Automatic driving vehicle neutral position control method and system
By using the steering median controller and sensor system in autonomous driving vehicles, combined with camera signals, accurately judge the straight driving state of the vehicle and optimize the lateral control, the problem of inaccurate judgment of the steering median value in the prior art is solved, and driving safety and stability are improved.
Patent Information
- Application Number
- CN202411964966.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-04-18
AI Technical Summary
The prior art is difficult to accurately judge the median steering value of autonomous driving vehicles, resulting in a degradation of lateral control performance and affecting driving safety and stability.
By using the steering median controller to read the historical learning value, combining the body posture sensor, vehicle speed and camera signal, we can determine whether the vehicle is in a straight state, and use the steering wheel angle to perform median learning to determine the steering median deviation learning value. At the same time, it continuously detects whether the median steering deviation learning value exceeds the preset alarm threshold and resets the median steering when a specific condition is met.
It effectively improves the accuracy and range of judgment of linear driving conditions, ensures the accuracy of the median steering value, improves the lateral control performance of the vehicle, thereby improving driving safety and stability, and promptly warns the driver of possible vehicle status abnormalities.
Smart Images
Figure CN119840656A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method and system for controlling a neutral position of an autonomous driving vehicle. Background Art
[0002] During the production and use of vehicles, the steering center position will cause the vehicle's lateral control performance to deteriorate due to precision and mechanical changes during production, resulting in a worse driving feel.
[0003] In the prior art, hand force, wheel speed or camera is used to judge straight-line driving. However, if hand force, wheel speed or camera is used for learning, it cannot be guaranteed that the accurate median value can be learned during lateral control due to hand force. At the same time, even with the addition of a camera, it is impossible to identify the situation where the vehicle is in the lane but not driving in a straight line. In the prior art, the steering median deviation learning value is also used for manual calibration, but the efficiency of calibration cannot be guaranteed, and the operation requirements are high. In the prior art, the steering median deviation learning value is also used for lateral control, but the steering median is not recalibrated, the median may become very large, and it is ultimately impossible to determine whether it is a learning error or the actual state.
[0004] Therefore, how to solve the problem in the prior art that the value of the steering center position cannot be accurately determined, thereby improving the lateral control performance of the vehicle and improving driving safety and stability, is a technical problem that needs to be urgently solved by those skilled in the art. Summary of the invention
[0005] To achieve the purpose of the present invention, the present application provides a method for controlling a neutral position of an autonomous driving vehicle, comprising:
[0006] Step S1: using the steering neutral controller to read the historical learning value;
[0007] Step S2: judging whether the vehicle is in a straight-ahead state according to the value of the vehicle posture sensor, the vehicle speed and the camera signal; if the vehicle is in a straight-ahead state, performing median learning using the steering wheel angle to determine a steering median deviation learning value;
[0008] Step S3: using the steering median deviation learning value to update the historical learning value;
[0009] Step S4: using the steering median controller to continuously optimize lateral control according to the steering median deviation learning value;
[0010] Step S5: continuously detecting whether the steering median deviation learning value exceeds a preset alarm threshold value, and if the steering median deviation learning value exceeds the preset alarm threshold value, notifying an alarm device to alarm;
[0011] Step S6: continuously detecting whether the neutral reset condition is met, and if so, using the steering neutral controller to control the steering machine to reset the steering neutral position; if the steering machine feedback is successful, clearing the steering neutral deviation learning value.
[0012] In some specific embodiments, step S1 includes:
[0013] If there is no historical learning value, a new learning value is assigned; if there is, the historical learning value is updated.
[0014] In some specific embodiments, step S2 includes: the median learning includes:
[0015] The vehicle's yaw rate and roll angle are read through the body posture sensor and the steering center controller. If the yaw rate and roll angle do not exceed the threshold, it is determined that the vehicle is not in a turning state and the body is not tilted;
[0016] The curvature of the lane line is identified through a camera and a steering center controller. If the curvature does not exceed a threshold, it is determined that the vehicle is traveling in a straight lane.
[0017] The hand force and the steering center controller are used to determine whether the driver is turning the steering wheel. If the steering wheel is not turned, it is determined that the vehicle is driving in a straight line.
[0018] In some specific embodiments, step S2 includes: if the vehicle is traveling straight in a straight lane, starting timing; if there is no lane line, determining whether the vehicle is traveling in a straight line based on a steering wheel hand force signal, and if the vehicle is traveling in a straight line, starting timing; if the timing exceeds a calibratable threshold, using the steering wheel angle for learning.
[0019] In some specific embodiments, step S4 further includes:
[0020] If there is no steering median deviation learning value, the steering median deviation learning value is defaulted to 0.
[0021] In some specific embodiments, step S6 includes: the neutral reset condition is: the vehicle speed is 0, the engine is in the starting state and the gear position needs to be in neutral or parking.
[0022] In some specific embodiments, step S6 includes: when resetting the neutral position, the steering neutral position controller sends the steering neutral position deviation learning value to the steering machine, and the steering machine resets the neutral position using the steering neutral position deviation learning value.
[0023] To achieve the same invention purpose, the present application also provides a mid-position control system for an autonomous driving vehicle, comprising:
[0024] Value reading module: used to read historical learning values using the steering neutral controller;
[0025] Numerical update module: used to determine whether the vehicle is in a straight-ahead state based on the value of the body posture sensor, vehicle speed and camera signal. If the vehicle is in a straight-ahead state, the steering wheel angle is used for median learning to determine the steering median deviation learning value;
[0026] A numerical updating module: used for updating a historical learning value using the steering median deviation learning value;
[0027] A control optimization module: used for continuously optimizing lateral control according to the steering median deviation learning value by using the steering median controller;
[0028] Alarm module: used for continuously detecting whether the steering median deviation learning value exceeds a preset alarm threshold value, and notifying an alarm device to alarm if the steering median deviation learning value exceeds the preset alarm threshold value;
[0029] Numerical reset module: used to continuously detect whether the neutral reset condition is met. If so, the steering neutral controller is used to control the steering machine to reset the steering neutral position; if the steering machine feedback is successful, the steering neutral deviation learning value is cleared.
[0030] In some specific embodiments, in the value updating module, the median learning includes:
[0031] The vehicle's yaw rate and roll angle are read through the body posture sensor and the steering center controller. If the yaw rate and roll angle do not exceed the threshold, it is determined that the vehicle is not in a turning state and the body is not tilted;
[0032] The curvature of the lane line is identified through a camera and a steering center controller. If the curvature does not exceed a threshold, it is determined that the vehicle is traveling in a straight lane.
[0033] The hand force and the steering center controller are used to determine whether the driver is turning the steering wheel. If the steering wheel is not turned, it is determined that the vehicle is driving in a straight line.
[0034] In some specific embodiments, the numerical update module is used to perform the following steps: if the vehicle is driving straight in a straight lane, start timing; if there is no lane line, determine whether the vehicle is driving in a straight line based on the steering wheel hand force signal, and if the vehicle is driving in a straight line, start timing; if the timing exceeds a calibratable threshold, use the steering wheel angle for learning.
[0035] Beneficial effects of the above technical solution:
[0036] The present application provides a method and system for controlling the median position of an autonomous driving vehicle. Based on the posture of the vehicle body, the system determines whether the vehicle is in a turning state, and determines whether it is in a straight lane by taking an image with a camera. This system can effectively determine whether the vehicle is in a straight-line driving state under all working conditions. When the lane line is not good, the vehicle body posture and hand strength can also be used to determine whether the vehicle is in a straight-line driving state. The accuracy and range of the judgment of straight-line driving can be effectively improved. In addition, the present application determines that the vehicle is in a stationary state and uses the steering median deviation learning value for calibration. It can repair the state in time when there is a small offset, thereby avoiding the situation where the steering median deviation learning value is too large, resulting in the inability to identify the fault. In addition, the present application also warns the driver when the median value is too large or suddenly changes, which helps the driver to identify the vehicle state and avoid danger. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0038] Figure 1 A schematic flow chart of a method for controlling a neutral position of an autonomous driving vehicle provided by an embodiment of the present invention;
[0039] Figure 2 A schematic structural diagram of a neutral control system for an autonomous driving vehicle provided in accordance with an embodiment of the present invention. DETAILED DESCRIPTION
[0040] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.
[0041] Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar symbols throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.
[0042] Embodiment 1
[0043] An embodiment of the present invention provides a method for controlling a mid-position of an autonomous driving vehicle, referring to Figure 1 As shown, including:
[0044] Step S1: Use the steering neutral controller to read the historical learning value.
[0045] In a specific embodiment of the present invention, step S1 includes:
[0046] If there is no historical learning value, a new learning value is assigned; if there is, the historical learning value is updated.
[0047] Step S2: using the steering median controller to determine whether the vehicle is in a straight-ahead state based on the value of the vehicle body posture sensor, the vehicle speed and the camera signal; if in a straight-ahead state, using the steering wheel angle for median learning to determine the steering median deviation learning value.
[0048] In a specific embodiment of the present invention, step S2 includes: the median learning includes:
[0049] The vehicle's yaw rate and roll angle are read through the body posture sensor and the steering center controller. If the yaw rate and roll angle do not exceed the threshold, it is determined that the vehicle is not in a turning state and the body is not tilted;
[0050] The curvature of the lane line is identified through a camera and a steering center controller. If the curvature does not exceed a threshold, it is determined that the vehicle is traveling in a straight lane.
[0051] The hand force and the steering center controller are used to determine whether the driver is turning the steering wheel. If the steering wheel is not turned, it is determined that the vehicle is driving in a straight line.
[0052] Specifically, the vehicle posture sensor is used to detect the yaw rate and the roll angle of the vehicle body; the camera is used to observe the lane line, and the vehicle speed needs to be greater than a threshold, at which point the accuracy of the yaw rate is sufficiently accurate.
[0053] Furthermore, after the median learning condition is met, the time when the condition is met needs to be recorded. If the time exceeds the threshold, the steering wheel angle during this period is processed according to the vehicle state estimation algorithm and the filtering algorithm to obtain the steering median deviation learning value. The vehicle state estimation algorithm establishes the vehicle state equation and iteratively updates the steering median according to the vehicle state. The filtering algorithm uses weighted average filtering.
[0054] In a specific embodiment of the present invention, step S2 includes: if the vehicle is traveling in a straight lane, start timing; if there is no lane line, determine whether the vehicle is traveling in a straight line according to the steering wheel hand force signal, and if the vehicle is traveling in a straight line, start timing; if the timing exceeds a calibratable threshold, use the steering wheel angle for learning. The steering wheel angle can be learned using a state observer or a filter.
[0055] Step S3: Using the steering median deviation learning value to update the historical learning value.
[0056] Specifically, if there is a historical learning value, the historical learning value is directly updated; if there is no historical learning value, the current steering median deviation learning value is directly used as the historical learning value before the next update.
[0057] Step S4: Utilizing the steering median controller to continuously optimize lateral control according to the steering median deviation learning value, that is, subtracting the steering median deviation learning value from the final steering control instruction, and then performing lateral control on the vehicle.
[0058] In a specific embodiment of the present invention, step S4 further includes:
[0059] If there is no steering median deviation learning value, the steering median deviation learning value is defaulted to 0.
[0060] Step S5: continuously detecting whether the steering median deviation learning value exceeds a preset alarm threshold, and notifying an alarm device to alarm if the steering median deviation learning value exceeds the preset alarm threshold. If there is no steering median deviation learning value, the steering median deviation learning value is assumed to be 0.
[0061] Step S6: continuously detecting whether the neutral reset condition is met, and if so, using the steering neutral controller to control the steering machine to reset the steering neutral position; if the steering machine feedback is successful, clearing the steering neutral deviation learning value.
[0062] In a specific embodiment of the present invention, step S6 includes: the neutral reset condition is: the vehicle speed is 0, the engine is in the starting state, and the gear position needs to be in neutral or parking gear. The engine is in the starting state to avoid reset failure. The gear position needs to be in neutral or parking gear, and the handbrake is pulled to avoid sudden start of the vehicle.
[0063] In a specific embodiment of the present invention, step S6 includes: when resetting the median position, the steering median controller sends the steering median deviation learning value to the steering machine, and the steering machine uses the steering median deviation learning value to reset the median position. When updating the historical learning value, weighted averaging or direct replacement of the historical learning value can be used.
[0064] The present application provides a method for controlling the median position of an autonomous driving vehicle. The method determines whether the vehicle is in a turning state based on the vehicle body posture, and determines whether it is in a straight lane by taking an image with a camera. The method can effectively determine whether the vehicle is in a straight driving state under all working conditions. When the lane line is not good, the vehicle body posture and hand strength can also be used to determine whether the vehicle is in a straight driving state. The accuracy and range of the judgment of straight driving can be effectively improved. In addition, the present application determines that the vehicle is in a stationary state and uses the steering median deviation learning value for calibration. It can repair the state in time when there is a small offset, thereby avoiding the situation where the steering median deviation learning value is too large, resulting in the inability to identify the fault. In addition, the present application also warns the driver when the median value is too large or suddenly changes, which helps the driver to identify the vehicle state and avoid danger.
[0065] Embodiment 2
[0066] An embodiment of the present invention provides a mid-position control system for an autonomous driving vehicle, referring to Figure 2 As shown, including:
[0067] The value reading module 10 is used to read the historical learning value by using the steering neutral controller, and if there is no historical learning value, assign a new learning value, and if there is, update the historical learning value;
[0068] The value updating module 20 is used to use the steering center position controller to determine whether the vehicle is in a straight-ahead state according to the value of the vehicle body posture sensor, the vehicle speed and the camera signal. If the vehicle is in a straight-ahead state, the steering wheel angle is used to perform center position learning to determine the steering center position deviation learning value;
[0069] Numerical updating module 30: used to update the historical learning value using the steering median deviation learning value; if there is a historical learning value, the historical learning value is directly updated; if there is no historical learning value, the current steering median deviation learning value is directly used as the historical learning value before the next update.
[0070] The control optimization module 40 is used to continuously optimize the lateral control according to the steering median deviation learning value by using the steering median controller, that is, subtract the steering median deviation learning value from the final steering control instruction, and then perform lateral control on the vehicle. If there is no steering median deviation learning value, the steering median deviation learning value is defaulted to 0.
[0071] Alarm module 50: used to continuously detect whether the steering median deviation learning value exceeds the preset alarm threshold value. If the steering median deviation learning value exceeds the preset alarm threshold value, the alarm device is notified to alarm; if there is no steering median deviation learning value, the steering median deviation learning value is defaulted to be 0.
[0072] The value reset module 60 is used to continuously detect whether the neutral reset condition is met. If so, the steering neutral controller is used to control the steering machine to reset the steering neutral position; if the steering machine feedback is successful, the steering neutral deviation learning value is cleared.
[0073] In a specific embodiment of the present invention, in the value updating module 20, the median learning includes:
[0074] The vehicle's yaw rate and roll angle are read through the body posture sensor and the steering center controller. If the yaw rate and roll angle do not exceed the threshold, it is determined that the vehicle is not in a turning state and the body is not tilted;
[0075] The curvature of the lane line is identified through a camera and a steering center controller. If the curvature does not exceed a threshold, it is determined that the vehicle is traveling in a straight lane.
[0076] The hand force and the steering center controller are used to determine whether the driver is turning the steering wheel. If the steering wheel is not turned, it is determined that the vehicle is driving in a straight line.
[0077] Specifically, the vehicle posture sensor is used to detect the yaw rate and the roll angle of the vehicle body; the camera is used to observe the lane line, and the vehicle speed needs to be greater than a threshold, at which point the accuracy of the yaw rate is sufficiently accurate.
[0078] Furthermore, after the median learning condition is met, the time when the condition is met needs to be recorded. If the time exceeds the threshold, the steering wheel angle during this period is processed according to the vehicle state estimation algorithm and the filtering algorithm to obtain the steering median deviation learning value. The vehicle state estimation algorithm establishes the vehicle state equation and iteratively updates the steering median according to the vehicle state. The filtering algorithm uses weighted average filtering.
[0079] In a specific embodiment of the present invention, the numerical update module 20 is used to: if the vehicle is traveling straight in a straight lane, start timing; if there is no lane line, determine whether the vehicle is traveling in a straight line based on the steering wheel hand force signal, and if the vehicle is traveling in a straight line, start timing; if the timing exceeds a calibratable threshold, use the steering wheel angle for learning.
[0080] In a specific embodiment of the present invention, in the value reset module 60, the neutral reset condition is: the vehicle speed is 0, the engine is in the starting state, and the gear position needs to be in neutral or parking gear. The engine is in the starting state to avoid reset failure. The gear position needs to be in neutral or parking gear to avoid sudden starting of the vehicle.
[0081] In a specific embodiment of the present invention, the value reset module 60 is used to: when resetting the median position, the steering median controller sends the steering median deviation learning value to the steering machine, and the steering machine uses the steering median deviation learning value to reset the median position. When updating the historical learning value, weighted averaging or direct replacement of the historical learning value can be used.
[0082] The present application provides a median control system for an autonomous driving vehicle. It determines whether the vehicle is in a turning state based on the vehicle body posture, and determines whether it is in a straight lane by taking images with a camera. It can effectively determine whether the vehicle is in a straight-line driving state under all working conditions. When the lane line is not good, the vehicle body posture and hand strength can also be used to determine whether the vehicle is in a straight-line driving state. The accuracy and range of the judgment of straight-line driving can be effectively improved. In addition, the present application determines that the vehicle is in a stationary state and uses the steering median deviation learning value for calibration. It can repair the state in time when there is a small offset, thereby avoiding the situation where the steering median deviation learning value is too large, resulting in the inability to identify the fault. In addition, the present application also warns the driver when the median value is too large or suddenly changes, which helps the driver to identify the vehicle state and avoid danger.
[0083] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
[0084] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referenced to each other. The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the functions in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing terminal device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes. Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention. Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or terminal device including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.
[0085] The method and device provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.
[0086] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", "one specific embodiment" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for controlling a mid-position of an autonomous driving vehicle, characterized in that: include: Step S1: using the steering neutral controller to read the historical learning value; Step S2: judging whether the vehicle is in a straight-ahead state according to the value of the vehicle posture sensor, the vehicle speed and the camera signal; if the vehicle is in a straight-ahead state, performing median learning using the steering wheel angle to determine a steering median deviation learning value; Step S3: using the steering median deviation learning value to update the historical learning value; Step S4: using the steering median controller to continuously optimize lateral control according to the steering median deviation learning value; Step S5: continuously detecting whether the steering median deviation learning value exceeds a preset alarm threshold value, and if the steering median deviation learning value exceeds the preset alarm threshold value, notifying an alarm device to alarm; Step S6: continuously detecting whether the neutral reset condition is met, and if so, using the steering neutral controller to control the steering machine to reset the steering neutral position; if the steering machine feedback is successful, clearing the steering neutral deviation learning value.
2. The method for controlling the mid-position of an automatic driving vehicle according to claim 1, characterized in that: Step S1 includes: If there is no historical learning value, a new learning value is assigned; if there is, the historical learning value is updated.
3. The method for controlling the mid-position of an automatic driving vehicle according to claim 1, characterized in that: In step S2, the median learning includes: The vehicle's yaw rate and roll angle are read through the body posture sensor and the steering center controller. If the yaw rate and roll angle do not exceed the threshold, it is determined that the vehicle is not in a turning state and the body is not tilted; The curvature of the lane line is identified through a camera and a steering center controller. If the curvature does not exceed a threshold, it is determined that the vehicle is traveling in a straight lane. The hand force and the steering center controller are used to determine whether the driver is turning the steering wheel. If the steering wheel is not turned, it is determined that the vehicle is driving in a straight line.
4. The method for controlling the mid-position of an automatic driving vehicle according to claim 3, characterized in that: Step S2 also includes: if the vehicle is traveling straight in a straight lane, start timing; if there is no lane line, determine whether the vehicle is traveling in a straight line based on the steering wheel hand force signal, and if the vehicle is traveling in a straight line, start timing; if the timing exceeds a calibratable threshold, use the steering wheel angle for learning.
5. The method for controlling the mid-position of an automatic driving vehicle according to claim 1, characterized in that: Step S4 also includes: If there is no steering median deviation learning value, the steering median deviation learning value is defaulted to 0.
6. The method for controlling the mid-position of an automatic driving vehicle according to claim 1, characterized in that: In step S6, the neutral reset condition is: the vehicle speed is 0, the engine is in the starting state, and the gear position needs to be in neutral or parking.
7. The method for controlling the neutral position of an automatic driving vehicle according to claim 1, characterized in that: Step S6 includes: when resetting the neutral position, sending the steering neutral position deviation learning value to the steering machine through the steering neutral position controller, and the steering machine resets the neutral position using the steering neutral position deviation learning value.
8. A mid-position control system for an autonomous driving vehicle, characterized in that: include: Value reading module: used to read historical learning values using the steering neutral controller; Numerical update module: used to determine whether the vehicle is in a straight-ahead state based on the value of the body posture sensor, vehicle speed and camera signal. If the vehicle is in a straight-ahead state, the steering wheel angle is used for median learning to determine the steering median deviation learning value; A numerical updating module: used for updating a historical learning value using the steering median deviation learning value; A control optimization module: used for continuously optimizing lateral control according to the steering median deviation learning value by using the steering median controller; Alarm module: used for continuously detecting whether the steering median deviation learning value exceeds a preset alarm threshold value, and notifying an alarm device to alarm if the steering median deviation learning value exceeds the preset alarm threshold value; Numerical reset module: used to continuously detect whether the neutral reset condition is met. If so, the steering neutral controller is used to control the steering machine to reset the steering neutral position; if the steering machine feedback is successful, the steering neutral deviation learning value is cleared.
9. The automatic driving vehicle neutral control system according to claim 8, characterized in that: In the numerical update module, the median learning includes: The vehicle's yaw rate and roll angle are read through the body posture sensor and the steering center controller. If the yaw rate and roll angle do not exceed the threshold, it is determined that the vehicle is not in a turning state and the body is not tilted; The curvature of the lane line is identified through a camera and a steering center controller. If the curvature does not exceed a threshold, it is determined that the vehicle is traveling in a straight lane. The hand force and the steering center controller are used to determine whether the driver is turning the steering wheel. If the steering wheel is not turned, it is determined that the vehicle is driving in a straight line.
10. The automatic driving vehicle neutral control system according to claim 9, characterized in that: The numerical update module is used to perform the following operations: if the vehicle is traveling straight in a straight lane, start timing; if there is no lane line, determine whether the vehicle is traveling in a straight line based on the steering wheel hand force signal, and if the vehicle is traveling in a straight line, start timing; if the timing exceeds a calibratable threshold, use the steering wheel angle for learning.