A method and apparatus for vehicle suspension preview control

Abstract

The embodiment of the present application provides a kind of vehicle suspension preview control method and device, it is applied to vehicle technical field, the vehicle is deployed with binocular camera, the binocular camera is integrated in the headlamp of the vehicle, the method comprises: obtaining target vehicle speed, and according to the target vehicle speed, baseline adjustment is carried out to the binocular camera;Image data collected by the binocular camera after baseline adjustment is obtained;According to the image data, generate road surface preview information;According to the road surface preview information, the suspension of the vehicle is previewed and controlled.Through the embodiment of the present application, the binocular camera is integrated in the headlamp, and the baseline of the binocular camera can be adjusted, the baseline length of the binocular camera is increased and the baseline length is adjustable, the perception ability of the binocular camera is improved, and then the effect of suspension preview control is improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a method and apparatus for vehicle suspension anti-aiming control. Background Technology

[0002] With the rapid development of vehicle technology, the perception and control capabilities of vehicles are improving day by day. Some vehicles are equipped with suspension anti-sighting systems, which can anti-sight control the suspension.

[0003] Existing suspension anti-sight systems primarily rely on LiDAR and monocular cameras from intelligent driving systems. While these can perceive road information to some extent, they suffer from high costs and susceptibility to weather conditions. Although some suspension anti-sight systems use binocular cameras, these cameras are typically mounted above the windshield, limiting their ability to identify obstacles ahead. Furthermore, binocular cameras use a single, integrated structure, and their baseline length is usually fixed, typically between 0.3 and 0.6 meters. This leaves room for improvement in depth perception distance and accuracy, impacting the effectiveness of suspension anti-sight control. Summary of the Invention

[0004] In view of the above problems, a method and apparatus for vehicle suspension anti-aiming control are proposed to overcome or at least partially solve the above problems, comprising:

[0005] A method for vehicle suspension anti-aiming control, characterized in that the vehicle is equipped with a binocular camera, the binocular camera being integrated into the vehicle's headlights, the method comprising:

[0006] The target vehicle speed is obtained, and the baseline of the binocular camera is adjusted according to the target vehicle speed.

[0007] Acquire image data from a stereo camera after baseline adjustment;

[0008] Based on the image data, road surface pre-aiming information is generated;

[0009] Based on the road surface pre-aiming information, the vehicle suspension is pre-aimed.

[0010] Optionally, the vehicle is equipped with an electric slide rail mechanism, which is used to control the binocular camera to perform baseline adjustment.

[0011] Optionally, baseline adjustment of the binocular camera is performed based on the target vehicle speed, including:

[0012] Obtain the road type, and determine the target baseline length based on the road type and the target vehicle speed;

[0013] The baseline of the binocular camera is adjusted according to the target baseline length.

[0014] Optionally, determining the target baseline length based on the road type and the target vehicle speed includes:

[0015] When the road type is a straight road segment or a near-straight road segment, the target baseline length is determined based on the target vehicle speed, according to the strategy corresponding to the speed range of the target vehicle speed.

[0016] In the case where the road type is a curved section, the curve radius is obtained, and the target baseline length is determined based on the curve radius and the target vehicle speed.

[0017] Optionally, the target baseline length is determined based on the target vehicle speed according to the strategy corresponding to the speed range in which the target vehicle speed is located, including:

[0018] When the target vehicle speed falls within a first vehicle speed range, the target baseline length is determined based on the target vehicle speed and the system response time.

[0019] When the target vehicle speed falls within the second vehicle speed range, the target baseline length is determined based on the target vehicle speed and the empirical coefficient corresponding to the target vehicle speed.

[0020] When the target vehicle speed falls within the third vehicle speed range, the target baseline length is determined based on the target vehicle speed and the maximum braking deceleration.

[0021] Wherein, the vehicle speed in the first speed range is less than the vehicle speed in the second speed range, and the vehicle speed in the second speed range is less than the vehicle speed in the third speed range.

[0022] Optionally, determining the target baseline length based on the curve radius and the target vehicle speed includes:

[0023] The maximum baseline length is determined based on the target vehicle speed and the maximum braking deceleration.

[0024] Determine the radius difference between the curve radius and the preset radius;

[0025] The target baseline length is determined based on the maximum baseline length and the radius difference.

[0026] Optionally, the target vehicle speed is obtained, including:

[0027] Obtain vehicle-related parameters and perform trajectory prediction based on the vehicle-related parameters; wherein, the vehicle-related parameters include the vehicle's yaw rate;

[0028] The target vehicle speed is determined based on the trajectory prediction results.

[0029] Optionally, based on the image data, road surface preview information is generated, including:

[0030] The image data is calibrated;

[0031] Feature extraction is performed on the calibrated image data to obtain feature information, and the feature information is analyzed to obtain image analysis results; wherein, the feature information includes depth information;

[0032] Based on the image analysis results and vehicle-related parameters, road surface preview information is generated.

[0033] Optionally, the image data includes first image data and second image data acquired by the binocular camera, and feature extraction is performed on the image data to obtain feature information, including:

[0034] Determine the Hamming distance between two pixels of the same object in the first image data and the second image data, and determine the matching cost based on the Hamming distance;

[0035] For each pixel, multiple paths are determined, and the path cost of the multiple paths is determined by combining the matching cost and the smoothness between pixels in each path.

[0036] From the path costs of the multiple paths, determine the path cost with the minimum, and determine the disparity between the first image data and the second image data based on the path cost with the minimum.

[0037] Depth information is determined based on the baseline length after baseline adjustment, the parallax, and the camera focal length.

[0038] Optionally, based on the road surface pre-aiming information, the vehicle suspension is pre-aimed, including:

[0039] The vehicle's speed-related parameters are acquired, and the height and / or stiffness of the vehicle's suspension are pre-aimed based on the road surface pre-aiming information and the speed-related parameters.

[0040] A device for vehicle suspension anti-aiming control, wherein the vehicle is equipped with a binocular camera integrated into the vehicle's headlights, the device comprising:

[0041] A baseline adjustment module is used to acquire the target vehicle speed and adjust the baseline of the binocular camera according to the target vehicle speed.

[0042] The image data acquisition module is used to acquire image data captured by the baseline-adjusted binocular camera;

[0043] The road surface preview information generation module is used to generate road surface preview information based on the image data;

[0044] The aiming control module is used to perform aiming control on the vehicle suspension based on the road surface aiming information.

[0045] The embodiments of the present invention have the following advantages:

[0046] In this embodiment of the invention, a binocular camera is deployed in the vehicle and integrated into the vehicle's headlight. By acquiring the target vehicle speed and adjusting the baseline of the binocular camera based on the target vehicle speed, image data collected by the binocular camera after baseline adjustment is acquired. Based on the image data, road surface pre-aiming information is generated. Based on the road surface pre-aiming information, pre-aiming control of the vehicle suspension is performed. This achieves the integration of the binocular camera into the headlight and enables baseline adjustment of the binocular camera, increasing the baseline length of the binocular camera and making the baseline length adjustable, thereby improving the perception capability of the binocular camera and thus improving the effect of suspension pre-aiming control. Attached Figure Description

[0047] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of the steps of a vehicle suspension anti-aiming control method provided in some embodiments of the present invention;

[0049] Figure 2 This is a schematic diagram of the architecture of a road pre-aiming system provided in some embodiments of the present invention;

[0050] Figure 3 This is a flowchart illustrating the steps of a baseline length adjustment process provided in some embodiments of the present invention;

[0051] Figure 4 This is a flowchart of the steps of another vehicle suspension anti-aiming control method provided in some embodiments of the present invention;

[0052] Figure 5 This is a flowchart of the steps of another vehicle suspension anti-aiming control method provided in some embodiments of the present invention;

[0053] Figure 6 This is a flowchart of the steps of another vehicle suspension anti-aiming control method provided in some embodiments of the present invention;

[0054] Figure 7This is a flowchart of the steps of a method for vehicle suspension anti-aiming control provided in some embodiments of the present invention;

[0055] Figure 8 This is a structural block diagram of a vehicle suspension anti-aiming control device provided in some embodiments of the present invention. Detailed Implementation

[0056] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0057] Reference Figure 1 The diagram shows a flowchart of a method for vehicle suspension anti-aiming control provided by some embodiments of the present invention. The vehicle may be equipped with a binocular camera, which may be integrated into the vehicle's headlights, such as two cameras being installed inside the left and right headlights respectively.

[0058] In this embodiment of the invention, by installing a binocular camera in the headlight of a vehicle, the baseline distance of binocular stereo vision is effectively improved by utilizing the maximum lateral space of the vehicle body. This improves the recognition distance and accuracy, enabling the suspension control system to acquire road information ahead more promptly and efficiently, thereby actively controlling the vehicle suspension in a timely manner and improving the comfort of the driver and passengers.

[0059] In some examples, the baseline length of the binocular camera can reach 1.5 to 1.7m, compared with the conventional baseline length of 0.3 to 0.6m. This can improve the ranging accuracy and maximum ranging distance of the binocular camera. For example, the theoretical ranging accuracy can be improved by 60% to 80%, and the maximum ranging distance can be improved by about 40%.

[0060] Specifically, it may include the following steps:

[0061] Step 101: Obtain the target vehicle speed and adjust the baseline of the binocular camera according to the target vehicle speed.

[0062] In some examples, the target speed can be the predicted speed, i.e., the vehicle's speed over a future time period (e.g., 2 seconds in the future), to improve the accuracy of the aiming. Of course, the target speed can also be the vehicle's real-time speed.

[0063] In practical applications, in order to achieve good suspension anti-aiming control at different vehicle speeds, the baseline length of the binocular camera can be adjusted according to the target vehicle speed.

[0064] In some embodiments of the present invention, the vehicle is provided with an electric slide rail mechanism, which is used to control the binocular camera to perform baseline adjustment.

[0065] In some examples, the electric sliding rail mechanism can be integrated into the headlight and electrically connected to the vehicle. The vehicle can control the electric sliding rail mechanism via electrical signals, which in turn can control the movement of the binocular camera to adjust the baseline length of the binocular camera.

[0066] In some embodiments of the present invention, baseline adjustment of the binocular camera is performed according to the target vehicle speed, including: acquiring the road type, and determining the target baseline length according to the road type and the target vehicle speed; and performing baseline adjustment of the binocular camera according to the target baseline length.

[0067] In practical applications, road types can include straight road sections, semi-straight road sections, and curved road sections. For different road types, the vehicle's driving state and the required road surface information differ. Therefore, the appropriate baseline length can be determined based on the road type and target vehicle speed. Under different vehicle speeds and road types, the binocular camera can operate with the optimal baseline length, improving perception capabilities.

[0068] In some examples, a straight road segment can be a road segment with a road curvature of 0, a quasi-straight road segment can be a road segment that tends to be straight, such as a quasi-straight road segment with a road curvature less than a preset curvature threshold, such as a preset curvature threshold of 0.05, and a curved road segment can be a road segment with a road curvature greater than a preset curvature threshold.

[0069] In some embodiments of the present invention, determining the target baseline length based on the road type and the target vehicle speed includes: when the road type is a straight road segment or a near-straight road segment, determining the target baseline length based on the target vehicle speed according to the strategy corresponding to the speed range of the target vehicle speed.

[0070] For straight or near-straight road sections, since the vehicle's direction of travel is relatively fixed, the need for road information acquisition is mainly concentrated at a relatively long distance. The appropriate baseline length can be determined based on the target vehicle speed. Specifically, the vehicle speed range can be divided into multiple intervals based on the target speed, with each interval corresponding to a different baseline length adjustment strategy. For example, in the low-speed interval, because the vehicle speed is slower, the real-time requirement for road information is relatively lower, and the baseline length can be appropriately shortened to improve the ranging accuracy of the binocular camera. In the high-speed interval, because the vehicle speed is faster, road information from a greater distance is needed for advance suspension aiming control, and the baseline length can be appropriately increased to expand the perception range of the binocular camera.

[0071] In some embodiments of the present invention, determining the target baseline length based on the target vehicle speed according to a strategy corresponding to the vehicle speed range in which the target vehicle speed is located includes:

[0072] When the target vehicle speed falls within a first vehicle speed range, the target baseline length is determined based on the target vehicle speed and the system response time.

[0073] When the target vehicle speed falls within the second vehicle speed range, the target baseline length is determined based on the target vehicle speed and the empirical coefficient corresponding to the target vehicle speed.

[0074] When the target vehicle speed falls within the third vehicle speed range, the target baseline length is determined based on the target vehicle speed and the maximum braking deceleration.

[0075] Wherein, the vehicle speed in the first speed range is less than the vehicle speed in the second speed range, and the vehicle speed in the second speed range is less than the vehicle speed in the third speed range. For example, the first speed range is 0 to 30 km / h, the second speed range is 30 to 80 km / h, and the third speed range is above 80 km / h.

[0076] In scenarios involving straight or near-straight road sections, different strategies can be employed to determine the target baseline length based on the target vehicle speed range. In the first speed range, due to the low speed, system response time significantly impacts the baseline length. Determining the target baseline length based on both the target speed and system response time ensures accurate acquisition of road information at low speeds. In the second speed range, with moderate speeds, determining the target baseline length based on the target speed and corresponding empirical coefficients improves processing efficiency while maintaining accuracy. In the third speed range, with higher speeds, the real-time and accuracy requirements for road information are even greater. Determining the target baseline length based on the target speed and maximum braking deceleration ensures timely response and suspension control at high speeds, enhancing driving safety and stability.

[0077] For example, if the first vehicle speed range is 0–30 km / h, the following formula can be used:

[0078]

[0079] in, For system response time, For the target vehicle speed, The target baseline length is within the first vehicle speed range, such as 1.5 to 1.6 meters.

[0080] For example, if the second speed range is 30–80 km / h, the following formula can be used:

[0081]

[0082] in, This is an empirical coefficient (obtained through actual vehicle calibration, such as when the target vehicle speed is 30km / h). (Value 0.56) For the target vehicle speed, The target baseline length is within the second speed range, such as 1.6 to 1.7 meters.

[0083] For example, for the third speed range of 80km / h and above, the following formula can be used:

[0084]

[0085] in, This is the maximum braking deceleration (related to vehicle braking performance and current vehicle speed). For the target vehicle speed, The target baseline length is within the third speed range, such as 1.7m.

[0086] In some embodiments of the present invention, determining the target baseline length based on the road type and the target vehicle speed includes: when the road type is a curved road segment, obtaining the curve radius, and determining the target baseline length based on the curve radius and the target vehicle speed.

[0087] For curved road sections, since the vehicle's direction of travel changes, the need to obtain road information requires not only distance but also consideration of the vehicle's steering and curve conditions. Therefore, when driving on a curve, the target baseline length can be determined by combining the target vehicle speed and the curve radius.

[0088] In some embodiments of the present invention, determining the target baseline length based on the curve radius and the target vehicle speed includes: determining the maximum baseline length based on the target vehicle speed and the maximum braking deceleration; determining the radius difference between the curve radius and the preset radius; and determining the target baseline length based on the maximum baseline length and the radius difference.

[0089] When the road type is a curved section, the maximum baseline length is determined based on the target vehicle speed and maximum braking deceleration to ensure sufficient road surface information is obtained when driving on curves, thereby improving driving safety and stability. Then, the difference between the curve radius and the preset radius can be determined to reflect the curvature of the curve. The target baseline length is determined based on the difference between the maximum baseline length and the radius, enabling the binocular camera to operate with the optimal baseline length when driving on curves, thus improving the perception of the road surface.

[0090] For example, the following formula can be used:

[0091]

[0092] Where R is the curve radius, R0 is the preset radius (e.g., 50m), and k is the attenuation coefficient (e.g., 0.05). For the maximum baseline length, This represents the target baseline length on curved road sections.

[0093] In some examples, the maximum baseline length The following formula can be used:

[0094]

[0095] in, For maximum braking deceleration, For the target vehicle speed, The target baseline length is within the first vehicle speed range, such as 1.7m.

[0096] Compared to existing road prediction systems, which are unable to effectively predict road conditions when vehicles are turning, on uneven or laterally inclined surfaces, resulting in poor vehicle posture and affecting passenger comfort and driving safety, this invention enables a road prediction system that uses a binocular camera installed in the vehicle's headlights to perceive road surface information in real time and feeds it back to the vehicle's suspension control system. This allows for adjustments to the suspension height and stiffness for different road types, such as straight sections, semi-straight sections, and curved sections, thereby improving passenger comfort and reducing system costs.

[0097] In some embodiments of the present invention, obtaining the target vehicle speed includes: obtaining vehicle-related parameters and performing trajectory prediction based on the vehicle-related parameters; wherein the vehicle-related parameters include the yaw rate of the vehicle; and determining the target vehicle speed based on the trajectory prediction result.

[0098] In practical applications, the vehicle's driving status changes in real time. To accurately predict the vehicle speed in the future, relevant vehicle parameters can be used for trajectory prediction. After obtaining the trajectory prediction results, the target vehicle speed can be determined by observing the changes in the trajectory (e.g., by using the trajectory prediction results to know the future position and heading angle, and then calculating the target vehicle speed based on the current position and heading angle and the future position and heading angle, so that the vehicle can be controlled at the target speed to reach the future position and heading angle).

[0099] In some examples, the vehicle's yaw rate, as a crucial parameter of its dynamic characteristics, reflects its steering behavior during operation. By incorporating yaw rate compensation, the accuracy and precision of vehicle trajectory prediction can be improved.

[0100] In some examples, trajectory prediction includes position prediction and heading angle prediction, which can be achieved using the following formula:

[0101]

[0102] Where t is the current time, Δt is the time step, and x t Let y be the x-coordinate of the current time. t Let x be the ordinate at the current time. t+Δt For the predicted x-coordinate, y t+Δt Let ψ be the predicted ordinate. t Let ψ be the heading angle at the current moment. t+Δt The predicted heading angle is given by γ, the yaw rate is given by δ, the steering angle (steering wheel angle) is given by δ, v1 is the linear velocity, L is the wheelbase (distance between the front and rear axles of the vehicle), and tan(δ) is the tangent of the steering angle, which determines the steering curvature.

[0103] like Figure 2 By acquiring vehicle-related parameters such as inertial measurement data, steering angle, and wheel speed, a trajectory prediction model is used to predict the trajectory for the next 2 seconds. Then, based on the trajectory prediction results (including the predicted position and the predicted heading angle), the target vehicle speed is determined. Subsequently, based on the target vehicle speed and road type, a baseline length decision is made to obtain the target baseline length. Then, according to the target baseline length, the electric sliding rail is controlled to execute commands to adjust the baseline length.

[0104] Step 102: Acquire image data from the binocular camera after baseline adjustment.

[0105] After baseline adjustment, image data can be acquired through the baseline-adjusted binocular cameras.

[0106] Step 103: Generate road surface pre-aiming information based on the image data.

[0107] After obtaining image data, road surface prediction information can be obtained through image data processing and analysis. In some examples, road surface prediction information includes road surface type, lane lines to be detected, and road surface curvature.

[0108] In some embodiments of the present invention, road surface preview information is generated based on the image data, including:

[0109] The image data is calibrated; features are extracted from the calibrated image data to obtain feature information, and the feature information is analyzed to obtain image analysis results; wherein, the feature information includes depth information; based on the image analysis results and vehicle-related parameters, road surface preview information is generated.

[0110] In some examples, calibrating image data may include distortion correction, image normalization, and illumination compensation to ensure image quality. For example, distortion correction can be performed using the following formula:

[0111]

[0112] Where (u, v) are the x and y coordinates of the image coordinate system, (u0, v0) is the origin of the image coordinate system, f is the camera focal length, and x' and y' are the normalized image coordinates. After normalization, the two images are projected onto the same plane, so that the target is located on the same view plane of the two cameras, simplifying the depth information matching process.

[0113] In practical applications, to obtain more accurate road surface preview information, feature extraction can be performed on image data. Feature information can include road surface height, shape, texture, and depth information. By extracting and analyzing this feature information, the road conditions ahead of the vehicle can be more accurately assessed, providing strong support for subsequent suspension preview control.

[0114] After obtaining the feature information, the feature information can be analyzed to obtain image analysis results, such as road surface type, detection lane lines, road surface curvature, etc. Then, the image analysis results and vehicle-related parameters such as inertial measurement data and vehicle speed can be fused to obtain road surface preview information.

[0115] In some embodiments of the present invention, the image data includes first image data and second image data acquired by the binocular camera, and feature extraction is performed on the image data to obtain feature information, including:

[0116] Sub-step 11: Determine the Hamming distance between two pixels of the same object in the first image data and the second image data, and determine the matching cost based on the Hamming distance.

[0117] In practical applications, the Census (Census Transform Algorithm, a non-parametric local image transformation method) transformation algorithm can be used to obtain the matching cost function as follows:

[0118]

[0119] in, For matching cost, Hamming is the function for calculating Hamming distance. and Let p = (x, y) be the binary descriptor for two pixels of the same object in the first and second image data, where p is the pixel coordinate of the left image (one of the first and second image data). d =(x−d,y) represents the coordinates of the right image (the other one between the first and second image data), and d represents the disparity.

[0120] The Census transform algorithm describes the left and right views and achieves matching by calculating the Hamming distance between the two images, thus improving matching accuracy and robustness.

[0121] Sub-step 12: For each pixel, determine multiple paths, and combine the matching cost and the smoothness between pixels in each path to determine the path cost of the multiple paths.

[0122] In practical applications, a semi-global block matching (SGBM) algorithm can be used for cost aggregation. Cost aggregation smooths and constrains the original matching cost, so that the final disparity selection is based not only on local pixel similarity, but also on the continuity of disparity values ​​of adjacent pixels.

[0123] In some examples, the smoothness between pixels in each path is the absolute value of the difference between the disparity values ​​of adjacent pixels. The smaller the smoothness, the more continuous the disparity values ​​of adjacent pixels are, and the smaller the path cost.

[0124] Each pixel has 8 adjacent pixels, meaning there are 8 path directions. Multiple paths can be selected, such as 4 or 6. For each path, the path cost can be determined by combining the matching cost and the smoothness between pixels in each path.

[0125] In some examples, the path cost can be expressed using the following formula:

[0126]

[0127] Where r is the path, For path cost, For matching cost, K is the cumulative number of pixels traversed along the path, P1 and P2 are smoothing penalty terms (P2>P1), p=(x,y) are the pixel coordinates of the left image (one of the first and second image data), p d =(x−d,y) represents the coordinates of the right image (the other one between the first and second image data), d represents the disparity, and L() is the cost calculation function.

[0128] Sub-step 13: Determine the minimum path cost from the path costs of the multiple paths, and determine the disparity between the first image data and the second image data based on the minimum path cost.

[0129] In some examples, after obtaining the path costs of multiple paths, a total cost aggregation can be performed to obtain a path cost set. For example, the path cost set can be expressed using the following formula:

[0130]

[0131] Where r is the path, and R is the set of aggregated paths. For path cost, This is the set of path costs.

[0132] After obtaining the set of path costs, the path cost with the smallest cost can be selected from it.

[0133] For example, minimum path cost The following formula can be used:

[0134]

[0135] After obtaining the minimum path cost, the minimum path cost can be used as the disparity between the first image data and the second image data.

[0136] Sub-step 14: Determine depth information based on the baseline length after baseline adjustment, the parallax, and the camera focal length.

[0137] After obtaining the parallax, depth information can be determined using the baseline length after baseline adjustment, the parallax, and the camera focal length. In some examples, depth information can be used for road surface type identification and road surface smoothness calculation.

[0138] For example, depth information can be expressed using the following formula:

[0139] z=f * b / d

[0140] Where z represents the depth information between the binocular camera and the target object, f represents the focal length of the camera, b represents the distance between the optical centers of the two cameras, i.e. the baseline length after baseline adjustment, and d represents the parallax.

[0141] Step 104: Based on the road surface pre-aiming information, perform pre-aiming control on the vehicle suspension.

[0142] After obtaining road surface pre-aiming information, a control signal can be generated based on the road surface pre-aiming information and sent to the suspension control system. The suspension control system then performs pre-aiming control on the vehicle suspension to improve the vehicle's driving stability and comfort.

[0143] In some embodiments of the present invention, the vehicle suspension is pre-aimed based on the road surface pre-aiming information, including: acquiring the vehicle's speed-related parameters, and pre-aiming the height and / or stiffness of the vehicle suspension based on the road surface pre-aiming information and the speed-related parameters.

[0144] In practical applications, the suspension can be adjusted using appropriate control strategies based on road surface preview information such as road type, lane markings, and road curvature, combined with real-time vehicle conditions such as speed, acceleration, and steering angle. For example, when a curve is detected ahead, the suspension stiffness and damping can be adjusted in advance based on the curve radius and vehicle speed, allowing the vehicle to better maintain road surface contact while cornering, improving driving stability and ride comfort. Similarly, when a bumpy road section is detected ahead, the suspension height and travel can be adjusted in advance to reduce the absorption and transmission of bumps, improving ride smoothness and ride comfort.

[0145] like Figure 3 and Figure 4 The aiming system is equipped with a binocular camera, an aiming controller, and a suspension control system. The aiming controller can be installed independently in the passenger compartment of the vehicle or integrated with the suspension control system into a single controller. The aiming controller includes an image acquisition module, an image calibration module, and a data fusion module.

[0146] The image acquisition module receives image data from the binocular camera and transmits the image data to the image processing module. The image processing module includes an image calibration submodule, an image feature extraction submodule, and an image analysis submodule. Specifically: the image calibration submodule calibrates the acquired images, including distortion correction, image normalization, and illumination compensation, to ensure image quality; the image feature extraction submodule extracts features such as road height, shape, texture, and depth information from the calibrated images; and the image analysis submodule analyzes the extracted features, identifies road surface types, detects lane lines, and calculates parameters such as road surface curvature. It then fuses the image analysis results with vehicle-related parameters to generate road surface preview information. Based on the road surface preview information, vehicle speed, acceleration, and other speed-related parameters, it calculates the required suspension height and stiffness, and transmits the control signals to the suspension control system.

[0147] In some examples, a machine learning module can also be set up to train and update the image processing algorithm in real time, improving the system's recognition accuracy and adaptability. The machine learning module includes a feature extractor, a loss function definer, and an optimization algorithm. The feature extractor defines the features to be learned, the loss function definer describes the learning effect, and the optimization algorithm implements the training and updating of the model.

[0148] In this embodiment of the invention, a binocular camera is deployed in the vehicle and integrated into the vehicle's headlight. By acquiring the target vehicle speed and adjusting the baseline of the binocular camera based on the target vehicle speed, image data collected by the binocular camera after baseline adjustment is acquired. Based on the image data, road surface pre-aiming information is generated. Based on the road surface pre-aiming information, pre-aiming control of the vehicle suspension is performed. This achieves the integration of the binocular camera into the headlight and enables baseline adjustment of the binocular camera, increasing the baseline length of the binocular camera and making the baseline length adjustable, thereby improving the perception capability of the binocular camera and thus improving the effect of suspension pre-aiming control.

[0149] In some examples, the specific effects may include the following:

[0150] 1. The binocular stereo vision system features a large baseline, long recognition distance, and high accuracy. Compared with traditional monocular vision sensors, it can more accurately identify key features such as road height and shape, effectively improving the problem of insufficient visual accuracy in existing technologies.

[0151] 2. By acquiring road information in real time and feeding it back to the vehicle suspension control system, the suspension height and stiffness can be adjusted in a timely manner, which greatly improves the driving comfort of the vehicle under various complex road conditions and effectively solves the problem of poor vehicle posture in the existing technology.

[0152] 3. The system has a simple structure and is easy to implement. It uses the vehicle headlight as the mounting carrier, which reduces additional hardware investment and makes it easy to promote and apply in various vehicle models.

[0153] 4. It has achieved intelligent and adaptive capabilities, and can automatically adjust the suspension height and stiffness according to real-time sensor data to adapt to complex and ever-changing road environments, thereby improving the vehicle's active safety performance.

[0154] Reference Figure 5 The diagram illustrates a flowchart of another method for vehicle suspension anti-aiming control provided by some embodiments of the present invention. The vehicle is equipped with a binocular camera integrated into the vehicle's headlights, and the method may specifically include the following steps:

[0155] Step 501: Obtain vehicle-related parameters and perform trajectory prediction based on the vehicle-related parameters; wherein, the vehicle-related parameters include the vehicle's yaw rate.

[0156] Step 502: Determine the target vehicle speed based on the trajectory prediction results.

[0157] Step 503: Adjust the baseline of the binocular camera according to the target vehicle speed.

[0158] Step 504: Acquire image data from the binocular camera after baseline adjustment.

[0159] Step 505: Generate road surface pre-aiming information based on the image data.

[0160] Step 506: Based on the road surface pre-aiming information, perform pre-aiming control on the vehicle suspension.

[0161] Reference Figure 6 The diagram illustrates a flowchart of another method for vehicle suspension anti-aiming control provided by some embodiments of the present invention. The vehicle is equipped with a binocular camera integrated into the vehicle's headlights, and the method may specifically include the following steps:

[0162] Step 601: Obtain the target vehicle speed and road type.

[0163] Step 602: If the road type is a straight road segment or a near-straight road segment, determine the target baseline length according to the strategy corresponding to the speed range of the target vehicle speed.

[0164] Step 603: Adjust the baseline of the binocular camera according to the target baseline length.

[0165] Step 604: Acquire image data from the binocular camera after baseline adjustment.

[0166] Step 605: Generate road surface pre-aiming information based on the image data.

[0167] Step 606: Based on the road surface pre-aiming information, perform pre-aiming control on the vehicle suspension.

[0168] Reference Figure 7 The diagram illustrates a flowchart of another method for vehicle suspension anti-aiming control provided by some embodiments of the present invention. The vehicle is equipped with a binocular camera integrated into the vehicle's headlights, and the method may specifically include the following steps:

[0169] Step 701: Obtain the target vehicle speed and road type.

[0170] Step 702: If the road type is a curved section, obtain the curve radius and determine the target baseline length based on the curve radius and the target vehicle speed.

[0171] Step 703: Adjust the baseline of the binocular camera according to the target baseline length.

[0172] Step 704: Acquire image data from the binocular camera after baseline adjustment;

[0173] Step 705: Generate road surface pre-aiming information based on the image data;

[0174] Step 706: Based on the road surface pre-aiming information, perform pre-aiming control on the vehicle suspension.

[0175] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0176] Reference Figure 8 The diagram illustrates a structural schematic of a vehicle suspension anti-aiming control device according to some embodiments of the present invention. The vehicle is equipped with a binocular camera, which is integrated into the vehicle's headlights. Specifically, the binocular camera may include the following modules:

[0177] The baseline adjustment module 801 is used to acquire the target vehicle speed and adjust the baseline of the binocular camera according to the target vehicle speed.

[0178] Image data acquisition module 802 is used to acquire image data captured by a binocular camera after baseline adjustment;

[0179] The road surface preview information generation module 803 is used to generate road surface preview information based on the image data;

[0180] The pre-aiming control module 804 is used to perform pre-aiming control on the vehicle suspension based on the road surface pre-aiming information.

[0181] Optionally, the vehicle is equipped with an electric slide rail mechanism, which is used to control the binocular camera to perform baseline adjustment.

[0182] Optionally, baseline adjustment of the binocular camera is performed based on the target vehicle speed, including:

[0183] Obtain the road type, and determine the target baseline length based on the road type and the target vehicle speed;

[0184] The baseline of the binocular camera is adjusted according to the target baseline length.

[0185] Optionally, determining the target baseline length based on the road type and the target vehicle speed includes:

[0186] When the road type is a straight road segment or a near-straight road segment, the target baseline length is determined according to the strategy corresponding to the speed range of the target vehicle speed.

[0187] In the case where the road type is a curved section, the curve radius is obtained, and the target baseline length is determined based on the curve radius and the target vehicle speed.

[0188] Optionally, the target baseline length is determined based on the target vehicle speed according to the strategy corresponding to the speed range in which the target vehicle speed is located, including:

[0189] When the target vehicle speed falls within a first vehicle speed range, the target baseline length is determined based on the target vehicle speed and the system response time.

[0190] When the target vehicle speed falls within the second vehicle speed range, the target baseline length is determined based on the target vehicle speed and the empirical coefficient corresponding to the target vehicle speed.

[0191] When the target vehicle speed falls within the third vehicle speed range, the target baseline length is determined based on the target vehicle speed and the maximum braking deceleration.

[0192] Wherein, the vehicle speed in the first speed range is less than the vehicle speed in the second speed range, and the vehicle speed in the second speed range is less than the vehicle speed in the third speed range.

[0193] Optionally, determining the target baseline length based on the curve radius and the target vehicle speed includes:

[0194] The maximum baseline length is determined based on the target vehicle speed and the maximum braking deceleration.

[0195] Determine the radius difference between the curve radius and the preset radius;

[0196] The target baseline length is determined based on the maximum baseline length and the radius difference.

[0197] Optionally, the target vehicle speed is obtained, including:

[0198] Obtain vehicle-related parameters and perform trajectory prediction based on the vehicle-related parameters; wherein, the vehicle-related parameters include the vehicle's yaw rate;

[0199] The target vehicle speed is determined based on the trajectory prediction results.

[0200] Optionally, based on the image data, road surface preview information is generated, including:

[0201] The image data is calibrated; features are extracted from the calibrated image data to obtain feature information, and the feature information is analyzed to obtain image analysis results; wherein, the feature information includes depth information;

[0202] Based on the image analysis results and vehicle-related parameters, road surface preview information is generated.

[0203] Optionally, the image data includes first image data and second image data acquired by the binocular camera, and feature extraction is performed on the image data to obtain feature information, including:

[0204] Determine the Hamming distance between two pixels of the same object in the first image data and the second image data, and determine the matching cost based on the Hamming distance;

[0205] For each pixel, multiple paths are determined, and the path cost of the multiple paths is determined by combining the matching cost and the smoothness between pixels in each path.

[0206] From the path costs of the multiple paths, determine the path cost with the minimum, and determine the disparity between the first image data and the second image data based on the path cost with the minimum.

[0207] Depth information is determined based on the baseline length after baseline adjustment, the parallax, and the camera focal length.

[0208] Optionally, based on the road surface pre-aiming information, the vehicle suspension is pre-aimed, including:

[0209] The vehicle's speed-related parameters are acquired, and the vehicle's suspension is pre-aimed based on the road surface pre-aiming information and the speed-related parameters.

[0210] Optionally, the vehicle suspension is pre-aimed, including: pre-aiming the height and / or stiffness of the vehicle suspension.

[0211] In this embodiment of the invention, a binocular camera is deployed in the vehicle and integrated into the vehicle's headlight. By acquiring the target vehicle speed and adjusting the baseline of the binocular camera based on the target vehicle speed, image data collected by the binocular camera after baseline adjustment is acquired. Based on the image data, road surface pre-aiming information is generated. Based on the road surface pre-aiming information, pre-aiming control of the vehicle suspension is performed. This achieves the integration of the binocular camera into the headlight and enables baseline adjustment of the binocular camera, increasing the baseline length of the binocular camera and making the baseline length adjustable, thereby improving the perception capability of the binocular camera and thus improving the effect of suspension pre-aiming control.

[0212] Some embodiments of the present invention also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method described above.

[0213] Some embodiments of the present invention also provide a computer-readable storage medium on which a computer program is stored, and which, when executed by a processor, implements the method described above.

[0214] Some embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the method described above.

[0215] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0216] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0217] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0218] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0219] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0220] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0221] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0222] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0223] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the aforementioned element.

[0224] The above provides a detailed description of the method and apparatus for vehicle suspension anti-aiming control. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for vehicle suspension anti-aiming control, characterized in that, The vehicle is equipped with a binocular camera, which is integrated into the vehicle's headlights; the method includes: The target vehicle speed is obtained, and the baseline of the binocular camera is adjusted according to the target vehicle speed; wherein the target vehicle speed is the predicted vehicle speed or the real-time vehicle speed of the vehicle. Acquire image data from a stereo camera after baseline adjustment; Based on the image data, road surface pre-aiming information is generated; Based on the road surface pre-aiming information, the vehicle suspension is pre-aimed.

2. The method according to claim 1, characterized in that, The vehicle is equipped with an electric slide rail mechanism, which is used to control the binocular camera to perform baseline adjustment. Based on the target vehicle speed, baseline adjustment is performed on the binocular camera, including: Obtain the road type, and determine the target baseline length based on the road type and the target vehicle speed; The baseline of the binocular camera is adjusted according to the target baseline length.

3. The method according to claim 2, characterized in that, Determining the target baseline length based on the road type and the target vehicle speed includes: When the road type is a straight road segment or a near-straight road segment, the target baseline length is determined based on the target vehicle speed, according to the strategy corresponding to the speed range of the target vehicle speed. In the case where the road type is a curved section, the curve radius is obtained, and the target baseline length is determined based on the curve radius and the target vehicle speed.

4. The method according to claim 3, characterized in that, According to the strategy corresponding to the speed range of the target vehicle speed, the target baseline length is determined based on the target vehicle speed, including: When the target vehicle speed falls within a first vehicle speed range, the target baseline length is determined based on the target vehicle speed and the system response time. When the target vehicle speed falls within the second vehicle speed range, the target baseline length is determined based on the target vehicle speed and the empirical coefficient corresponding to the target vehicle speed. When the target vehicle speed falls within the third vehicle speed range, the target baseline length is determined based on the target vehicle speed and the maximum braking deceleration. Wherein, the vehicle speed in the first speed range is less than the vehicle speed in the second speed range, and the vehicle speed in the second speed range is less than the vehicle speed in the third speed range.

5. The method according to claim 3, characterized in that, Determining the target baseline length based on the curve radius and the target vehicle speed includes: The maximum baseline length is determined based on the target vehicle speed and the maximum braking deceleration. Determine the radius difference between the curve radius and the preset radius; The target baseline length is determined based on the maximum baseline length and the radius difference.

6. The method according to any one of claims 1-5, characterized in that, To obtain the target vehicle speed, including: Obtain vehicle-related parameters and perform trajectory prediction based on the vehicle-related parameters; wherein, the vehicle-related parameters include the vehicle's yaw rate; The target vehicle speed is determined based on the trajectory prediction results.

7. The method according to any one of claims 1-5, characterized in that, Based on the image data, road surface pre-aiming information is generated, including: The image data is calibrated; Feature extraction is performed on the calibrated image data to obtain feature information, and the feature information is analyzed to obtain image analysis results; wherein, the feature information includes depth information; Based on the image analysis results and vehicle-related parameters, road surface preview information is generated.

8. The method according to claim 7, characterized in that, The image data includes first image data and second image data acquired by the binocular camera. Feature extraction is performed on the image data to obtain feature information, including: Determine the Hamming distance between two pixels of the same object in the first image data and the second image data, and determine the matching cost based on the Hamming distance; For each pixel, multiple paths are determined, and the path cost of the multiple paths is determined by combining the matching cost and the smoothness between pixels in each path. From the path costs of the multiple paths, determine the path cost with the minimum, and determine the disparity between the first image data and the second image data based on the path cost with the minimum. Depth information is determined based on the baseline length after baseline adjustment, the parallax, and the camera focal length.

9. The method according to any one of claims 1-5, characterized in that, Based on the road surface pre-aiming information, the vehicle suspension is pre-aimed, including: The vehicle's speed-related parameters are acquired, and the height and / or stiffness of the vehicle's suspension are pre-aimed based on the road surface pre-aiming information and the speed-related parameters.

10. A device for vehicle suspension anti-aiming control, characterized in that, The vehicle is equipped with a binocular camera, which is integrated into the vehicle's headlights. The device includes: A baseline adjustment module is used to acquire a target vehicle speed and adjust the baseline of the binocular camera based on the target vehicle speed; wherein the target vehicle speed is a predicted vehicle speed or the real-time vehicle speed of the vehicle. The image data acquisition module is used to acquire image data captured by the baseline-adjusted binocular camera; The road surface preview information generation module is used to generate road surface preview information based on the image data; The aiming control module is used to perform aiming control on the vehicle suspension based on the road surface aiming information.

Images