Intelligent driving system EPS corner self-learning method, system, storage medium and vehicle

Abstract

The present invention belongs to the field of intelligent driving technology and discloses an intelligent driving system EPS corner self-learning method, system, storage medium and vehicle: using the center point of the camera as the origin of the coordinate system, constructing a lane line position function; obtaining the vehicle speed, steering wheel angle, steering wheel torque in real time, and obtaining the lane line recognition quality parameter Q output by the camera. i The system determines whether the vehicle is traveling in a stable, straight lane. If so, it issues a self-learning flag Flg. Upon receiving the self-learning flag Flg, it initiates self-learning of the steering wheel angle neutral position. This invention addresses the problem of systematic deviation between the steering wheel angle signal and the vehicle's actual steering angle.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent driving technology, and specifically relates to an intelligent driving system EPS corner self-learning method, system, storage medium and vehicle. Background Art

[0002] In recent years, the rapid development and widespread application of internet technology, high-precision mapping, and artificial intelligence have fueled the growth of autonomous driving technology. Research indicates that autonomous driving can reduce traffic accidents by 90% and lower travel costs by 70%, making it a key core technology for the next generation of intelligent vehicles. The commercially available Level 2 and Level 3 intelligent assisted driving systems approach autonomous driving to a certain extent, addressing common traffic accident scenarios such as rear-end collisions, sideways collisions, and driver fatigue. This approach, through the use of assisted driving, can help reduce accidents to a certain extent.

[0003] In existing technologies, Level 1, Level 2, and Level 3 driver assistance technologies typically involve three steps: perception, decision-making, and execution. First, sensors such as cameras or millimeter-wave radars collect and process environmental and in-vehicle information. Vehicle state parameters, including lane information, obstacles, and traffic signs, are acquired via the CAN bus or Ethernet through the vehicle's actuators. The decision-making control module then makes decisions based on this acquired information and the driver's intent, formulates a corresponding control strategy, and sends control instructions to the CAN bus or Ethernet. Finally, the vehicle's actuators implement control, providing feedback to the underlying modules to execute tasks, including acceleration, braking, steering, and human-machine interaction.

[0004] In L2 and L3 intelligent driving systems, the steering wheel is controlled through a series of complex algorithms. The vehicle's expected driving trajectory is calculated based on lane lines, traffic environment, and information about traffic participants. The steering angle or steering torque acting on the steering wheel is then calculated and responded to through the Electric Power Steering (EPS).

[0005] For intelligent driving systems, the steering wheel angle signal is a crucial reference signal for planning, decision-making, and control based on environmental information captured by sensors and vehicle information obtained through the onboard communication network, as well as for steering angle control via the EPS (Electrical Stability Control). Typically, the steering wheel angle signal is calculated internally by the EPS or obtained through a steering wheel angle sensor in the vehicle's steering mechanism. In some vehicles, the signal is derived from a virtual steering wheel angle calculated by the Electronic Stability Control (ESC) based on vehicle kinematic parameters. However, there is often a systematic deviation between the steering wheel angle signal and the vehicle's actual steering angle, which can significantly impact the intelligent driving system's planning, decision-making, and control functions. Summary of the Invention

[0006] In response to the technical problems raised above, the present invention provides an intelligent driving system EPS angle self-learning method, system, storage medium and vehicle, aiming to eliminate the systematic deviation between the steering wheel angle signal and the actual steering wheel steering angle of the vehicle.

[0007] In a first aspect, the present invention provides an EPS corner self-learning method for an intelligent driving system, the method comprising the following steps:

[0008] Step 1: Use the center point of the camera as the origin of the coordinate system and construct the lane position function:

[0009] y i =c 0i +c 1i x+c 2i x 2 +c 3i x 3 ,

[0010] Where x is the distance from the projection point of the point on the lane line perpendicular to the vehicle's centerline to the origin of the coordinate system, c 0i is the distance between the center point and the lane lines on both sides in the direction perpendicular to the lane centerline, c 1i is the angle between the vehicle centerline and the lane line, c 2i is the lane curvature, c 3i is the lane line curvature change rate, y i is the distance from a point on the lane line to the vehicle's center axis in the horizontal, vertical, and vehicle center axis directions. When i=1, it indicates the left lane line, and when i=2, it indicates the right lane line.

[0011] Step 2: Obtain the vehicle speed, steering wheel angle, steering wheel torque in real time, and obtain the lane line recognition quality parameter Q output by the camera i , Q i∈[0,1], when i=1, it indicates the left lane line, when i=2, it indicates the right lane line;

[0012] Step 3: Determine whether the vehicle is traveling in a stable straight line on the straight road. If it is, a self-learning flag Flg is issued.

[0013] Step 4: When the self-learning flag Flg is obtained, the steering wheel angle neutral position self-learning is started.

[0014] Specifically, the method for determining whether the vehicle is running stably in a straight line is as follows:

[0015] If conditions 1 to 6 are met at the same time and the duration exceeds the time threshold T, the vehicle is determined to be in a stable straight-line driving state on the straight road; otherwise, the vehicle is determined not to be in a stable straight-line driving state on the straight road;

[0016] Condition 1: Lane recognition quality parameter Q i Greater than the parameter threshold;

[0017] Condition 2: The absolute value of the angle c1 between the vehicle centerline and the lane lines on both sides is less than the angle threshold;

[0018] Condition 3: The absolute value of the lane curvature c2 is less than the curvature threshold;

[0019] Condition 4: the vehicle speed is greater than the vehicle speed threshold;

[0020] Condition 5: The absolute value of the steering wheel angle is less than the angle threshold;

[0021] Condition 6: The absolute value of the steering wheel torque is less than the torque threshold.

[0022] Specifically, in step 4, when the self-learning flag Flg is obtained, a first-order low-pass filtering algorithm is used to filter and compensate the steering wheel angle. The formula of the first-order low-pass filtering algorithm is:

[0023] Y n =αX n +(1-α)Y n-1 ,

[0024] Among them, α is the filter coefficient, X n is the sampling value of this time, Y n-1 is the last filtering compensation value, Y n is the current filtering compensation value;

[0025] When the steering wheel angle is consistent with the target angle, the steering wheel angle neutral self-learning is completed.

[0026] Specifically, the value range of the filter coefficient α is 0.001-0.01.

[0027] Specifically, the steering wheel angle is obtained by a steering wheel angle sensor provided on the steering wheel, and the steering wheel torque is obtained by a steering wheel torque sensor provided on the steering wheel.

[0028] Specifically, the time threshold T is 2s;

[0029] The vehicle speed threshold is 10 km / h.

[0030] In a second aspect, the present invention further provides an intelligent driving system EPS corner self-learning system, the system comprising:

[0031] Function construction module, used to construct the lane position function with the center point of the camera as the origin of the coordinate system:

[0032] y i =c 0i +c 1i x+c 2i x 2 +c 3i x 3 ,

[0033] Where x is the distance from the projection point of the point on the lane line perpendicular to the vehicle's centerline to the origin of the coordinate system, c 0i is the distance between the center point and the lane lines on both sides in the direction perpendicular to the lane centerline, c 1i is the angle between the vehicle centerline and the lane line, c 2i is the lane curvature, c 3i is the lane line curvature change rate, y i is the distance from a point on the lane line to the vehicle's center axis in the horizontal, vertical, and vehicle center axis directions. When i=1, it indicates the left lane line, and when i=2, it indicates the right lane line.

[0034] The vehicle information acquisition module is used to obtain the vehicle's speed, steering wheel angle, steering wheel torque in real time, and obtain the lane line recognition quality parameter Q output by the camera i , Q i ∈[0,1], when i=1, it indicates the left lane line, when i=2, it indicates the right lane line;

[0035] The condition judgment module is used to judge whether the vehicle is running stably and straight on the straight road. If it is running stably and straight on the straight road, a self-learning flag Flg is issued;

[0036] The self-learning module is used to start self-learning of the steering wheel angle neutral position when the self-learning flag Flg is obtained.

[0037] In a third aspect, the present invention provides a computer storage medium storing program instructions, wherein when the program instructions are running, the device where the computer storage medium is located is controlled to execute any one of the above-mentioned intelligent driving system EPS corner self-learning methods.

[0038] In a fourth aspect, the present invention provides a processor for running a program, wherein when the program is running, any one of the above-mentioned intelligent driving system EPS corner self-learning methods is executed.

[0039] In a fifth aspect, the present invention provides a vehicle that adopts any of the above-mentioned intelligent driving system EPS corner self-learning methods.

[0040] The present invention discloses a method, system, storage medium, and vehicle for self-learning steering angles in an intelligent driving system (EPS). Compared with the prior art, the present invention has at least the following beneficial effects:

[0041] 1. To address the high-precision steering wheel angle signals required by intelligent driving systems and the steering wheel angle signal system errors encountered when precisely controlling the steering wheel angle, this system utilizes environmental perception sensors such as the intelligent driving system's forward-facing camera to obtain lane information, identify the vehicle traveling straight within the lane, and then conducts self-learning of the steering wheel angle neutral position to eliminate the steering wheel angle signal system errors.

[0042] 2. The accuracy of the steering wheel angle median error obtained by further judgment and identification based on traditional vehicle dynamics parameters or wheel speed sensor signals is greatly improved, while avoiding the situation where the steering wheel median angle changes suddenly due to the triggering of the flag when the conditions are met, resulting in a sudden change in vehicle angle control. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0044] Figure 1 This is a flow chart of an EPS corner self-learning method for an intelligent driving system according to the present invention;

[0045] Figure 2 This is a structural diagram of the EPS corner self-learning system of an intelligent driving system of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. Obviously, the specific embodiments described herein are only used to illustrate the present invention and are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0047] It should be noted that if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0048] Figure 1 FIG. 1 is a flow chart of an embodiment of an EPS corner self-learning method for an intelligent driving system provided by the present invention, and the flow chart specifically includes the following steps:

[0049] Step 1: Use the center point of the camera as the origin of the coordinate system and construct the lane position function:

[0050] y i =c 0i +c 1i x+c 2i x 2 +c 3i x 3 ,

[0051] Where x is the distance from the projection point of the point on the lane line perpendicular to the vehicle's centerline to the origin of the coordinate system, c 0i is the distance between the center point and the lane lines on both sides in the direction perpendicular to the lane centerline, c 1i is the angle between the vehicle centerline and the lane line, c 2i is the lane curvature, c 3i is the lane line curvature change rate, y i It is the distance from a point on the lane line to the center axis of the vehicle in the horizontal, vertical and vehicle center axis directions. When i=1, it indicates the left lane line, and when i=2, it indicates the right lane line.

[0052] Based on the lane position function, the lane lines on both sides of the vehicle are resolved into polynomial equations represented by four parameters. The camera also generates a parameter Q∈[0,1] for each lane line, indicating lane recognition quality. A higher Q value indicates higher lane recognition quality. C1 is the angle between the vehicle centerline and the lane lines on either side, expressed in radians. C2 can be approximated as the curvature of the lane line at the camera coordinate system's origin.

[0053] Step 2: Obtain the vehicle speed, steering wheel angle, steering wheel torque in real time, and obtain the lane line recognition quality parameter Q output by the camera i , Q i ∈[0,1], when i=1, it indicates the left lane line, and when i=2, it indicates the right lane line.

[0054] Specifically, the steering wheel angle is obtained by a steering wheel angle sensor provided on the steering wheel, and the steering wheel torque is obtained by a steering wheel torque sensor provided on the steering wheel.

[0055] Step 3: Determine whether the vehicle is traveling in a stable straight line on the straight road. If it is, a self-learning flag Flg is issued.

[0056] Specifically, the method for determining whether the vehicle is running stably in a straight line is as follows:

[0057] If conditions 1 to 6 are met at the same time and the duration exceeds the time threshold T, the vehicle is determined to be in a stable straight-line driving state on the straight road; otherwise, the vehicle is determined not to be in a stable straight-line driving state on the straight road;

[0058] Condition 1: Lane recognition quality parameter Q i Greater than the parameter threshold;

[0059] Condition 2: The absolute value of the angle c1 between the vehicle centerline and the lane lines on both sides is less than the angle threshold;

[0060] Condition 3: The absolute value of the lane curvature c2 is less than the curvature threshold;

[0061] Condition 4: the vehicle speed is greater than the vehicle speed threshold;

[0062] Condition 5: The absolute value of the steering wheel angle is less than the angle threshold;

[0063] Condition 6: The absolute value of the steering wheel torque is less than the torque threshold.

[0064] When the lane line recognition quality parameter Qi is greater than the parameter threshold, it indicates that the lane line quality is good; when the absolute value of the angle c1 between the vehicle centerline and the lane lines on both sides is less than the angle threshold, it indicates that the vehicle is traveling nearly parallel to the lane line; when the absolute value of the lane line curvature c2 is less than the curvature threshold, it indicates that the lane line in which the vehicle is located is close to a straight line; when the vehicle speed is greater than the vehicle speed threshold, it indicates that the vehicle is traveling; when the absolute value of the steering wheel angle is less than the angle threshold, it indicates that the driver is controlling the vehicle to slightly turn within the lane to adjust the vehicle to go straight; when the absolute value of the steering wheel torque is less than the torque threshold, it indicates that the driver is slightly manipulating the steering wheel and has not obviously intervened.

[0065] Furthermore, the time threshold T is 2s;

[0066] The vehicle speed threshold is 10 km / h, and the vehicle speed range is generally 10 km / h-60 km / h.

[0067] The steering wheel angle is turned around the neutral position (0°).

[0068] Step 4: When the self-learning flag Flg is obtained, the steering wheel angle neutral position self-learning is started.

[0069] Specifically, in step 4, when the self-learning flag Flg is obtained, a first-order low-pass filtering algorithm is used to filter and compensate the steering wheel angle. The formula of the first-order low-pass filtering algorithm is:

[0070] Y n =αX n +(1-α)Y n-1 ,

[0071] Among them, α is the filter coefficient, X n is the sampling value of this time, Y n-1 is the last filtering compensation value, Y n is the current filtering compensation value;

[0072] When the steering wheel angle is consistent with the target angle, the steering wheel angle neutral self-learning is completed.

[0073] Specifically, the value range of the filter coefficient α is 0.001-0.01.

[0074] The filter coefficient α is relatively small, at 0.001-0.01, and its effect is that after the steering wheel neutral position self-learning conditions are met, the vehicle can learn a stable and continuous neutral value in about ten seconds of straight driving.

[0075] Figure 2 The figure shows a schematic diagram of an embodiment of an EPS corner self-learning system for an intelligent driving system provided by the present invention. Figure 2As shown, the system includes:

[0076] Function construction module, used to construct the lane position function with the center point of the camera as the origin of the coordinate system:

[0077] y i =c 0i +c 1i x+c 2i x 2 +c 3i x 3 ,

[0078] Where x is the distance from the projection point of the point on the lane line perpendicular to the vehicle's centerline to the origin of the coordinate system, c 0i is the distance between the center point and the lane lines on both sides in the direction perpendicular to the lane centerline, c 1i is the angle between the vehicle centerline and the lane line, c 2i is the lane curvature, c 3i is the lane line curvature change rate, y i It is the distance from a point on the lane line to the center axis of the vehicle in the horizontal, vertical and vehicle center axis directions. When i=1, it indicates the left lane line, and when i=2, it indicates the right lane line.

[0079] The vehicle information acquisition module is used to obtain the vehicle's speed, steering wheel angle, steering wheel torque in real time, and obtain the lane line recognition quality parameter Q output by the camera i , Q i ∈[0,1], when i=1, it indicates the left lane line, and when i=2, it indicates the right lane line.

[0080] The condition judgment module is used to judge whether the vehicle is running stably and straight on the straight road. If it is running stably and straight on the straight road, a self-learning flag Flg is issued.

[0081] The self-learning module is used to start self-learning of the steering wheel angle neutral position when the self-learning flag Flg is obtained.

[0082] According to another aspect of an embodiment of the present invention, a computer storage medium is provided, which stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute any one of the above-mentioned intelligent driving system EPS corner self-learning methods.

[0083] According to another aspect of an embodiment of the present invention, a processor is provided, which is used to run a program, wherein when the program is run, any one of the above-mentioned intelligent driving system EPS corner self-learning methods is executed.

[0084] According to another aspect of an embodiment of the present invention, a vehicle is provided, which adopts any of the above-mentioned intelligent driving system EPS corner self-learning methods.

[0085] The above embodiments merely represent preferred implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for self-learning the EPS corner of an intelligent driving system, characterized in that: The steps include: Step 1: Use the center point of the camera as the origin of the coordinate system and construct the lane position function: y i =c 0i +c 1i x+c 2i x 2 +c 3i x 3 , Where x is the distance from the projection point of the point on the lane line perpendicular to the vehicle's centerline to the origin of the coordinate system, c 0i is the distance between the center point and the lane lines on both sides in the direction perpendicular to the lane centerline, c 1i is the angle between the vehicle centerline and the lane line, c 2i is the lane curvature, c 3i is the lane line curvature change rate, y i is the distance from a point on the lane line to the vehicle's center axis in the horizontal, vertical, and vehicle center axis directions. When i=1, it indicates the left lane line, and when i=2, it indicates the right lane line. Step 2: Obtain the vehicle speed, steering wheel angle, steering wheel torque in real time, and obtain the lane line recognition quality parameter Q output by the camera i , Q i ∈[0,1], when i=1, it indicates the left lane line, when i=2, it indicates the right lane line; Step 3: Determine whether the vehicle is traveling in a stable straight line on the straight road. If it is, a self-learning flag Flg is issued. Step 4: When the self-learning flag Flg is obtained, the steering wheel angle neutral position self-learning is started.

2. The EPS corner self-learning method of an intelligent driving system according to claim 1, characterized in that: The method to determine whether the vehicle is running stably in a straight line is as follows: If conditions 1 to 6 are met at the same time and the duration exceeds the time threshold T, the vehicle is determined to be in a stable straight-line driving state on the straight road; otherwise, the vehicle is determined not to be in a stable straight-line driving state on the straight road; Condition 1: Lane recognition quality parameter Q i Greater than the parameter threshold; Condition 2: The absolute value of the angle c1 between the vehicle centerline and the lane lines on both sides is less than the angle threshold; Condition 3: The absolute value of the lane curvature c2 is less than the curvature threshold; Condition 4: the vehicle speed is greater than the vehicle speed threshold; Condition 5: The absolute value of the steering wheel angle is less than the angle threshold; Condition 6: The absolute value of the steering wheel torque is less than the torque threshold.

3. The EPS corner self-learning method of an intelligent driving system according to claim 1, characterized in that: In step 4, when the self-learning flag Flg is obtained, a first-order low-pass filtering algorithm is used to filter and compensate the steering wheel angle. The formula of the first-order low-pass filtering algorithm is: Y n =αX n +(1-α)Y n-1 , Among them, α is the filter coefficient, X n is the sampling value of this time, Y n-1 is the last filtering compensation value, Y n is the current filtering compensation value; When the steering wheel angle is consistent with the target angle, the steering wheel angle neutral self-learning is completed.

4. The EPS corner self-learning method of an intelligent driving system according to claim 3, characterized in that: The value range of the filter coefficient α is 0.001-0.

01.

5. The EPS corner self-learning method of an intelligent driving system according to claim 1, characterized in that: The steering wheel angle is obtained by a steering wheel angle sensor provided on the steering wheel, and the steering wheel torque is obtained by a steering wheel torque sensor provided on the steering wheel.

6. The EPS corner self-learning method of an intelligent driving system according to claim 2, characterized in that: The time threshold T is 2s; The vehicle speed threshold is 10 km / h.

7. An intelligent driving system EPS steering angle self-learning system, used to implement the intelligent driving system EPS steering angle self-learning method according to any one of claims 1 to 6, characterized in that: include: Function construction module, used to construct the lane position function with the center point of the camera as the origin of the coordinate system: y i =c 0i +c 1i x+c 2i x 2 +c 3i x 3 , Where x is the distance from the projection point of the point on the lane line perpendicular to the vehicle's centerline to the origin of the coordinate system, c 0i is the distance between the center point and the lane lines on both sides in the direction perpendicular to the lane centerline, c 1i is the angle between the vehicle centerline and the lane line, c 2i is the lane curvature, c 3i is the lane line curvature change rate, y i is the distance from a point on the lane line to the vehicle's center axis in the horizontal, vertical, and vehicle center axis directions. When i=1, it indicates the left lane line, and when i=2, it indicates the right lane line. The vehicle information acquisition module is used to obtain the vehicle's speed, steering wheel angle, steering wheel torque in real time, and obtain the lane line recognition quality parameter Q output by the camera i , Q i ∈[0,1], when i=1, it indicates the left lane line, when i=2, it indicates the right lane line; The condition judgment module is used to judge whether the vehicle is running stably and straight on the straight road. If it is running stably and straight on the straight road, a self-learning flag Flg is issued; The self-learning module is used to start self-learning of the steering wheel angle neutral position when the self-learning flag Flg is obtained.

8. A computer storage medium, characterized in that The computer storage medium stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute the EPS corner self-learning method of the intelligent driving system according to any one of claims 1 to 6.

9. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the EPS corner self-learning method of the intelligent driving system according to any one of claims 1 to 6.

10. A vehicle, characterized in that: The intelligent driving system EPS corner self-learning method as described in any one of claims 1 to 6 is adopted.

Images