded initial time of human-machine co-driving. The latest additional delay duration is then obtained. After obtaining the latest additional delay duration, it is converted into a cycle number, and the delay counter is reset.

[0077] At the end of each judgment cycle, the predicted steering wheel angle for the next cycle is estimated. A simple model of the steering mechanism is constructed using a first-order inertial element, as shown in the following formula:

[0078]

[0079] Where τ is the inertial time constant, δ f δ is the actual turning angle. d The desired steering wheel angle is the steering angle command output by the control algorithm. The above differential equation (continuous domain) is simply discretized as follows:

[0080] δ f (k+1)=δ f (k)+(δ d (k)-δ f (k))dt / τ,

[0081] Where dt is the control period, typically 20ms. By selecting an appropriate inertial time constant (e.g., 0.1s), the predicted steering wheel angle for the next period can be estimated.

[0082] The aforementioned steering wheel zero-angle update method can identify the steering wheel zero-angle without relying on additional sensor equipment, thus improving the measurement accuracy of the steering wheel zero-angle. When the true zero-angle changes due to external influences such as road inclination or mechanical structure changes, it has the ability to autonomously correct it in real time. Furthermore, when the human-machine co-driving mode is triggered, it can identify the abnormal situation and execute remedial measures, quickly restoring normal operation when the disturbance ends. This ensures that the unmanned vehicle is not negatively affected by large zero-angle errors during autonomous driving, especially during high-speed straight-line driving, thereby ensuring the stability and safety of autonomous driving.

[0083] In one embodiment, a steering wheel zero-off angle update method includes:

[0084] The integral gain is obtained based on the vehicle's speed and curvature; the lateral offset error of the vehicle is obtained based on the vehicle's autonomous driving system; the lateral offset error is used to characterize the degree of difference between the planned driving route of the autonomous driving system and the actual driving route of the vehicle; and a lateral offset error integrator is constructed based on the product of the integral gain and the lateral offset error.

[0085] The system determines the vehicle's driving status. When the vehicle is driving in a straight line, it determines the driving mode triggered by the vehicle based on the difference between the latest predicted steering wheel angle and the current steering wheel angle. The driving mode includes human-machine co-driving mode or normal driving mode.

[0086] If the vehicle is not traveling in a straight line, stop updating the steering wheel zero angle and keep the latest updated steering wheel zero angle unchanged; if the vehicle does not switch driving modes, obtain the latest predicted steering wheel angle based on the vehicle's autonomous driving system and return to the step of judging the vehicle's driving status.

[0087] When the vehicle triggers the human-machine co-driving mode, the steering wheel zero-angle update is stopped, and the latest updated steering wheel zero-angle remains unchanged; if the vehicle does not switch driving modes, the latest predicted steering wheel angle is obtained based on the vehicle's autonomous driving system, and the process returns to the step of judging the vehicle's driving status.

[0088] If the vehicle does not trigger the human-machine co-driving mode and the delay counter reaches the additional delay duration, the steering wheel zero-offset angle is updated according to the lateral offset error integrator; the additional delay duration is obtained by the vehicle each time it switches from the human-machine co-driving mode to the normal driving mode, based on the duration of the human-machine co-driving mode trigger; the delay counter starts counting down each time the vehicle switches from the human-machine co-driving mode to the normal driving mode.

[0089] If the vehicle does not switch driving modes, the system obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of determining the vehicle's driving status.

[0090] When the vehicle switches from normal driving mode to human-machine co-driving mode, obtain the initial moment of human-machine co-driving; based on the vehicle's autonomous driving system, obtain the latest predicted steering wheel angle, and return to execute the step of judging the vehicle's driving status.

[0091] When the vehicle switches from human-machine co-driving mode to normal driving mode, the trigger duration of the human-machine co-driving mode is obtained based on the initial moment of human-machine co-driving, and the additional delay duration is updated based on the trigger duration; based on the vehicle's autonomous driving system, the latest predicted steering wheel angle is obtained, and the process returns to the step of judging the vehicle's driving status.

[0092] In one exemplary embodiment, such as Figure 3 As shown, a method for updating the zero-offset angle of a steering wheel includes steps 301 to 310. Wherein:

[0093] Step 301: Algorithm initialization, including setting the initial zero deflection angle and the additional delay counter to 0, setting the previous steering angle control command and predicted steering wheel angle to the current actual steering wheel angle, initializing the steering angle tracking status to normal, and setting the initial time of triggering human-machine co-driving (steering angle tracking abnormality) to the current time.

[0094] Step 302: Determine if the vehicle is traveling in a straight line. Specifically, if the vehicle speed is less than 25 m / s, extract the curvature of the reference point on the current planned trajectory. If the absolute value of this curvature is less than a set threshold, it is considered a straight-line condition; otherwise, it is a curve. If the vehicle speed exceeds 25 m / s, calculate the lateral acceleration (vehicle speed * yaw rate) at the reference point and the actual vehicle. If either of the two absolute acceleration values ​​exceeds a set threshold, it is considered a curve; otherwise, it is a straight-line condition. The curvature and lateral acceleration thresholds used in the above judgment conditions can be selected by observing test data of the actual vehicle in straight-line and curve conditions. The vehicle speed is judged first here because the curvature is very small during high-speed straight-line travel, and the curvature accuracy of the reference point on the planned trajectory is insufficient; therefore, lateral acceleration is used instead.

[0095] Step 303: Determine if human-machine co-driving is triggered. In this mode, if the state machine does not determine that the driver has taken over, the steering wheel angle is affected by the driver and cannot track the control command. The vehicle slowly deviates from the trajectory, causing the lateral error to change in an undesirable direction at this stage. This leads to the steering wheel zero-angle being updated in the wrong direction in step 304. Therefore, this judgment must be made before updating the zero-angle. The most direct idea for determining whether human-machine co-driving is triggered is to determine whether the current steering wheel angle is within a reasonable range, i.e., to calculate the upper and lower bounds of the angle. If the current steering wheel angle is detected to be within this range, it is considered that human-machine co-driving has not been triggered (the algorithm controls the vehicle normally); otherwise, human-machine co-driving has been triggered. The most direct way to calculate the upper and lower bounds is to add or subtract a value (minimum bandwidth) from the command of the previous cycle. In practice, due to the delay of the actuator (when responding to high-speed conditions, the difference between the angle and the command is proportional to the speed), it is not enough to calculate the upper and lower bounds only according to a fixed bandwidth (that is, the value mentioned above that is added / subtracted) (using it as the initial value). At this point, an additional predicted turning angle needs to be calculated (described in detail in step 3012). This predicted turning angle is compared with the initial upper and lower bounds; the larger value is selected for the upper bound, and the smaller value for the lower bound. A schematic diagram illustrating the above process is shown below. Figures 4-5 In the diagram, viewed from the right, the top and bottom lines represent the upper and lower limits of the real-time calculation, respectively, while the middle line represents the actual steering wheel angle.

[0096] Determining whether the additional delay has ended is relatively simple: just monitor whether the value of the delay counter is 0. Once the counter is started, it automatically decrements by 1 each cycle.

[0097] Step 304: After satisfying the update conditions for the straight-line zero deflection angle, call the lateral offset error integrator to update the straight-line steering wheel zero deflection angle, as shown in the following formula.

[0098] δ offset =δ offset +l e *gain

[0099] Among them, l e Let 'gain' represent the lateral offset error. The above formula is essentially a simplified integrator, where the integral gain is designed to be proportional to vehicle speed and curvature. The formula shows that the greater the vehicle speed and curvature, the faster the zero-offset angle is updated; the greater the lateral offset, the more the zero-offset angle is integrated. Initially, the zero-offset angle is set to 0, and the car will gradually deviate from its trajectory. However, the integral effect of the lateral error will cause the steering wheel angle to gradually approach the true zero-offset angle until the vehicle is driving stably with no error (or very little error). This is the principle behind the integrator's adaptive zero-offset angle update.

[0100] Step 305: If the update conditions for zero-offset angle are not met (i.e., human-machine co-driving is triggered or the additional delay has not been completed), the steering wheel zero-offset angle remains unchanged. When human-machine co-driving is detected (steering wheel angle cannot properly track the command), the remedial logic is to freeze the zero-offset angle instead of resetting it directly to 0, to prevent the zero-offset angle from changing abruptly.

[0101] Step 306: Determine whether the vehicle has switched from normal driving to human-machine co-driving, that is, whether the steering wheel has switched from normal tracking command to abnormal. The previous steering wheel angle tracking command recognition result was normal, while the current result is abnormal.

[0102] Step 307: If the judgment condition of step 306 is met, then record the current time as the initial moment of triggering human-machine co-driving.

[0103] Step 308: Determine whether the vehicle has switched from human-machine co-driving to normal driving, that is, whether the steering wheel has switched from abnormal tracking command to normal. The previous steering wheel angle tracking command identification result was abnormal, while the current result is normal.

[0104] Step 309: The judgment condition of Step 308 is met. At this time, the lateral offset error is often large (considering that the error change lags behind the vehicle driving action). Even if the human-machine co-driving has been disengaged and the steering wheel angle control has returned to normal, there will still be a delay before the zero offset angle can start working. The key point of Step 30 is how to calculate the above-mentioned delay time. Calculating the delay time involves two aspects: one is the confidence of the time. If the large lateral error is indeed caused by the triggering of human-machine co-driving (steering wheel angle tracking abnormality), the confidence of the delay time will be high. The method to judge the confidence is to check the time when human-machine co-driving (steering wheel angle tracking abnormality) is triggered (subtract the value recorded in Step 307 from the current time). Here, the confidence is set to be proportional to the time of the steering wheel tracking abnormality (an upper limit can be set; if the upper limit is exceeded, the confidence will always be 1). The advantage of this design is that if there is a misidentification of human-machine co-driving, considering that the misidentification time is usually short, the confidence level will be very small, and the subsequent calculation delay time will also be short, reducing the impact of misidentification on the zero-offset adaptive update function.

[0105] On the other hand, it's about estimating how long it will take for the current lateral error to converge to within the expected value at the current vehicle speed; this time is the required delay. The time required for the vehicle to return to the expected lateral error range through its own control action when it's at the reference speed and within the system's maximum permissible lateral offset error is used as the reference delay. For example, at a speed of 20 m / s, it takes approximately 2 seconds for the error to converge from its maximum value of 0.5 m to 0.1 m (the expected value). If the error when the steering wheel resumes corner tracking at this speed is 0.3 m, the delay time is approximately 1 second (assuming a linear relationship between convergence time and error). If the confidence level at this point is 1, then the final output delay time is 1 second * 1 = 1 second. After obtaining the delay duration, it is converted into a number of cycles, and the delay counter is reset.

[0106] Step 310: Estimate the predicted steering wheel angle for the next cycle. A first-order inertial element is used here to model the steering mechanism simply, as shown in the following formula:

[0107]

[0108] Where τ is the inertial time constant, δ f δ is the actual turning angle. d The desired steering wheel angle is the angle command output by the control algorithm. Here, the control command, in trigonometric function form, is used as input, and a first-order inertial element is used to simulate the steering wheel angle tracking process, such as... Figure 6 As shown.

[0109] The above differential equation (continuous domain) can be discretized simply as follows:

[0110] δ f (k+1)=δf (k)+(δ d (k)-δ f (k))dt / τ

[0111] Where dt is the control period, typically 20ms. By selecting a suitable inertial time constant (e.g., 0.1s), the predicted steering wheel angle for the next period can be estimated. The predicted steering wheel angle serves as the input data for determining the steering wheel tracking state in step 303. Other variables, such as the control command from the previous moment and the tracking state, are also updated in this step.

[0112] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0113] Based on the same inventive concept, this application also provides a steering wheel zero-angle update device for implementing the aforementioned steering wheel zero-angle update method. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more steering wheel zero-angle update device embodiments provided below can be found in the limitations of the steering wheel zero-angle update method described above, and will not be repeated here.

[0114] In one exemplary embodiment, such as Figure 7 As shown, a steering wheel zero-off-angle update device 700 is provided, including: a determination module 701, an update module 702, and an iteration module 703, wherein:

[0115] The determination module 701 is used to determine the driving status of the vehicle. When the vehicle is driving in a straight line, it determines the driving mode triggered by the vehicle based on the degree of difference between the latest predicted steering wheel angle and the current steering wheel angle. The driving mode includes human-machine co-driving mode or normal driving mode.

[0116] The update module 702 is used to update the steering wheel zero angle based on the lateral offset error integrator when the vehicle has not triggered the human-machine co-driving mode and the delay counter has reached the additional delay duration. The additional delay duration is obtained by the vehicle each time it switches from the human-machine co-driving mode to the normal driving mode, based on the duration of the human-machine co-driving mode trigger. The delay counter starts counting down each time the vehicle switches from the human-machine co-driving mode to the normal driving mode.

[0117] The iteration module 703 is used to obtain the latest predicted steering wheel angle based on the vehicle's autonomous driving system when the vehicle has not switched driving modes, and then return to the step of judging the vehicle's driving status.

[0118] In one embodiment, the iteration module 703 is further configured to stop updating the steering wheel zero angle and keep the latest updated steering wheel zero angle unchanged when the vehicle is not in a straight driving state; and to obtain the latest predicted steering wheel angle based on the vehicle's autonomous driving system and return to the step of judging the vehicle's driving state when the vehicle has not changed driving modes.

[0119] In one embodiment, the iteration module 703 is further configured to stop updating the steering wheel zero angle and keep the latest updated steering wheel zero angle unchanged when the vehicle triggers the human-machine co-driving mode; and to obtain the latest predicted steering wheel angle based on the vehicle's autonomous driving system and return to the step of judging the vehicle's driving status when the vehicle does not switch driving modes.

[0120] In one embodiment, the iteration module 703 is further configured to obtain the initial moment of human-machine co-driving when the vehicle switches from normal driving mode to human-machine co-driving mode; based on the vehicle's autonomous driving system, obtain the latest predicted steering wheel angle, and return to the step of judging the vehicle's driving status.

[0121] In one embodiment, the iteration module 703 is further configured to, when the vehicle switches from human-machine co-driving mode to normal driving mode, obtain the trigger duration of the human-machine co-driving mode based on the initial moment of human-machine co-driving, update the additional delay duration based on the trigger duration, obtain the latest predicted steering wheel angle based on the vehicle's autonomous driving system, and return to the step of judging the vehicle's driving status.

[0122] In one embodiment, the update module 702 is further configured to obtain an integral gain based on the vehicle speed and curvature; obtain the lateral offset error of the vehicle based on the vehicle's autonomous driving system; the lateral offset error is used to characterize the degree of difference between the planned driving route of the autonomous driving system and the actual driving route of the vehicle; and construct a lateral offset error integrator based on the product of the integral gain and the lateral offset error.

[0123] Each module in the aforementioned steering wheel zero-off-angle update device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0124] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores steering wheel zero-angle data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a steering wheel zero-angle update method.

[0125] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0126] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: determining the driving state of a vehicle; if the vehicle is in a straight-line driving state, determining the driving mode triggered by the vehicle based on the degree of difference between the latest acquired predicted steering wheel angle and the current steering wheel angle; the driving mode includes a human-machine co-driving mode or a normal driving mode; if the vehicle has not triggered the human-machine co-driving mode and the delay counter has reached the additional delay duration, updating the steering wheel zero-offset angle based on the lateral offset error integrator; the additional delay duration is obtained based on the trigger duration of the human-machine co-driving mode each time the vehicle switches from the human-machine co-driving mode to the normal driving mode; the delay counter starts counting each time the vehicle switches from the human-machine co-driving mode to the normal driving mode; if the vehicle has not switched driving modes, obtaining the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returning to the step of determining the driving state of the vehicle.

[0127] In one embodiment, when the processor executes the computer program, it further performs the following steps: when the vehicle is not driving in a straight line, it stops updating the steering wheel zero angle and keeps the latest updated steering wheel zero angle unchanged; when the vehicle does not switch driving modes, it obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of judging the vehicle's driving status.

[0128] In one embodiment, when the processor executes the computer program, it further implements the following steps: when the vehicle triggers the human-machine co-driving mode, it stops updating the steering wheel zero angle and keeps the latest updated steering wheel zero angle unchanged; when the vehicle does not switch driving modes, it obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of judging the vehicle's driving status.

[0129] In one embodiment, when the processor executes the computer program, it further implements the following steps: when the vehicle switches from normal driving mode to human-machine co-driving mode, it obtains the initial moment of human-machine co-driving; based on the vehicle's autonomous driving system, it obtains the latest predicted steering wheel angle and returns to the step of determining the vehicle's driving status.

[0130] In one embodiment, when the processor executes the computer program, it further implements the following steps: when the vehicle switches from human-machine co-driving mode to normal driving mode, based on the initial moment of human-machine co-driving, it obtains the trigger duration of the human-machine co-driving mode and updates the additional delay duration based on the trigger duration; based on the vehicle's autonomous driving system, it obtains the latest predicted steering wheel angle and returns to the step of judging the vehicle's driving status.

[0131] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining an integral gain based on the vehicle's speed and curvature; obtaining the lateral offset error of the vehicle's driving based on the vehicle's autonomous driving system; the lateral offset error is used to characterize the degree of difference between the planned driving route of the autonomous driving system and the actual driving route of the vehicle; and constructing a lateral offset error integrator based on the product of the integral gain and the lateral offset error.

[0132] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When executed by a processor, the computer program performs the following steps: determining the driving state of the vehicle; if the vehicle is in a straight-line driving state, determining the driving mode triggered by the vehicle based on the degree of difference between the latest predicted steering wheel angle and the current steering wheel angle; the driving mode includes a human-machine co-driving mode or a normal driving mode; if the vehicle has not triggered the human-machine co-driving mode and the delay counter has reached the additional delay duration, updating the steering wheel zero-offset angle based on the lateral offset error integrator; the additional delay duration is obtained based on the trigger duration of the human-machine co-driving mode each time the vehicle switches from the human-machine co-driving mode to the normal driving mode; the delay counter starts counting each time the vehicle switches from the human-machine co-driving mode to the normal driving mode; if the vehicle has not switched driving modes, obtaining the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returning to the step of determining the driving state of the vehicle.

[0133] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: when the vehicle is not in a straight-line driving state, it stops updating the steering wheel zero angle and keeps the latest updated steering wheel zero angle unchanged; when the vehicle does not switch driving modes, it obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of judging the vehicle's driving state.

[0134] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: when the vehicle triggers the human-machine co-driving mode, it stops updating the steering wheel zero angle and keeps the latest updated steering wheel zero angle unchanged; when the vehicle does not switch driving modes, it obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of judging the vehicle's driving status.

[0135] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: when the vehicle switches from normal driving mode to human-machine co-driving mode, it obtains the initial moment of human-machine co-driving; based on the vehicle's autonomous driving system, it obtains the latest predicted steering wheel angle and returns to the step of judging the vehicle's driving status.

[0136] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: when the vehicle switches from human-machine co-driving mode to normal driving mode, based on the initial moment of human-machine co-driving, obtains the trigger duration of the human-machine co-driving mode, and updates the additional delay duration based on the trigger duration; based on the vehicle's autonomous driving system, obtains the latest predicted steering wheel angle, and returns to the step of judging the vehicle's driving status.

[0137] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining an integral gain based on the vehicle's speed and curvature; obtaining the lateral offset error of the vehicle's driving based on the vehicle's autonomous driving system; the lateral offset error is used to characterize the degree of difference between the planned driving route of the autonomous driving system and the actual driving route of the vehicle; and constructing a lateral offset error integrator based on the product of the integral gain and the lateral offset error.

[0138] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: determining the driving state of a vehicle; if the vehicle is in a straight-line driving state, determining the driving mode triggered by the vehicle based on the degree of difference between the latest acquired predicted steering wheel angle and the current steering wheel angle; the driving mode includes a human-machine co-driving mode or a normal driving mode; if the vehicle has not triggered the human-machine co-driving mode and the delay counter has reached the additional delay duration, updating the steering wheel zero-offset angle based on the lateral offset error integrator; the additional delay duration is obtained based on the trigger duration of the human-machine co-driving mode each time the vehicle switches from the human-machine co-driving mode to the normal driving mode; the delay counter starts counting each time the vehicle switches from the human-machine co-driving mode to the normal driving mode; if the vehicle has not switched driving modes, obtaining the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returning to the step of determining the driving state of the vehicle.

[0139] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: when the vehicle is not in a straight-line driving state, it stops updating the steering wheel zero angle and keeps the latest updated steering wheel zero angle unchanged; when the vehicle does not switch driving modes, it obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of judging the vehicle's driving state.

[0140] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: when the vehicle triggers the human-machine co-driving mode, it stops updating the steering wheel zero angle and keeps the latest updated steering wheel zero angle unchanged; when the vehicle does not switch driving modes, it obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of judging the vehicle's driving status.

[0141] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: when the vehicle switches from normal driving mode to human-machine co-driving mode, it obtains the initial moment of human-machine co-driving; based on the vehicle's autonomous driving system, it obtains the latest predicted steering wheel angle and returns to the step of judging the vehicle's driving status.

[0142] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: when the vehicle switches from human-machine co-driving mode to normal driving mode, based on the initial moment of human-machine co-driving, obtains the trigger duration of the human-machine co-driving mode, and updates the additional delay duration based on the trigger duration; based on the vehicle's autonomous driving system, obtains the latest predicted steering wheel angle, and returns to the step of judging the vehicle's driving status.

[0143] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining an integral gain based on the vehicle's speed and curvature; obtaining the lateral offset error of the vehicle's driving based on the vehicle's autonomous driving system; the lateral offset error is used to characterize the degree of difference between the planned driving route of the autonomous driving system and the actual driving route of the vehicle; and constructing a lateral offset error integrator based on the product of the integral gain and the lateral offset error.

[0144] 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, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0145] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile 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 many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0146] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 specification.

[0147] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method of updating a zero angle of a steering wheel, characterized by, The method includes: The vehicle's driving status is determined. When the vehicle is driving in a straight line, the driving mode triggered by the vehicle is determined based on the degree of difference between the latest predicted steering wheel angle and the current steering wheel angle. The driving mode includes human-machine co-driving mode or normal driving mode. If the vehicle does not trigger the human-machine co-driving mode and the delay counter reaches the additional delay duration, the steering wheel zero-angle is updated according to the lateral offset error integrator; the additional delay duration is obtained by the vehicle each time it switches from the human-machine co-driving mode to the normal driving mode, based on the trigger duration of the human-machine co-driving mode; the delay counter starts counting each time the vehicle switches from the human-machine co-driving mode to the normal driving mode. If the vehicle does not switch driving modes, the system obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of determining the vehicle's driving status.

2. The method of claim 1, wherein, The method further includes: When the vehicle is not traveling in a straight line, stop updating the steering wheel zero-off angle and keep the latest updated steering wheel zero-off angle unchanged. If the vehicle does not switch driving modes, the system obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of determining the vehicle's driving status.

3. The method of claim 1, wherein, The method further includes: When the vehicle triggers the human-machine co-driving mode, the steering wheel zero-angle update is stopped, and the latest updated steering wheel zero-angle remains unchanged. If the vehicle does not switch driving modes, the system obtains the latest predicted steering wheel angle based on the vehicle's autonomous driving system and returns to the step of determining the vehicle's driving status.

4. The method according to claim 1, characterized in that, The method further includes: When the vehicle switches from the normal driving mode to the human-machine co-driving mode, the initial moment of human-machine co-driving is obtained; Based on the vehicle's autonomous driving system, the latest predicted steering wheel angle is obtained, and the system returns to perform the step of determining the vehicle's driving status.

5. The method according to claim 4, characterized in that, The method further includes: When the vehicle switches from the human-machine co-driving mode to the normal driving mode, the trigger duration of the human-machine co-driving mode is obtained based on the initial time of the human-machine co-driving mode, and the additional delay duration is updated based on the trigger duration. Based on the vehicle's autonomous driving system, the latest predicted steering wheel angle is obtained, and the system returns to perform the step of determining the vehicle's driving status.

6. The method according to claim 1, characterized in that, The method for obtaining the lateral offset error integrator includes: The integral gain is obtained based on the vehicle's speed and curvature. Based on the vehicle's autonomous driving system, the lateral offset error of the vehicle's driving is obtained; the lateral offset error is used to characterize the degree of difference between the planned driving route of the autonomous driving system and the actual driving route of the vehicle. The lateral offset error integrator is constructed based on the product of the integral gain and the lateral offset error.

7. A steering wheel zero-off-angle updating device, characterized in that, The device includes: The determination module is used to determine the driving status of the vehicle. When the vehicle is driving in a straight line, it determines the driving mode triggered by the vehicle based on the degree of difference between the latest predicted steering wheel angle and the current steering wheel angle. The driving mode includes human-machine co-driving mode or normal driving mode. The update module is used to update the steering wheel zero-offset angle according to the lateral offset error integrator when the vehicle has not triggered the human-machine co-driving mode and the delay counter has reached the additional delay duration; the additional delay duration is obtained by the vehicle each time it switches from the human-machine co-driving mode to the normal driving mode, based on the trigger duration of the human-machine co-driving mode; the delay counter starts counting each time the vehicle switches from the human-machine co-driving mode to the normal driving mode; The iteration module is used to obtain the latest predicted steering wheel angle based on the vehicle's autonomous driving system, and return to the step of determining the vehicle's driving status, if the vehicle does not switch driving modes.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images