Rear wheel track prediction method, anti-scratching reminding method and system and intelligent driving domain controller

Abstract

The embodiment of the invention relates to the technical field of intelligent driving, and discloses a rear wheel track prediction method, an anti-rubbing reminding method and system and an intelligent driving domain controller, and the rear wheel track prediction method comprises the steps: obtaining front wheel cornering stiffness and rear wheel cornering stiffness based on a vehicle pitch angle; based on the axle distance between the front axle and the rear axle of the vehicle, the vehicle mass, the vehicle running speed, the front wheel cornering stiffness and the rear wheel cornering stiffness, a compensation model is established; the compensation model is adopted to compensate the traditional Ackerman model to obtain a rear wheel track prediction model; and obtaining a rear wheel prediction trajectory based on the current steering wheel angle and the rear wheel trajectory prediction model. According to the technical scheme, the problem that a traditional rear wheel track prediction model is not accurate due to the fact that the pitching posture of a vehicle body is changed under complex working conditions such as underground garage exit ramps and mountainous area slope parking spaces can be solved; and anti-scratch reminding is carried out on the driver in time, so that the driving safety is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, specifically to a rear wheel trajectory prediction method, a scratch prevention reminder method and system, and an intelligent driving domain controller. Background Technology

[0002] With the development of intelligent connected vehicle technology, automatic parking assist systems and 360° panoramic surround view systems have become standard features in mid-to-high-end models. Among them, rear wheel trajectory prediction technology is widely used for reversing guidance. By collecting parameters such as steering wheel angle, vehicle speed, and wheelbase, it calculates and displays the vehicle's rear driving path to help the driver judge whether a collision with obstacles is likely.

[0003] However, existing technologies have the following significant drawbacks: most rear-wheel trajectory algorithms use the traditional Ackerman model for prediction, which assumes the vehicle is on a level surface and does not consider the impact of the vehicle's pitch attitude on the actual wheel track projection and steering geometry when driving on an incline. When going downhill, the front of the vehicle dips, and the vehicle's attitude changes, causing a significant deviation between the rear-wheel path predicted by the traditional model and the actual trajectory. This is especially true on steep inclines (>10%), where the error can reach more than 20cm, severely weakening the system's reliability and making the vehicle prone to scraping in complex conditions such as underground parking garage exit ramps and mountain slope parking spaces. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide a rear wheel trajectory prediction method, a scratch prevention reminder method and system, and an intelligent driving domain controller to solve the problem of inaccuracy of traditional models caused by changes in vehicle pitch attitude in complex working conditions such as underground garage exit ramps and mountain slope parking spaces. The invention provides timely scratch prevention reminders to the driver and improves driving safety when the vehicle pitch attitude changes.

[0005] According to one aspect of the present invention, a rear wheel trajectory prediction method is provided, the method comprising: Obtain vehicle parameters, including vehicle mass, wheelbase between the front and rear axles, vehicle pitch angle, steering wheel angle, and vehicle speed. The front wheel lateral stiffness and rear wheel lateral stiffness are obtained based on the vehicle pitch angle. A compensation model is established based on the wheelbase between the front and rear axles of the vehicle, the vehicle mass, the vehicle speed, the front wheel lateral stiffness, and the rear wheel lateral stiffness. The rear wheel trajectory prediction model is obtained by compensating the traditional Ackerman model with the aforementioned compensation model. The predicted rear wheel trajectory is obtained based on the current steering wheel angle and the rear wheel trajectory prediction model.

[0006] In one alternative approach, the vehicle parameters also include the vehicle center of gravity height, the distance from the front axle to the vehicle center of gravity, the distance from the rear axle to the vehicle center of gravity, and the lateral stiffness under a unit vertical load. The process of obtaining the front wheel lateral stiffness and rear wheel lateral stiffness based on the vehicle pitch angle includes the following sub-steps: The front axle vertical load is obtained based on the vehicle pitch angle, the vehicle mass, the wheelbase between the front and rear axles, the vehicle center of gravity height, and the distance from the rear axle to the vehicle center of gravity. The rear axle vertical load is obtained based on the vehicle pitch angle, the vehicle mass, the wheelbase between the front and rear axles, the vehicle center of gravity height, and the distance from the front axle to the vehicle center of gravity. The front wheel lateral stiffness is obtained based on the lateral stiffness under the unit vertical load and the front axle vertical load. The rear wheel lateral stiffness is obtained based on the lateral stiffness under the unit vertical load and the rear axle vertical load.

[0007] According to a second aspect of the present invention, a rear wheel trajectory prediction system is provided, comprising: Data acquisition module: used to collect the vehicle parameters, including vehicle mass, wheelbase between the front and rear axles, vehicle pitch angle, steering wheel angle, and vehicle speed; Compensation model establishment module: used to obtain the front wheel lateral stiffness and rear wheel lateral stiffness based on the vehicle pitch angle, and to establish a compensation model based on the wheelbase between the front and rear axles, the vehicle mass, the vehicle speed, the front wheel lateral stiffness and the rear wheel lateral stiffness; Wheel trajectory prediction model establishment module: used to compensate the traditional Ackermann model according to the compensation model to obtain the rear wheel trajectory prediction model; Rear wheel trajectory prediction module: used to obtain the predicted rear wheel trajectory based on the current steering wheel angle and the rear wheel trajectory prediction model.

[0008] According to a third aspect of the present invention, a method for preventing scratches and dents is provided, the method comprising: The rear wheel position is determined based on the rear wheel trajectory prediction obtained by the rear wheel trajectory prediction method described above. The position includes a first position and a second position. The first position is when the distance between the rear wheel and the lateral obstacle is less than a preset safety threshold, and the second position is when the distance between the rear wheel and the lateral obstacle is not less than the preset safety threshold. When the rear wheel is in the first position, the warning mechanism is triggered; when the rear wheel is in the second position, the warning mechanism is deactivated.

[0009] In one alternative approach, the distance between the rear wheel and the lateral obstacle is calculated using the following sub-steps: The current position of the rear wheels is determined based on the rear wheel trajectory prediction model. Determine the equation of the line for the lateral obstacle; The distance between the rear wheel and the lateral obstacle is determined based on the current position of the rear wheel and the linear equation of the lateral obstacle.

[0010] In one alternative approach, the first position state is divided into multiple risk levels based on the distance between the rear wheel and the lateral obstacle; and different early warning mechanisms are set according to the risk levels.

[0011] In one alternative approach, the method further includes a step of outputting a target region image to the onboard surround view imaging module based on the vehicle's attitude, comprising the following sub-steps: The vehicle's attitude is determined based on the vehicle's pitch angle; Obtain the original front view image of the target area; When the vehicle pitch angle is greater than the set pitch angle, the vehicle downhill duration is not less than the set time, the vehicle speed is less than the set speed, and the steering wheel angle is greater than the set angle, the vehicle is determined to be in the first posture; otherwise, the vehicle is determined to be in the second posture. When the vehicle is in the first posture, the original front view image of the target area is visually corrected and then used as the target area image, which is then output to the vehicle surround view imaging module. When the vehicle is in the second posture, the original front view image of the target area is output as the target area image to the vehicle surround view imaging module.

[0012] In one alternative approach, the visual correction of the original front view image of the target area includes the following sub-steps: A lookup table for pre-generating a top angle-position mapping is generated based on standard chessboard patterns captured by vehicle cameras at different top angles. The target output area is divided into a true restoration area and a virtual completion area; The mapping relationship of the realistically restored area is obtained from the tilt angle-position mapping lookup table based on the vehicle's pitch angle, and the inverse perspective mapping is performed for correction based on the mapping relationship; the virtual completion area is filled with a preset texture template for correction.

[0013] According to a fourth aspect of the present invention, a scratch prevention reminder system is provided, comprising: Rear wheel position determination module: used to determine the position state of the rear wheel based on the predicted rear wheel trajectory obtained by the above rear wheel trajectory prediction method; wherein, the position state includes a first position state and a second position state; the first position state is the position state in which the distance between the rear wheel and the lateral obstacle is less than a preset safety threshold, and the second position state is the position state in which the distance between the rear wheel and the lateral obstacle is not less than the preset safety threshold; Control module: Used to send a warning command to the warning module when the rear wheel is in the first position state; Early warning module: Used to control the early warning mechanism according to early warning instructions.

[0014] According to a fifth aspect of the present invention, a smart driving domain controller is provided, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to implement the rear wheel trajectory prediction method and / or the anti-scratching reminder method as described above when executed.

[0015] According to a sixth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the rear wheel trajectory prediction method and / or the anti-scratching reminder method as described above.

[0016] This invention addresses the inaccuracy of traditional models caused by changes in vehicle pitch attitude in complex conditions such as underground parking garage exit ramps and mountainous parking spaces by generating a rear wheel trajectory prediction model based on the vehicle's pitch angle, building upon the traditional Ackerman model. Simultaneously, the rear wheel position is determined based on the rear wheel trajectory prediction model. When the vehicle is detected in a high-risk collision state (i.e., a first position state), a warning mechanism is triggered to promptly alert the driver to prevent collisions, thus improving driving safety when the vehicle's pitch attitude changes.

[0017] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0018] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart illustrating a first embodiment of the rear wheel trajectory prediction method provided by the present invention is shown. Figure 2 The flowchart of a sub-step in step 120 of the rear wheel trajectory prediction method provided by the present invention is shown. Figure 3 A schematic diagram of an embodiment of the rear wheel trajectory prediction system provided by the present invention is shown; Figure 4 A flowchart illustrating an embodiment of the anti-scratch reminder method provided by the present invention is shown; Figure 5 The flowchart of the anti-scratching reminder method provided by the present invention is shown in step 210. Figure 6 A schematic diagram of an embodiment of the anti-scratch reminder system provided by the present invention is shown; Figure 7 The flowchart illustrating the implementation of the rear wheel trajectory prediction and anti-scratching reminder method provided by the present invention is shown. Detailed Implementation

[0019] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0020] Example 1: Figure 1 A flowchart of a first embodiment of the rear wheel trajectory prediction method of the present invention is shown, which is executed by a rear wheel trajectory prediction system. Figure 1 As shown, the method includes the following steps: Step 110: Obtain vehicle parameters, including vehicle mass, wheelbase between the front and rear axles, vehicle pitch angle, steering wheel angle, and vehicle speed.

[0021] Specifically, step 110 requires determining the relevant vehicle data to be used in subsequent steps, including both constant and variable data.

[0022] The constant data includes vehicle mass, distance from the front axle to the vehicle's center of gravity, distance from the rear axle to the vehicle's center of gravity, vehicle center of gravity height, wheelbase between the front and rear axles, and initial thresholds.

[0023] The variable data includes vehicle pitch angle, steering wheel angle, vehicle heading angle, vehicle speed, vehicle gear, vehicle current position, and safety factor.

[0024] Specifically, the vehicle's pitch angle is collected in real time by an inertial measurement unit while driving on a slope. The current steering wheel angle, yaw angle, speed, and gear position are obtained using a steering wheel angle sensor, vehicle speed signal, and gear information. The vehicle's current position is obtained through a vehicle positioning system or relative position tracking.

[0025] Step 120: Obtain the front wheel lateral stiffness and the rear wheel lateral stiffness based on the vehicle pitch angle.

[0026] Step 130: Establish a compensation model based on the wheelbase between the front and rear axles of the vehicle, the vehicle mass, the vehicle speed, the front wheel lateral stiffness, and the rear wheel lateral stiffness.

[0027] Specifically, when a vehicle is going downhill, the pitch angle causes a transfer of load between the front and rear axles, and the change in vehicle attitude alters the actual steering characteristics. Therefore, it is necessary to compensate and correct the traditional Ackerman model based on the changes in steering characteristics to solve the problem of inaccurate prediction of the traditional rear wheel trajectory due to changes in vehicle pitch attitude in complex conditions such as underground parking garage exit ramps and mountain slope parking spaces.

[0028] Step 140: Use the compensation model to compensate the traditional Ackerman model to obtain the rear wheel trajectory prediction model.

[0029] On a level road surface, the trajectory of the vehicle's rear wheels can be derived based on the traditional Ackerman model. For a front-wheel steering vehicle, the trajectory of the rear wheel center is an arc with a radius of curvature of... satisfy:

[0030] In the formula, This indicates the wheelbase between the front and rear axles of a vehicle. This represents the steering wheel angle, corresponding to the front wheel steering angle. It can be obtained by converting the steering wheel angle sensor signal. The conversion relationship is determined by the transmission ratio of the vehicle's steering system. Let the transmission ratio be d, then... , This represents the data obtained from the steering wheel angle sensor signal.

[0031] Step 150: Obtain the predicted rear wheel trajectory based on the current steering wheel angle and the rear wheel trajectory prediction model.

[0032] Specifically, the corrected trajectory curvature radius of the rear wheels is determined by the rear wheel trajectory prediction model, and then the position of the rear wheels is determined by combining the current position of the vehicle.

[0033] The above method generates a rear wheel trajectory prediction model based on the vehicle pitch angle, on the basis of the traditional Ackerman model, and solves the problem of inaccuracy of the traditional model due to changes in vehicle pitch attitude in complex working conditions such as underground garage exit ramps and mountain slope parking spaces.

[0034] Figure 2 A flowchart illustrating a sub-step in step 120 of the rear wheel trajectory prediction method of the present invention is shown.

[0035] In step 120, the front wheel lateral stiffness and rear wheel lateral stiffness are obtained based on the vehicle pitch angle, including the following sub-steps: Step 121: Obtain the front axle vertical load based on the vehicle pitch angle, vehicle mass, wheelbase between the front and rear axles, vehicle center of gravity height, and distance from the rear axle to the vehicle center of gravity. Obtain the rear axle vertical load based on the vehicle pitch angle, vehicle mass, wheelbase between the front and rear axles, vehicle center of gravity height, and distance from the front axle to the vehicle center of gravity.

[0036] The front axle vertical load and the rear axle vertical load are calculated using the following formulas:

[0037]

[0038] In the formula, Indicates the vertical load on the front axle; Indicates the vertical load on the rear axle; Indicates vehicle mass; Represents gravitational acceleration; Indicates the distance from the front axle to the vehicle's center of gravity; Indicates the distance from the rear axle to the vehicle's center of gravity; Indicates the height of the vehicle's center of gravity; Represents the sine function; Indicates the vehicle's pitch angle; This indicates the wheelbase between the front and rear axles of a vehicle.

[0039] Step 122: Obtain the front wheel lateral stiffness based on the lateral stiffness under the unit vertical load and the front axle vertical load; obtain the rear wheel lateral stiffness based on the lateral stiffness under the unit vertical load and the rear axle vertical load.

[0040] The front wheel lateral stiffness and rear wheel lateral stiffness are calculated using the following formulas:

[0041]

[0042] In the formula, Indicates the front wheel lateral stiffness; Indicates the rear wheel lateral stiffness; It represents the lateral stiffness under a unit vertical load.

[0043] Specifically, the rear wheel trajectory prediction model obtained in step 140 is as follows:

[0044] In the formula, Indicates the radius of curvature of the corrected trajectory; Represents the tangent function; Indicates the steering wheel angle; This indicates the wheelbase between the front and rear axles of a vehicle. Indicates vehicle mass; Indicates the vehicle's speed; Indicates the front wheel lateral stiffness; Indicates the rear wheel lateral stiffness; Indicates the distance from the front axle to the vehicle's center of gravity; This indicates the distance from the rear axle to the vehicle's center of gravity.

[0045] Example 2: like Figure 3 As shown, Figure 3 A schematic diagram of an embodiment of the rear wheel trajectory prediction system of the present invention is shown. Based on Embodiment 1, this embodiment provides a rear wheel trajectory prediction system that can execute the rear wheel trajectory prediction method described in Embodiment 1. Specifically, it includes: a data acquisition module 10, a compensation model establishment module 20, a wheel trajectory prediction model establishment module 30, and a rear wheel trajectory prediction module 40.

[0046] The data acquisition module 10 is used to collect the vehicle parameters.

[0047] Specifically, the data acquisition module 10 includes sensors and other components required for acquiring the vehicle parameters.

[0048] Specifically, the vehicle parameters collected by the data acquisition module 10 include both constant and variable data. Constant data includes vehicle mass, distance from the front axle to the vehicle's center of gravity, distance from the rear axle to the vehicle's center of gravity, vehicle center of gravity height, wheelbase between the front and rear axles, and initial threshold values. Variable data includes the vehicle's pitch angle when driving on a slope, the vehicle's current position, steering wheel angle, yaw angle, vehicle speed, and vehicle gear.

[0049] The compensation model establishment module 20 is used to obtain the front wheel lateral stiffness and rear wheel lateral stiffness based on the vehicle pitch angle, and to establish a compensation model based on the wheelbase between the front and rear axles, the vehicle mass, the vehicle speed, the front wheel lateral stiffness and the rear wheel lateral stiffness.

[0050] The wheel trajectory prediction model building module 30 is used to compensate the traditional Ackerman model according to the compensation model to obtain the rear wheel trajectory prediction model.

[0051] The rear wheel trajectory prediction module 40 is used to obtain the predicted rear wheel trajectory based on the current steering wheel angle and the rear wheel trajectory prediction model.

[0052] In some embodiments, the compensation model establishment module 20 includes a vertical load determination unit, a lateral stiffness determination unit, and a compensation model unit.

[0053] The vertical load determination unit is used to determine the front axle vertical load and the rear axle vertical load based on the vehicle pitch angle.

[0054] The lateral stiffness determination unit is used to determine the lateral stiffness of the front wheel based on the front axle vertical load and the lateral stiffness of the rear wheel based on the rear axle vertical load.

[0055] The compensation model unit is used to establish a compensation model based on the wheelbase between the front and rear axles of the vehicle, the vehicle mass, the vehicle speed, the front wheel lateral stiffness, and the rear wheel lateral stiffness.

[0056] The above system determines the position of the rear wheels based on the rear wheel trajectory prediction model. When the system detects that the vehicle is in the first position state, which is a high-risk collision condition, it triggers an early warning mechanism to promptly remind the driver to avoid collisions and improve driving safety when the vehicle's pitch attitude changes.

[0057] Example 3: Figure 4 A flowchart of a first embodiment of the anti-scratch reminder method of the present invention is shown, which is executed by an anti-scratch reminder system. Figure 4 As shown, the method includes the following steps: Step 210: Determine the position state of the rear wheel based on the predicted rear wheel trajectory obtained in Example 1.

[0058] Specifically, the position state includes a first position state and a second position state. The first position state is when the distance between the rear wheel and the lateral obstacle is less than a preset safety threshold, and the second position state is when the distance between the rear wheel and the lateral obstacle is not less than the preset safety threshold. That is, the first position state is when there is a risk of the rear wheel colliding with the lateral obstacle, and the second position state is when there is no risk of the rear wheel colliding with the lateral obstacle.

[0059] Step 220: When the rear wheel is in the first position, the warning mechanism is triggered; when the rear wheel is in the second position, the warning mechanism is deactivated.

[0060] The early warning mechanism serves as a reminder to the driver, guiding them to correct their driving actions promptly. This may include a red indicator light on the central control screen, a voice prompt saying "Please straighten the steering wheel," and vibration alerts from the steering wheel or seat.

[0061] The rear wheel position is determined based on the rear wheel trajectory prediction model. When the vehicle is detected to be in the first position state, that is, the distance between the rear wheel and the lateral obstacle is less than the preset safety threshold, the warning mechanism is triggered to promptly remind the driver to avoid collision and improve driving safety when the vehicle pitch attitude changes.

[0062] Figure 5 The diagram shows a flowchart of a sub-step in step 210 of the anti-scratch reminder method of the present invention.

[0063] In step 210, the position state of the rear wheel is determined based on the predicted rear wheel trajectory obtained in Example 1, and is calculated according to the following sub-steps: Step 211: Determine the current position of the rear wheel based on the rear wheel trajectory prediction model.

[0064] The current position of the rear wheel is as follows:

[0065]

[0066] In the formula, Indicates the position of the rear wheel on the X-axis; Indicates the position of the rear wheel on the Y-axis; Indicates the current coordinates of the vehicle's rear wheel center; Indicates the radius of curvature of the corrected trajectory; Represents the sine function; Represents the cosine function; The parameter representing the arc length along the trajectory; Indicates the vehicle's heading angle.

[0067] Step 212: Determine the equation of the straight line of the lateral obstacle.

[0068] Specifically, the RANSAC algorithm is used to fit the linear equation of the lateral obstacle.

[0069] The specific fitting of the straight-line equation for the lateral obstacle is as follows:

[0070] In the formula, a, b, and c are constants obtained by fitting the linear equation of the lateral obstacle using the RANSAC algorithm; Indicates the location of the obstacle to the side.

[0071] Step 213: Determine the distance between the rear wheel and the lateral obstacle based on the current position of the rear wheel and the straight line equation of the lateral obstacle.

[0072] The distance value is calculated using the following formula:

[0073] In the formula, Indicates the first distance value; express The minimum value in each; This represents the sequence of rear wheel path points within the next T seconds, obtained from the rear wheel trajectory prediction model.

[0074] Step 214: When the distance value is less than the preset safety threshold, determine that the rear wheel is in the first position state; otherwise, determine that the rear wheel is in the second position state.

[0075] To further avoid false triggering of the warning mechanism, when the distance value is less than the preset safety threshold and the vehicle is on a downhill slope and the steering wheel is not straightened, the rear wheel is determined to be in the first position state.

[0076] Specifically, the first distance value being less than the preset safety threshold is expressed as follows:

[0077] In the formula, Indicates the first distance value; Indicates the initial threshold; Indicates the vehicle's speed; This represents the safety factor.

[0078] In some embodiments, the first position state is divided into multiple risk levels based on the distance between the rear wheel and the lateral obstacle; and different early warning mechanisms are set according to the risk levels.

[0079] The risk levels are categorized into low-risk, medium-risk, and high-risk levels. Specifically, the safety factor decreases sequentially from low-risk to medium-risk to high-risk levels.

[0080] Specifically, when the risk level is low, the multimodal reminder is a red indicator on the central control screen; when the risk level is medium, the multimodal reminder is a red indicator on the central control screen and a voice prompt saying "Please straighten the steering wheel"; when the risk level is high, the multimodal reminder is a red indicator on the central control screen, a voice prompt saying "Please straighten the steering wheel" and a vibration reminder on the steering wheel or seat.

[0081] In some embodiments, EPS (Electric Power Steering) and ESC (Electric Stability Control) can be optionally connected to automatically perform slight steering corrections or unilateral braking when the driver is unresponsive and the risk continues to escalate, assisting the vehicle in safely parking.

[0082] In some embodiments, the method further includes a step of outputting a target area image to the vehicle surround view imaging module based on the vehicle's attitude, comprising the following sub-steps: The vehicle's attitude is determined based on the vehicle's pitch angle.

[0083] Obtain the original front view image of the target area.

[0084] When the vehicle pitch angle is greater than the set pitch angle, the downhill duration is not less than the set time, the vehicle speed is less than the set speed, and the steering wheel angle is greater than the set angle, the vehicle is determined to be in the first posture; otherwise, the vehicle is determined to be in the second posture.

[0085] Specifically, the pitch angle is set to 3°, the downhill driving time is set to 1 second, the vehicle speed is set to 8 km / h, and the steering angle is set to 15°. The steering wheel angle here is the absolute value.

[0086] In addition, to further avoid false triggering of visual correction, when the vehicle is in the first posture, it must also meet the following requirements: the absolute value of the change in steering wheel angle is less than 5° / s, and the vehicle is in forward or reverse gear.

[0087] When the vehicle is in the first posture, the original front view image of the target area is visually corrected and used as the target area image, which is then output to the vehicle surround view imaging module. When the vehicle is in the second posture, the original front view image of the target area is used as the target area image and output to the vehicle surround view imaging module.

[0088] Among them, the vehicle surround view imaging module is the vehicle surround view imaging system, which is a driver assistance system that uses four 180° wide-angle cameras installed around the vehicle to collect images, and then processes them through distortion restoration, perspective transformation, and image stitching to form a 360° panoramic top view.

[0089] Specifically, the visual correction includes the following sub-steps: A lookup table for pre-generating a top-position mapping is generated based on standard checkerboard patterns captured by vehicle cameras at different top angles.

[0090] Specifically, the vehicle body equipped with a forward-facing camera is placed on a test bench, and the forward-facing camera is used at different downward angles (e.g., 15°). A standard checkerboard pattern was captured at 30° angles (1° increments); IPM calibration was performed for each angle to generate a coordinate mapping from the "target ground plane grid" to the "raw image pixels"; this mapping was then stored as a LUT. ][x'][z'] → (u, v), a total of 16 tables (corresponding to 16 angles); thus obtaining the mapping lookup table.

[0091] The target output area is divided into a true restoration area and a virtual completion area.

[0092] Specifically, the target corrected image resolution is 480 × 270, adapted to the partial display of the central control screen. The location of the actual restoration area is between 1m and 5m from the vehicle, while the location of the virtual completion area is between 0.2m and 1m from the vehicle. It actively acknowledges that "nearby shots are impossible" and provides spatial perception reference through virtual completion to avoid image fragmentation. The target output area can be the forward-looking area.

[0093] The mapping relationship of the real-world region is obtained from the tilt angle-position mapping lookup table based on the vehicle's pitch angle, and then inverse perspective mapping is performed for correction based on the mapping relationship.

[0094] Specifically, it iterates through each pixel (x', z') in the target output region corresponding to the true-to-true region; it looks up the tilt angle-position mapping table to obtain the coordinates (u, v) of each pixel in the corrected true-to-true region; and it uses bilinear interpolation to obtain the color value. When looking up the table, based on the vehicle's tilt angle, it selects the two closest angles (e.g., ...). =22° and 23°), and perform linear interpolation to obtain the final mapping relationship.

[0095] The virtual completion area is corrected by filling it with a preset texture template.

[0096] Specifically, a preset typical slope bottom texture template (such as gray paving stones, cement roads, and curb stones) is loaded; the preset typical slope bottom texture template is then subjected to perspective deformation based on the vehicle's pitch angle to simulate the nearby ground. When simulating the nearby ground, a semi-transparent red warning stripe can be superimposed to indicate "Close to the front of the vehicle, beware of scraping".

[0097] In the vehicle surround view imaging module, the corrected real-world image area and the corrected virtual completion area are merged, replacing the original forward quadrant to generate an augmented reality display. The rear wheel trajectory prediction line, predicted by the rear wheel trajectory prediction model, is then overlaid on the augmented reality display. A text prompt can be added simultaneously: "Going downhill, please straighten your steering wheel." Furthermore, if the rear wheel trajectory prediction line enters the lateral safety threshold area, the line turns red, and a voice reminder is activated.

[0098] By fusing surround-view images and generating augmented reality displays, the detection results of lane lines or curbs in the calibrated images are used to verify the rationality of the rear wheel trajectory prediction, thus forming a closed-loop feedback.

[0099] In some embodiments, when the vehicle speed is not less than 10 km / h, the perspective correction is stopped and the original front view image is restored; when the steering wheel is straightened, the warning mechanism is stopped; when the camera is obstructed, i.e. the image grayscale variance is less than the threshold, the "camera blurry" icon is displayed, but the virtual completion area is still retained.

[0100] Example 4: like Figure 6 As shown, Figure 6 A schematic diagram of an embodiment of the anti-scratch warning system of the present invention is shown. Based on Embodiment 3, this embodiment provides an anti-scratch warning system that can execute the anti-scratch warning method as described in Embodiment 6. Specifically, it includes: a rear wheel position determination module 50, a control module 60, and a warning module 70.

[0101] The rear wheel position determination module 50 is used to determine the position state of the rear wheel based on the predicted rear wheel trajectory obtained in Embodiment 1. The position state includes a first position state and a second position state. The first position state is a position state in which the distance between the rear wheel and the lateral obstacle is less than a preset safety threshold, and the second position state is a position state in which the distance between the rear wheel and the lateral obstacle is not less than the preset safety threshold.

[0102] Control module: Used to send a warning command to the warning module when the rear wheel is in the first position state.

[0103] Early warning module: Used to control the early warning mechanism according to early warning instructions.

[0104] In some embodiments, the system may also include an attitude determination module, a vision correction module, and an in-vehicle surround view imaging module.

[0105] The attitude determination module is used to determine the vehicle's attitude. When the vehicle is in the first attitude, the vision correction module is activated; when the vehicle is in the second attitude, the vision correction module is deactivated.

[0106] The visual correction module is used to visually correct the original front view image of the target output area before outputting it to the vehicle surround view imaging module.

[0107] The vehicle-mounted surround view imaging module is used to display the target output area.

[0108] The vehicle surround view imaging module is a panoramic imaging parking assistance system, also known as a 360° panoramic visual parking system or a car surround view system. It is a driver assistance system that uses four 180° wide-angle cameras installed around the vehicle to collect images, and then processes them through distortion restoration, perspective transformation, and image stitching to form a 360° panoramic top view.

[0109] The above system determines the position of the rear wheels based on the rear wheel trajectory prediction model. When the system detects that the vehicle is in the first position state, that is, the distance between the rear wheels and the side obstacle is less than the preset safety threshold, it triggers the warning mechanism to promptly remind the driver to avoid collisions and improve driving safety when the vehicle pitch attitude changes.

[0110] Example 5: Figure 7 The diagram shows a structural schematic of an embodiment of the intelligent driving domain controller of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the intelligent driving domain controller.

[0111] like Figure 7 As shown, an intelligent driving domain controller may include: a processor 601, a communication interface 602, a memory 603, and a communication bus 604.

[0112] The processor 601, communication interface 602, and memory 603 communicate with each other via communication bus 604. Communication interface 602 is used to communicate with other devices, such as the intelligent driving domain controller or other server network elements. The processor 601 executes program 610, which, during execution, implements the steps described above in the rear wheel trajectory prediction method and / or anti-scratching warning method to predict the vehicle's rear wheel trajectory and / or provide anti-scratching warnings.

[0113] Specifically, program 610 may include program code, which includes computer-executable instructions.

[0114] Specifically, processor 601 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The intelligent driving domain controller includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0115] Memory 603 is used to store program 610. Memory 603 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0116] Specifically, program 610 can be called by processor 601 to cause the intelligent driving domain controller to perform the following operations: Obtain vehicle parameters, including vehicle mass, wheelbase between the front and rear axles, vehicle pitch angle, steering wheel angle, and vehicle speed. The front wheel lateral stiffness and rear wheel lateral stiffness are obtained based on the vehicle pitch angle; A compensation model is established based on the wheelbase between the front and rear axles of the vehicle, the vehicle mass, the vehicle speed, the front wheel lateral stiffness, and the rear wheel lateral stiffness. The rear wheel trajectory prediction model is obtained by compensating the traditional Ackerman model using the aforementioned compensation model. The predicted rear wheel trajectory is obtained based on the current steering wheel angle and the rear wheel trajectory prediction model.

[0117] The data stream described above is consistent with the data stream in Example 1. For details, please refer to the description in Example 1. This example will not repeat the description.

[0118] In an alternative implementation, program 610 is invoked by processor 601 to cause the intelligent driving domain controller to execute a specific sub-step of step 120 in embodiment 1.

[0119] In an alternative implementation, program 610 may also be invoked by processor 601 to cause the intelligent driving domain controller to perform the following operations: The position state of the rear wheel is determined based on the predicted trajectory of the rear wheel. The position state includes a first position state and a second position state. The first position state is when the distance between the rear wheel and the lateral obstacle is less than a preset safety threshold, and the second position state is when the distance between the rear wheel and the lateral obstacle is not less than the preset safety threshold. When the rear wheel is in the first position, the warning mechanism is triggered; when the rear wheel is in the second position, the warning mechanism is deactivated.

[0120] The data stream described above is consistent with the data stream in Example 3. For details, please refer to the description of Example 3. This example will not repeat the description.

[0121] In one alternative implementation, program 610 is invoked by processor 601 to cause the intelligent driving domain controller to execute a specific sub-step of step 210 in embodiment 1.

[0122] The intelligent driving domain controller described above addresses the inaccuracy of traditional models caused by changes in vehicle pitch attitude in complex conditions such as underground parking garage exit ramps and mountain slopes by generating a rear wheel trajectory prediction model based on the vehicle's pitch angle, building upon the traditional Ackerman model. Simultaneously, it determines the rear wheel position based on the rear wheel trajectory prediction model. When the vehicle is detected in its first position state—a high-risk collision situation—a warning mechanism is triggered to promptly alert the driver to prevent collisions, thus improving driving safety when the vehicle's pitch attitude changes.

[0123] Example 6: This invention provides a computer-readable storage medium storing at least one executable instruction that, when executed on an intelligent driving domain controller, causes the intelligent driving domain controller to perform the rear wheel trajectory prediction method in Embodiment 1 and / or the anti-scratch reminder method in Embodiment 3.

[0124] Specifically, the executable instructions can be used to cause the intelligent driving domain controller to perform the following operations: Obtain vehicle parameters, including vehicle mass, wheelbase between the front and rear axles, vehicle pitch angle, steering wheel angle, and vehicle speed. The front wheel lateral stiffness and rear wheel lateral stiffness are obtained based on the vehicle pitch angle; A compensation model is established based on the wheelbase between the front and rear axles of the vehicle, the vehicle mass, the vehicle speed, the front wheel lateral stiffness, and the rear wheel lateral stiffness. The rear wheel trajectory prediction model is obtained by compensating the traditional Ackerman model using the aforementioned compensation model. The predicted rear wheel trajectory is obtained based on the current steering wheel angle and the rear wheel trajectory prediction model.

[0125] In one alternative implementation, the executable instructions may further be used to cause the intelligent driving domain controller to perform the following operations: The position state of the rear wheel is determined based on the predicted trajectory of the rear wheel. The position state includes a first position state and a second position state. The first position state is when the distance between the rear wheel and the lateral obstacle is less than a preset safety threshold, and the second position state is when the distance between the rear wheel and the lateral obstacle is not less than the preset safety threshold. When the rear wheel is in the first position, the warning mechanism is triggered; when the rear wheel is in the second position, the warning mechanism is deactivated.

[0126] By building upon the traditional Ackerman model and generating a rear-wheel trajectory prediction model based on the vehicle's pitch angle, this addresses the inaccuracy of traditional models caused by changes in vehicle pitch attitude in complex conditions such as underground parking garage exit ramps and mountainous parking spaces. Simultaneously, the rear-wheel trajectory prediction model determines the rear wheel position. When the vehicle is detected in its highest-risk position (high-risk collision condition), a warning mechanism is triggered to promptly alert the driver to prevent collisions, thus improving driving safety when the vehicle's pitch attitude changes.

[0127] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Furthermore, the embodiments of this invention are not directed to any particular programming language.

[0128] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. Similarly, for the sake of brevity and to aid in understanding one or more aspects of the invention, in the description of exemplary embodiments of the invention above, various features of the embodiments are sometimes grouped together in a single embodiment, figure, or description thereof. The claims, which follow the detailed description, are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0129] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components, except that at least some of such features and / or processes or units are mutually exclusive.

[0130] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for predicting rear wheel trajectory, characterized in that, The method includes: Obtain vehicle parameters, including vehicle mass, wheelbase between the front and rear axles, vehicle pitch angle, steering wheel angle, and vehicle speed. The front wheel lateral stiffness and rear wheel lateral stiffness are obtained based on the vehicle pitch angle. A compensation model is established based on the wheelbase between the front and rear axles of the vehicle, the vehicle mass, the vehicle speed, the front wheel lateral stiffness, and the rear wheel lateral stiffness. The rear wheel trajectory prediction model is obtained by compensating the traditional Ackerman model using the aforementioned compensation model. The predicted rear wheel trajectory is obtained based on the current steering wheel angle and the rear wheel trajectory prediction model.

2. The rear wheel trajectory prediction method according to claim 1, characterized in that: The vehicle parameters also include the vehicle's center of gravity height, the distance from the front axle to the vehicle's center of gravity, the distance from the rear axle to the vehicle's center of gravity, and the lateral stiffness under a unit vertical load. The process of obtaining the front wheel lateral stiffness and rear wheel lateral stiffness based on the vehicle pitch angle includes the following sub-steps: The front axle vertical load is obtained based on the vehicle pitch angle, the vehicle mass, the wheelbase between the front and rear axles, the vehicle center of gravity height, and the distance from the rear axle to the vehicle center of gravity. The rear axle vertical load is obtained based on the vehicle pitch angle, the vehicle mass, the wheelbase between the front and rear axles, the vehicle center of gravity height, and the distance from the front axle to the vehicle center of gravity. The front wheel lateral stiffness is obtained based on the lateral stiffness under the unit vertical load and the front axle vertical load. The rear wheel lateral stiffness is obtained based on the lateral stiffness under the unit vertical load and the rear axle vertical load.

3. A rear wheel trajectory prediction system, characterized in that, include: Data acquisition module: used to collect the vehicle parameters, including vehicle mass, wheelbase between the front and rear axles, vehicle pitch angle, steering wheel angle, and vehicle speed; Compensation model establishment module: used to obtain the front wheel lateral stiffness and rear wheel lateral stiffness based on the vehicle pitch angle, and to establish a compensation model based on the wheelbase between the front and rear axles, the vehicle mass, the vehicle speed, the front wheel lateral stiffness and the rear wheel lateral stiffness; Wheel trajectory prediction model establishment module: used to compensate the traditional Ackermann model according to the compensation model to obtain the rear wheel trajectory prediction model; Rear wheel trajectory prediction module: used to obtain the predicted rear wheel trajectory based on the current steering wheel angle and the rear wheel trajectory prediction model.

4. A method for preventing scratches and bumps, characterized in that, The method includes: The rear wheel position state is determined by the rear wheel predicted trajectory obtained according to claim 1 or 2, wherein the position state includes a first position state and a second position state; the first position state is a position state in which the distance between the rear wheel and the lateral obstacle is less than a preset safety threshold, and the second position state is a position state in which the distance between the rear wheel and the lateral obstacle is not less than the preset safety threshold; When the rear wheel is in the first position, the warning mechanism is triggered; when the rear wheel is in the second position, the warning mechanism is deactivated.

5. The anti-scratching reminder method according to claim 4, characterized in that, The distance between the rear wheel and the lateral obstacle is calculated using the following sub-steps: The current position of the rear wheels is determined based on the rear wheel trajectory prediction model. Determine the equation of the line for the lateral obstacle; The distance between the rear wheel and the lateral obstacle is determined based on the current position of the rear wheel and the linear equation of the lateral obstacle.

6. The anti-scratching reminder method according to claim 5, characterized in that, Based on the distance between the rear wheel and the lateral obstacle, the first position state is divided into multiple risk levels; Different early warning mechanisms are set up based on the risk levels.

7. The anti-scratch reminder method according to claim 4, characterized in that, It also includes the step of outputting the target area image to the vehicle surround view imaging module based on the vehicle's attitude, which includes the following sub-steps: The vehicle's attitude is determined based on the vehicle's pitch angle; Obtain the original front view image of the target area; When the vehicle pitch angle is greater than the set pitch angle, the vehicle downhill duration is not less than the set time, the vehicle speed is less than the set speed, and the steering wheel angle is greater than the set angle, the vehicle is determined to be in the first posture. Otherwise, determine that the current vehicle is in the second posture; When the vehicle is in the first posture, the original front view image of the target area is visually corrected and then used as the target area image, which is then output to the vehicle surround view imaging module. When the vehicle is in the second posture, the original front view image of the target area is output as the target area image to the vehicle surround view imaging module.

8. The anti-scratch reminder method according to claim 7, characterized in that, The visual correction of the original front view image of the target area includes the following sub-steps: A lookup table for pre-generating a top angle-position mapping is generated based on standard chessboard patterns captured by vehicle cameras at different top angles. The target output area is divided into a true restoration area and a virtual completion area; The mapping relationship of the realistically restored area is obtained from the tilt angle-position mapping lookup table based on the vehicle's pitch angle, and the inverse perspective mapping is performed for correction based on the mapping relationship; the virtual completion area is filled with a preset texture template for correction.

9. A scratch-proof reminder system, characterized in that, include: Rear wheel position determination module: used to determine the position state of the rear wheel according to the rear wheel predicted trajectory obtained according to claim 1 or 2; wherein, the position state includes a first position state and a second position state; the first position state is a position state in which the distance between the rear wheel and the lateral obstacle is less than a preset safety threshold, and the second position state is a position state in which the distance between the rear wheel and the lateral obstacle is not less than the preset safety threshold; Control module: Used to send a warning command to the warning module when the rear wheel is in the first position state; Early warning module: Used to control the early warning mechanism according to early warning instructions.

10. A smart driving domain controller, characterized in that, include: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to implement the rear wheel trajectory prediction method as described in claim 1 or 2 and / or the anti-scratching reminder method as described in any one of claims 4 to 8 when executed.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the rear wheel trajectory prediction method as described in claim 1 or 2 and / or the anti-scratching reminder method as described in any one of claims 4 to 8.

Images