Intelligent vehicle lamp dynamic control system and method based on support vector regression

Abstract

The application provides a kind of intelligent car light dynamic control system and method based on support vector regression, belongs to the technical field of intelligent control of car light.The intelligent car light dynamic control system includes: data acquisition module is used to obtain the dynamic data of vehicle in real time;Data processing module is used to generate feature data by data processing the dynamic data of vehicle;SVR module is used to generate driving path prediction data and vehicle state prediction data within future seconds based on feature data;Car light dynamic control module is used to generate car light control instruction corresponding to driving path prediction data and feature data;Motor module is used to drive car light system to execute corresponding operation based on the beam angle control instruction of car light;Car light projection subsystem is used to project the received image data to the front road surface.By combining the prediction ability of support vector regression model, dynamically adjusting the illumination area and brightness of car light, the safety and driving comfort of night driving are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent vehicle lighting control technology, specifically to an intelligent vehicle lighting dynamic control system and method based on support vector regression. Background Technology

[0002] With the development of vehicle automation and intelligence, intelligent lighting systems have gradually become one of the key technologies in the automotive industry. Traditional lighting systems are controlled by simple switching or adjusting light intensity, which cannot adapt to real-time changes in complex road conditions, especially at night or in inclement weather. To improve driving safety and experience, some existing technologies have begun to introduce dynamic lighting control systems. Existing systems typically detect the vehicle's driving status through sensors and adjust the beam direction or brightness of the headlights according to fixed preset rules. However, these systems lack flexibility in complex road environments and struggle to provide precise lighting control based on real-time changes in the driving environment.

[0003] Most current automotive lighting control systems rely primarily on simple sensor inputs and adjust the beam based on a preset set of rules. However, these systems have several shortcomings:

[0004] 1. Due to the limitations of fixed rules, the dynamic response speed and adaptability of vehicle lights are insufficient, making it difficult to cope with complex driving environments;

[0005] 2. Existing technologies fail to incorporate vehicle path prediction data to optimize beam adjustment, resulting in a gap between the headlight illumination effect and actual driving needs;

[0006] 3. Lacking a real-time closed-loop feedback mechanism, the headlights cannot be dynamically adjusted based on the actual illumination effect.

[0007] The above-mentioned problems urgently need to be solved. Summary of the Invention

[0008] The purpose of this invention is to overcome at least one technical problem existing in the prior art and to provide an intelligent vehicle lighting dynamic control system and method based on support vector regression.

[0009] On one hand, this invention provides an intelligent vehicle lighting dynamic control system based on support vector regression. The intelligent vehicle lighting dynamic control system includes: a data acquisition module, a data processing module, an SVR module, a vehicle lighting dynamic control module, a motor module, and a vehicle lighting projection subsystem. The output of the data acquisition module is electrically connected to the input of the data processing module. The first output of the data processing module is electrically connected to the input of the SVR module. The second output of the data processing module is electrically connected to the first input of the vehicle lighting dynamic control module. The first output of the SVR module is electrically connected to the second input of the vehicle lighting dynamic control module. The output of the vehicle lighting dynamic control module is electrically connected to the inputs of the motor module and the vehicle lighting projection subsystem, respectively. The motor module and the vehicle lighting projection subsystem are externally connected to the vehicle lighting system. The data acquisition module is used to acquire vehicle dynamic data in real time based on onboard sensors. The data processing module is used to process the vehicle dynamic data using a Kalman filter algorithm to generate feature data. The SVR module integrates a model creation module, a model optimization module, and a model training module. The system includes a prediction result generation module; a model creation module for creating a basic SVR model by introducing a Gaussian kernel function; a model optimization module for optimizing the kernel parameters and regularization coefficients in the basic SVR model based on the Osprey optimization algorithm; a model training module for training the optimized basic SVR model based on a pre-stored training set; a prediction result generation module for inputting the feature data into the trained SVR model to generate vehicle driving path prediction data and vehicle state prediction data for the next few seconds; a headlight dynamic control module for generating corresponding headlight control commands based on the driving path prediction data and the feature data, the headlight control commands including one or a combination of headlight beam angle control commands, headlight brightness control commands, and headlight projection spot shape control commands; a motor module for driving the headlight system to perform corresponding operations based on the headlight beam angle control commands; and a headlight projection subsystem for controlling the brightness of the headlight system and the image data to be projected based on the headlight brightness control commands and headlight projection spot shape control commands.

[0010] Furthermore, the intelligent vehicle lighting dynamic control system also includes a real-time monitoring and feedback module. The output of the real-time monitoring and feedback module is electrically connected to the third input of the vehicle lighting dynamic control module, the second output of the SVR module is electrically connected to the first input of the real-time monitoring and feedback module, and the third output of the data processing module is electrically connected to the second input of the real-time monitoring and feedback module. The real-time monitoring and feedback module is used to monitor the illumination effect of the vehicle lights in real time through the vehicle-mounted camera, and compare it with the vehicle's driving path prediction data and vehicle status data generated by the SVR module for the next few seconds, as well as the road information ahead of the vehicle sent by the data processing module. Based on the comparison result, it sends control commands to the vehicle lighting dynamic control module, so that the vehicle lighting dynamic control module adaptively adjusts the control rules for generating vehicle lighting control commands based on the control commands. The illumination effect includes one or a combination of the light intensity, illumination angle, and light spot shape of the vehicle lighting illumination area.

[0011] Furthermore, the data acquisition module integrates vehicle sensors, vehicle cameras, and / or lidar to collect in real time one or a combination of the following: vehicle speed, acceleration, steering wheel angle, gyroscope data, road curvature, GPS information, ambient light intensity, speed limit warning, and distance between the vehicle and obstacles in front of the vehicle.

[0012] Furthermore, the data processing module is used to clean, filter, denoise, and normalize the dynamic data of the vehicle based on a Kalman filter to generate feature data.

[0013] The Kalman filtering algorithm is integrated into the Kalman filter, and its state equation is:

[0014] x k =Ax k-1 +Bu k-1 +ω k-1 ;

[0015] Where, x k This represents the state of the system at time k, where A represents the state transition matrix, B represents the control matrix, and u... k-1 To control the input, ω k-1 This is process noise;

[0016] The observation process of the system is described as follows:

[0017] z k =Hx k +v k ;

[0018] Among them, z k These are the observed values, H is the observation matrix, which describes the relationship between the state and the measured values, and v k For measuring noise;

[0019] The Kalman filter performs real-time noise reduction on vehicle dynamic data by combining prediction models and observations.

[0020] Furthermore, the objective function of the basic SVR model is:

[0021] f(x)=ω T Φ(x)+b;

[0022] Where ω is the weight vector, Φ(x) is the feature mapping of the input data x, which maps low-dimensional data to high-dimensional space through the kernel function, and b is the bias term;

[0023] The Gaussian kernel function is:

[0024]

[0025] Where, x i Let x be any point in space. j Let σ be the center of the kernel function, and σ be the width parameter of the kernel function. i -x j ||For x i To x j The Euclidean distance between them.

[0026] Furthermore, the model optimization module is used to: set the root mean square error of the historical data input into the SVR model as the fitness function of the Osprey optimization algorithm; the Osprey optimization algorithm optimizes the regularization coefficient and kernel parameter in the basic SVR model by minimizing the root mean square error corresponding to the fitness function, thereby completing the process of optimizing the kernel parameter and regularization coefficient in the basic SVR model, including: setting the initial parameters in the Osprey optimization algorithm, iterating sequentially, and reaching the maximum number of iterations or the Osprey optimization algorithm tending to stabilize, indicating that the optimal value has been found.

[0027] Furthermore, the root mean square error function corresponding to the fitness function is:

[0028]

[0029] Where m is the number of samples, F i_predict It is the predicted value, F i_actual This is the actual value.

[0030] Furthermore, the driving path prediction data and vehicle status prediction data include one or a combination of the following in the next few seconds: predicted vehicle speed, predicted acceleration, predicted steering wheel angle, predicted gyroscope data, predicted road curvature, predicted GPS information, predicted ambient light intensity, and predicted distance between the vehicle and obstacles in front of the vehicle.

[0031] Furthermore, the vehicle headlight dynamic control module integrates a beam direction adjustment submodule, a beam brightness adjustment submodule, and a beam shape adjustment submodule. The beam direction adjustment submodule generates control commands to dynamically adjust the headlight beam direction based on the vehicle's current driving direction in the feature data and the predicted steering wheel angle in the driving path prediction data. The beam brightness adjustment submodule generates control commands to dynamically adjust the beam brightness based on the vehicle's predicted speed and the predicted distance between the vehicle and obstacles in front of the vehicle in the vehicle state prediction data. The beam shape adjustment submodule generates control commands to dynamically adjust the image data to be projected based on the road information ahead of the vehicle sent by the data processing module.

[0032] Secondly, embodiments of the present invention provide a method for intelligent vehicle lighting dynamic control based on support vector regression. This method is applied to the aforementioned intelligent vehicle lighting dynamic control system based on support vector regression. The method includes: system initialization; real-time acquisition of vehicle dynamic data by the data acquisition module based on onboard sensors; data processing by the data processing module using a Kalman filter algorithm to process the vehicle dynamic data and generate feature data; the SVR module creating a basic SVR model by introducing a Gaussian kernel function; optimizing the kernel parameters and regularization coefficients in the basic SVR model using an Osprey optimization algorithm; training the optimized basic SVR model based on a pre-stored training set; and inputting the feature data into the trained SVR model to generate vehicle path prediction data and vehicle state prediction data for the next few seconds. The vehicle headlight dynamic control module generates corresponding headlight control commands based on the driving path prediction data and the feature data; the motor module drives the headlight system to perform corresponding operations based on the headlight beam angle control commands; the headlight projection subsystem controls the brightness of the headlight system and the image data to be projected based on the headlight brightness control commands and the headlight projection spot shape control commands; the real-time monitoring feedback module monitors the headlight illumination effect in real time through the vehicle-mounted camera, and compares it with the vehicle driving path prediction data and vehicle status data for the next few seconds generated by the SVR module and the road information ahead of the vehicle sent by the data processing module. Based on the comparison result, it sends control commands to the headlight dynamic control module, so that the headlight dynamic control module adaptively adjusts the control rules for generating headlight control commands based on the control commands.

[0033] Thirdly, embodiments of the present invention also provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the above-described intelligent vehicle lighting dynamic control method based on support vector regression.

[0034] Fourthly, embodiments of the present invention also provide a readable storage medium, which, when the instructions in the storage medium are executed by the processor of an electronic device, enables the electronic device to execute the above-described intelligent vehicle lighting dynamic control method based on support vector regression.

[0035] The beneficial effects of this invention are as follows: This invention provides an intelligent vehicle lighting dynamic control system and method based on Support Vector Regression (SVR). By embedding a Kalman filter algorithm in the data processing module, it can effectively extract data from the data acquisition module for real-time noise reduction, providing more accurate state estimates. Simultaneously, by utilizing a swarm intelligence optimization algorithm (Osprey optimization algorithm) to optimize the hyperparameters of the SVR, it can effectively improve the robustness and generalization of the SVR model, thereby further improving the predictive performance of the SVR. After embedding the prediction algorithm into the intelligent vehicle lighting dynamic control system, the system's intelligence is enhanced, thereby improving the safety and comfort of nighttime driving. This invention's system and method can be widely applied in the fields of intelligent assisted driving and autonomous driving, and also provides a new solution for vehicle lighting controller algorithms. Attached Figure Description

[0036] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0037] Figure 1 This is a schematic diagram of a smart vehicle lighting dynamic control system based on support vector regression provided in Embodiment 1 of the present invention.

[0038] Figure 2 This is a schematic diagram of another intelligent vehicle lighting dynamic control system based on support vector regression provided in Embodiment 1 of the present invention.

[0039] Figure 3 This is a flowchart of a smart vehicle lighting dynamic control method based on support vector regression provided in Embodiment 2 of the present invention.

[0040] Figure 4 This is a partial block diagram of the electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0041] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the figures. The process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0042] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0043] The present invention will now be described in detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0044] For ease of understanding, the following technical terms are explained:

[0045] Kalman filtering is a recursive estimation algorithm widely used for prediction, smoothing, and denoising of time series data. It is primarily used for linear systems and performs real-time correction based on the noise characteristics of sensor data, given a known system model. Kalman filtering can infer a more accurate state from noisy observation data based on historical information and physical models. It predicts the state at the next time step based on the system's dynamic model and then corrects it using actual measurement data. Its core idea is to provide the optimal estimate based on Bayesian estimation, combined with previous predictions and current observations.

[0046] SVR (Support Vector Regression) is a machine learning algorithm used to solve regression problems, that is, to predict the values ​​of continuous variables. Its principle is similar to Support Vector Machine (SVM), but the goal is different. SVR aims to build a predictive model that minimizes the error between the predicted and actual values.

[0047] Osprey Optimization Algorithm (OOA) is an optimization algorithm based on osprey behavior, proposed in 2023. This algorithm finds the best candidate by simulating the hunting behavior of ospreys and features strong optimization ability and fast convergence speed.

[0048] Example 1

[0049] For ease of understanding, the inventive concept will be described in its entirety before a detailed description of the embodiments of the present invention:

[0050] This application provides an intelligent vehicle lighting dynamic control system and method based on Support Vector Regression (SVR) to improve driving safety and experience, and to achieve intelligent vehicle lighting control and adaptive adjustment. It mainly consists of seven parts: a data acquisition module, a data processing module, an SVR module, an intelligent vehicle lighting dynamic control module, a motor module, a vehicle lighting projection subsystem, and a real-time feedback module. The data acquisition module collects vehicle driving status data. The data processing module performs noise smoothing and data normalization on the collected raw data. The SVR module constructs and trains an SVR model based on the processed feature data, establishing a nonlinear relationship between the input data and the future vehicle driving path and lighting requirements, outputting the vehicle's driving trajectory for the next few seconds. The intelligent vehicle lighting dynamic control module automatically adjusts the illumination direction, illumination angle, brightness, and light spot shape of the vehicle lights according to the output of the SVR model. The motor module receives control commands from the intelligent vehicle lighting dynamic control module and drives the vehicle lights to perform corresponding adjustment operations. The vehicle lighting projection system is mainly responsible for projecting image data onto the road ahead. The real-time feedback module monitors the illumination effect of the vehicle lights and environmental changes in real time, and feeds this information back to the system for further optimization and adjustment. The intelligent vehicle light dynamic control system of this application intelligently processes vehicle and environmental data, combining the predictive capabilities of a support vector regression model to dynamically adjust the illumination area and brightness of the vehicle lights, thereby improving nighttime driving safety and comfort.

[0051] The specific implementation method is as follows:

[0052] like Figure 1 The diagram shown is a schematic of the structure of an intelligent vehicle lighting dynamic control system based on support vector regression provided by the present invention.

[0053] As an example, the intelligent vehicle lighting dynamic control system includes: a data acquisition module 1, a data processing module 2, an SVR module 3, a vehicle lighting dynamic control module 4, a motor module 5, and a vehicle lighting projection subsystem 6. The output terminal of the data acquisition module 1 is electrically connected to the input terminal of the data processing module 2. The first output terminal of the data processing module 2 is electrically connected to the input terminal of the SVR module 3. The second output terminal of the data processing module 2 is electrically connected to the first input terminal of the vehicle lighting dynamic control module 4. The first output terminal of the SVR module 3 is electrically connected to the second input terminal of the vehicle lighting dynamic control module 4. The output terminal of the vehicle lighting dynamic control module 4 is electrically connected to the input terminals of the motor module 5 and the vehicle lighting projection subsystem 6, respectively. The motor module 5 and the vehicle lighting projection subsystem 6 are externally connected to the vehicle lighting system.

[0054] In some feasible implementations, the data acquisition module 1 is used to acquire dynamic vehicle data in real time based on onboard sensors. The data acquisition module 1 integrates onboard sensors, onboard cameras, and / or lidar to acquire, in real time, one or a combination of vehicle speed, acceleration, steering wheel angle, gyroscope data, road curvature, GPS information, ambient light intensity, speed limit warnings, and the distance to obstacles in front of the vehicle. Specifically, the data acquisition module 1 uses onboard sensors, such as speed sensors, steering angle sensors, and acceleration sensors, to acquire dynamic vehicle data in real time, including but not limited to vehicle speed, steering angle, acceleration, and braking status. This data reflects the vehicle's current motion state and driving behavior. Simultaneously, it integrates photosensitive sensors, onboard cameras, lidar, etc., to detect surrounding environmental conditions in real time, including but not limited to light intensity, speed limit warnings, and the distance to obstacles in front of the vehicle. This data affects the vehicle's vision and road condition perception while driving. The data acquisition module 1 packages this information and sends it to the data processing module 2.

[0055] In some feasible implementations, the data processing module 2 is used to process the vehicle's dynamic data using a Kalman filter algorithm to generate feature data. Preferably, the data processing module 2 is used to clean, filter, denoise, and normalize the vehicle's dynamic data using a Kalman filter algorithm to generate feature data; the Kalman filter algorithm is integrated into the Kalman filter, and its state equation is:

[0056] x k =Ax k-1 +Bu k-1 +ω k-1 ;

[0057] Where, x k This represents the state of the system at time k, where A represents the state transition matrix, B represents the control matrix, and u... k-1 To control the input, ω k-1 This is process noise;

[0058] The observation process of the system is described as follows:

[0059] z k =Hx k +v k ;

[0060] Among them, z k These are the observed values, H is the observation matrix, which describes the relationship between the state and the measured values, and v k To measure noise, the Kalman filter combines the prediction model and observations to denoise the vehicle's dynamic data in real time, providing a more accurate state estimate.

[0061] Data processing module 2 performs preliminary cleaning and noise reduction on the raw data acquired from the sensor, removing outliers and unreliable data to ensure the quality of data in subsequent processing. This reduces the complexity of the SVR model and improves its prediction accuracy, ensuring that the data input into the SVR model is more accurate, which is the basis for the SVR model to make efficient predictions.

[0062] In some feasible implementations, combined with Figure 2 As shown, the SVR module 3 integrates a model creation module 310, a model optimization module 320, a model training module 330, and a prediction result generation module 340. The model creation module 310 is used to create a basic SVR model by introducing a Gaussian kernel function. The model optimization module 320 is used to optimize the kernel parameters and regularization coefficients in the basic SVR model based on the Osprey optimization algorithm. The model training module 330 is used to train the optimized basic SVR model based on a pre-stored training set. The prediction result generation module 340 is used to input the feature data into the trained SVR model to generate vehicle driving path prediction data and vehicle state prediction data for the next few seconds.

[0063] Preferably, the objective function of the basic SVR model is:

[0064] f(x)=ω T Φ(x)+b;

[0065] Where ω is the weight vector, Φ(x) is the feature mapping of the input data x, which maps low-dimensional data to high-dimensional space through the kernel function, and b is the bias term;

[0066] The Gaussian kernel function is:

[0067]

[0068] Where, x i Let x be any point in space. j Let σ be the center of the kernel function, and σ be the width parameter of the kernel function. i -x j ||For x i To x j The Euclidean distance between them.

[0069] Specifically, the core idea of ​​SVR is to perform regression using a hyperplane that fits the data as closely as possible while allowing for error within a certain tolerance range. This tolerance range is controlled by a parameter ε, called the epsilon-insensitive tube.

[0070] The goal of SVR is to minimize the weights ω while keeping the error within acceptable limits, thus smoothing the function and avoiding overfitting. To achieve this, SVR optimizes the following formula:

[0071]

[0072] Where C is the regularization coefficient, ξ i and It is a slack variable, representing the error of the predicted value exceeding the ε range.

[0073] After introducing kernel functions, SVR can handle nonlinear regression problems. In this embodiment, Gaussian kernel functions are preferred.

[0074] In some feasible implementations, the model optimization module 320 is used to: set the root mean square error of the historical data input into the SVR model as the fitness function of the Osprey optimization algorithm; the Osprey optimization algorithm optimizes the regularization coefficient and kernel parameter in the basic SVR model by minimizing the root mean square error corresponding to the fitness function, thereby completing the optimization process of the kernel parameter and regularization coefficient in the basic SVR model, including: setting the initial parameters in the Osprey optimization algorithm, iterating sequentially, and reaching the maximum number of iterations or the Osprey optimization algorithm tending to stabilize, indicating that the optimal value has been found. The root mean square error function corresponding to the fitness function is:

[0075]

[0076] Where m is the number of samples, F i_predict It is the predicted value, F i_actual This is the actual value.

[0077] Specifically, emerging intelligent optimization algorithms have proven in recent years to possess the ability to coordinate global exploration and local development, thus exhibiting good performance in handling some engineering optimization problems. This embodiment will use OOA to optimize the kernel parameters and regularization coefficients of SVR.

[0078] The process of changing the location of a population in OOA consists of two stages: the first stage is when the ospreys identify the location of the fish and catch them (global exploration), and the second stage is when the fish are moved to a suitable location (local mining).

[0079] In the first phase, the osprey detects the location of underwater fish. Once the fish's location is determined, it attacks and preys on it underwater. The first phase is modeled based on a simulation of this natural behavior of the osprey. For each osprey, the locations of other ospreys in the search space with better objective function values ​​are considered as underwater fish. The fish group for each osprey is represented by the following formula:

[0080] FP i ={Xk |k∈{1,2,...,N}∧F k <F i}∪{X best};

[0081] Among them, FP i F is the set of fish belonging to the i-th osprey. k and F i These represent the fitness values ​​corresponding to the positions of the k-th and i-th ospreys, respectively, where N is the population size and X is the number of ospreys. best That is the best position for the osprey.

[0082] The first-stage update formula is as follows:

[0083]

[0084] Where, x i,j This represents the location information of the osprey. Let r be the new position of the i-th osprey in the j-th dimension during the first stage. i,j It is a random number between [0,1], SF i It is the target chosen by the i-th Osprey, SF i,j It is its corresponding dimension, I i,j is a random number in the set {1,2}.

[0085]

[0086] Among them, lb j It is the lower boundary corresponding to the j-th dimension, ub j It is the upper boundary corresponding to the j-th dimension.

[0087] In the second phase, after catching a fish, the osprey carries it to a relatively safe location to eat. The second phase of population renewal in OOA is modeled based on a simulation of this natural behavior of the osprey. Modeling the act of carrying the fish to a suitable location causes a slight change in the osprey's position in the search space, which increases the effectiveness of OOA in local searches.

[0088] The second-stage update formula is as follows:

[0089]

[0090] in, For the i-th osprey, in the second stage, its new position in the j-th dimension is... It is its corresponding fitness value, r is a random number between [0,1], and t and T are the current iteration number and the maximum iteration number, respectively.

[0091] The root mean square error of the historical data input to SVR is set as the fitness function of OOA. OOA optimizes the regularization coefficient and kernel parameters of SVR by minimizing the root mean square error. Initial parameters in OOA are set and iterated sequentially. Reaching the maximum number of iterations or the algorithm stabilizing indicates that the optimal value has been found.

[0092] The formula for the root mean square error function corresponding to the fitness function is as follows:

[0093]

[0094] Where m is the number of samples, F i_predict It is the predicted value, F i_actual This is the actual value.

[0095] Out-of-Arrangement (OOA) can effectively improve the prediction accuracy of the SVR model, optimizing its performance. After acquiring real-time sensor data from the data processing module, the SVR predicts the vehicle's driving path and state data for the next few seconds based on this data. In other words, the SVR module generates corresponding prediction data based on the input vehicle dynamic data. The driving path prediction data and vehicle state prediction data include one or a combination of the following for the next few seconds: predicted vehicle speed, predicted acceleration, predicted steering wheel angle, predicted gyroscope data, predicted road curvature, predicted GPS information, predicted ambient light intensity, and predicted distance between the vehicle and obstacles in front of it.

[0096] In some feasible implementations, the vehicle headlight dynamic control module 4 is used to generate corresponding vehicle headlight control commands based on the driving path prediction data and the feature data. The vehicle headlight control commands include one or a combination of vehicle headlight beam angle control commands, vehicle headlight brightness control commands, and vehicle headlight projection spot shape control commands. Preferably, combined with... Figure 2As shown, the vehicle headlight dynamic control module 4 integrates a beam direction adjustment submodule 410, a beam brightness adjustment submodule 420, and a spot shape adjustment submodule 430. The beam direction adjustment submodule 410 generates control commands to dynamically adjust the headlight beam direction based on the vehicle's current driving direction in the feature data and the predicted steering wheel angle in the driving path prediction data. The beam brightness adjustment submodule 420 generates control commands to dynamically adjust the beam brightness based on the vehicle's predicted speed and the predicted distance between the vehicle and obstacles in front of the vehicle in the vehicle state prediction data. The spot shape adjustment submodule 430 generates control commands to dynamically adjust the projected image data based on the road information ahead of the vehicle sent by the data processing module. Specifically, the beam direction adjustment submodule 410 generates control commands based on the vehicle's current driving direction and estimated steering angle, transmitting them to the motor module 5 to dynamically adjust the headlight beam direction. The beam automatically shifts with the vehicle's driving direction, ensuring that the beam illuminates the road area being traveled when turning or changing lanes. The beam brightness adjustment submodule 420 dynamically adjusts the beam brightness based on the predicted vehicle speed and the distance to obstacles ahead. When the vehicle is traveling at a higher speed, the beam's illumination distance will increase. The added real-time prediction mechanism ensures that the driver has sufficient reaction time. The spot shape adjustment submodule 430 dynamically adjusts the image data to be projected based on the road information collected by the camera and transmits it to the vehicle headlight projection subsystem 6 for projection.

[0097] In some feasible implementations, the intelligent vehicle lighting dynamic control system further includes a real-time monitoring feedback module 7. The output of the real-time monitoring feedback module 7 is electrically connected to the third input of the vehicle lighting dynamic control module 4, the second output of the SVR module 3 is electrically connected to the first input of the real-time monitoring feedback module 7, and the third output of the data processing module 2 is electrically connected to the second input of the real-time monitoring feedback module 7. The real-time monitoring feedback module 7 is used to monitor the illumination effect of the vehicle lights in real time through the vehicle-mounted camera, and compare it with the vehicle's driving path prediction data and vehicle status data generated by the SVR module 3 for the next few seconds, as well as the road information ahead of the vehicle sent by the data processing module 2. Based on the comparison result, it sends a control command to the vehicle lighting dynamic control module 4, so that the vehicle lighting dynamic control module 4 adaptively adjusts the control rules for generating vehicle lighting control commands based on the control command. The illumination effect includes one or a combination of the light intensity, illumination angle, and light spot shape of the vehicle lighting illumination area. Specifically, the real-time monitoring feedback module 7 monitors the illumination of the vehicle lights in real time through the vehicle-mounted camera. The specific operation steps are as follows: Illumination range monitoring: The camera detects the actual illumination area and brightness value of the vehicle lights and compares this data with the target value output by the SVR module 3. Error calculation and adjustment: When a large deviation is detected between the actual illumination effect and the target value, the real-time monitoring feedback module 7 sends a corresponding control signal to the vehicle light dynamic control module 4 based on the error value. This allows the module to dynamically adjust the control rules based on the control signal, thereby adjusting the beam direction and brightness in real time. For example, when the error value is within the first error range, a first control signal is sent to the vehicle light dynamic control module 4, and the module adjusts the beam direction and brightness control rules slightly based on the first control signal. When the error value is within the second error range, a second control signal is sent to the vehicle light dynamic control module 4, and the module adjusts the beam direction and brightness control rules significantly based on the second control signal. It should be noted that the adjustment method of this control rule can be modified and set independently by relevant technical personnel based on actual needs. In other words, the real-time monitoring and feedback module 7 can establish a real-time data monitoring mechanism. This module monitors the actual lighting effect of the vehicle lights in real time using the onboard camera, and feeds back information such as the light intensity, angle, and shape of the illuminated area to the vehicle light dynamic control module. Simultaneously, it compares the real-time data with the prediction results of the SVR model to detect model anomalies or failures. Based on the comparison results, it dynamically adjusts and optimizes the vehicle lights to maintain optimal adaptability and performance, ultimately achieving closed-loop control.

[0098] In some feasible implementations, the motor module 5 is used to drive the headlight system to perform corresponding operations based on the beam angle control command of the headlight. The headlight projection subsystem 6 is used to control the brightness of the headlight system and the image data to be projected based on the headlight brightness control command and the headlight projection spot shape control command. Specifically, the motor module 5 is mainly responsible for adjusting the headlight angle, while the headlight projection subsystem 6 is responsible for projecting the image onto the road ahead.

[0099] The above embodiments, by embedding the Kalman filter algorithm in the data processing module, can effectively extract data from the data acquisition module for real-time noise reduction, providing a more accurate state estimate. Simultaneously, utilizing a swarm intelligence optimization algorithm (Osprey optimization algorithm) to optimize the hyperparameters of the SVR can effectively improve the robustness and generalization of the SVR model, thereby further enhancing the predictive performance of the SVR. After embedding the prediction algorithm into the intelligent vehicle lighting dynamic control system, the system's intelligence is enhanced, thereby improving the safety and comfort of nighttime driving. The system and method of this invention can be widely applied in the fields of intelligent assisted driving and autonomous driving, and also provide a new solution for vehicle lighting controller algorithms.

[0100] It is worth mentioning that all modules involved in this embodiment are logical units. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by this invention; however, this does not mean that other units are absent from this embodiment.

[0101] Example 2

[0102] Please see Figure 3 This embodiment provides a flowchart of a smart vehicle lighting dynamic control method based on support vector regression.

[0103] As an example, the method is applied to the intelligent vehicle lighting dynamic control system based on support vector regression described in Embodiment 1, and the method includes:

[0104] S310: System initialization.

[0105] S320: The data acquisition module acquires the vehicle's dynamic data in real time based on the on-board sensors.

[0106] S330: The data processing module uses the Kalman filter algorithm to process the dynamic data of the vehicle and generate feature data.

[0107] S340: The SVR module creates a basic SVR model by introducing a Gaussian kernel function.

[0108] S350: Optimize the kernel parameters and regularization coefficients in the basic SVR model based on the Osprey optimization algorithm.

[0109] S360: Trains the optimized base SVR model based on a pre-stored training set.

[0110] S370: Input the feature data into the trained SVR model to generate vehicle driving path prediction data and vehicle state prediction data for the next few seconds.

[0111] S380: The vehicle lighting dynamic control module generates corresponding vehicle lighting control commands based on the driving path prediction data and the feature data.

[0112] S390: The motor module drives the vehicle lighting system to perform corresponding operations based on the beam angle control command of the vehicle light.

[0113] S3100: The vehicle headlight projection subsystem controls the brightness of the vehicle headlight system and the image data to be projected based on the vehicle headlight brightness control command and the vehicle headlight projection spot shape control command.

[0114] S3110: The real-time monitoring feedback module monitors the illumination effect of the vehicle lights in real time through the vehicle-mounted camera, and compares it with the vehicle's driving path prediction data and vehicle status data generated by the SVR module for the next few seconds, as well as the road information ahead of the vehicle sent by the data processing module. Based on the comparison result, the module sends a control command to the vehicle light dynamic control module, so that the vehicle light dynamic control module adaptively adjusts the control rules for generating vehicle light control commands based on the control command.

[0115] It is not difficult to see that this embodiment is a method embodiment corresponding to the first embodiment, and this embodiment can be implemented in conjunction with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and will not be repeated here to reduce repetition. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the first embodiment.

[0116] Example 3

[0117] Please see Figure 4 The present invention also provides an electronic device, including: a memory and a processor; the memory stores at least one program instruction; the processor loads and executes the at least one program instruction to implement the intelligent vehicle lighting dynamic control method based on support vector regression provided in Embodiment 2.

[0118] The memory 702 and processor 701 are connected via a bus, which may include any number of interconnecting buses and bridges, connecting various circuits of one or more processors 701 and memory 702 together. The bus may also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by processor 701 is transmitted over a wireless medium via an antenna, which further receives data and transmits it to processor 701.

[0119] Processor 701 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory 702 can be used to store data used by processor 701 during operation.

[0120] Example 4

[0121] This invention also proposes a storage medium storing a dynamic control method for intelligent vehicle lights based on support vector regression. When the dynamic control program for intelligent vehicle lights based on support vector regression is executed, it implements the steps of the dynamic control method for intelligent vehicle lights based on support vector regression as described above. Since this storage medium adopts all the technical solutions of all the above embodiments, it possesses at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be elaborated further here.

[0122] The above descriptions are merely embodiments of the present invention. Commonly known structures and characteristics are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, based on the guidance provided in this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A smart vehicle lighting dynamic control system based on support vector regression, characterized in that, The intelligent vehicle lighting dynamic control system includes: a data acquisition module, a data processing module, an SVR module, a vehicle lighting dynamic control module, a motor module, and a vehicle lighting projection subsystem. The output terminal of the data acquisition module is electrically connected to the input terminal of the data processing module. The first output terminal of the data processing module is electrically connected to the input terminal of the SVR module. The second output terminal of the data processing module is electrically connected to the first input terminal of the vehicle lighting dynamic control module. The first output terminal of the SVR module is electrically connected to the second input terminal of the vehicle lighting dynamic control module. The output terminal of the vehicle lighting dynamic control module is electrically connected to the input terminals of the motor module and the vehicle lighting projection subsystem, respectively. The motor module and the vehicle lighting projection subsystem are externally connected to the vehicle lighting system. The data acquisition module is used to acquire real-time dynamic data of the vehicle based on onboard sensors; The data processing module is used to process the dynamic data of the vehicle based on the Kalman filter algorithm to generate feature data, including: cleaning, filtering, denoising and normalizing the dynamic data of the vehicle to generate feature data. The Kalman filtering algorithm is integrated into the Kalman filter, and its state equation is: ； in, Is the system in time The state at any given moment, Represents the state transition matrix. Represents the control matrix. To control the input, This is process noise; The observation process of the system is described as follows: ； in, These are observed values. It is an observation matrix that describes the relationship between the state and the measured values. For measuring noise; Kalman filters denoise vehicle dynamic data in real time by combining prediction models and observations. The SVR module integrates a model creation module, a model optimization module, a model training module, and a prediction result generation module. The model creation module is used to create a basic SVR model by introducing a Gaussian kernel function; The model optimization module is used to optimize the kernel parameters and regularization coefficients in the basic SVR model based on the Osprey optimization algorithm. The objective function of the basic SVR model is: ； in, It is a weight vector. Input data Feature mapping uses kernel functions to map low-dimensional data to a high-dimensional space. It is a bias term; The Gaussian kernel function is: ； in, For any point in space, As the center of the kernel function, The width parameter of the kernel function. for arrive The Euclidean distance between them; The model optimization module is used to: set the root mean square error of the historical data input into the SVR model as the fitness function of the Osprey optimization algorithm; the Osprey optimization algorithm optimizes the regularization coefficient and kernel parameters in the basic SVR model by minimizing the root mean square error corresponding to the fitness function, thereby completing the optimization process of the kernel parameters and regularization coefficients in the basic SVR model, including: setting the initial parameters in the Osprey optimization algorithm, iterating sequentially, and reaching the maximum number of iterations or the Osprey optimization algorithm tending to stabilize, indicating that the optimal value has been found; the root mean square error function corresponding to the fitness function is: ； Where m is the number of samples, It is a predicted value. This is the actual value; The model training module is used to train the optimized base SVR model based on a pre-stored training set; The prediction result generation module is used to input the feature data into the trained SVR model to generate vehicle driving path prediction data and vehicle status prediction data for the next few seconds. The vehicle headlight dynamic control module is used to generate corresponding vehicle headlight control commands based on the driving path prediction data and the feature data. The vehicle headlight control commands include one or a combination of vehicle headlight beam angle control commands, vehicle headlight brightness control commands, and vehicle headlight projection spot shape control commands. The motor module is used to drive the vehicle lighting system to perform corresponding operations based on the beam angle control command of the vehicle light; The vehicle headlight projection subsystem is used to control the brightness of the vehicle headlight system and the image data to be projected based on the vehicle headlight brightness control command and the vehicle headlight projection spot shape control command. The intelligent vehicle lighting dynamic control system further includes a real-time monitoring and feedback module. The output of the real-time monitoring and feedback module is electrically connected to the third input of the vehicle lighting dynamic control module. The second output of the SVR module is electrically connected to the first input of the real-time monitoring and feedback module. The third output of the data processing module is electrically connected to the second input of the real-time monitoring and feedback module. The real-time monitoring and feedback module is used to monitor the illumination effect of the vehicle lights in real time through the vehicle-mounted camera and compare it with the vehicle's driving path prediction data and vehicle status data generated by the SVR module for the next few seconds, as well as the road information ahead of the vehicle sent by the data processing module. Based on the comparison result, it sends control commands to the vehicle lighting dynamic control module, so that the vehicle lighting dynamic control module adaptively adjusts the control rules for generating vehicle lighting control commands based on the control commands. The illumination effect includes one or a combination of the light intensity, illumination angle, and light spot shape of the vehicle lighting illumination area.

2. The intelligent vehicle lighting dynamic control system based on support vector regression according to claim 1, characterized in that, The data acquisition module integrates vehicle sensors, vehicle cameras, and / or lidar to collect in real time one or a combination of the following: vehicle speed, acceleration, steering wheel angle, gyroscope data, road curvature, GPS information, ambient light intensity, speed limit warnings, and distance between the vehicle and obstacles in front of the vehicle.

3. The intelligent vehicle lighting dynamic control system based on support vector regression according to claim 1, characterized in that, The driving path prediction data and vehicle status prediction data include one or a combination of the following in the next few seconds: predicted vehicle speed, predicted acceleration, predicted steering wheel angle, predicted gyroscope data, predicted road curvature, predicted GPS information, predicted ambient light intensity, and predicted distance between the vehicle and obstacles in front of the vehicle.

4. The intelligent vehicle lighting dynamic control system based on support vector regression according to claim 3, characterized in that, The vehicle headlight dynamic control module integrates a beam direction adjustment submodule, a beam brightness adjustment submodule, and a spot shape adjustment submodule. The beam direction adjustment submodule is used to generate control commands to dynamically adjust the direction of the headlight beam based on the vehicle's current driving direction in the feature data and the steering wheel predicted angle in the driving path prediction data. The beam brightness adjustment submodule is used to generate control commands to dynamically adjust the beam brightness based on the predicted vehicle speed and the predicted distance between the vehicle and the obstacle in front of the vehicle in the vehicle state prediction data. The light spot shape adjustment submodule is used to generate control commands for dynamically adjusting the image data to be projected based on the road information ahead of the vehicle sent by the data processing module.

5. A method for dynamic control of intelligent vehicle lights based on support vector regression, characterized in that, The method is applied to the intelligent vehicle lighting dynamic control system based on support vector regression as described in any one of claims 1-4, and the method includes: System initialization; The data acquisition module acquires real-time dynamic data of the vehicle based on onboard sensors. The data processing module uses the Kalman filter algorithm to process the dynamic data of the vehicle and generate feature data. The SVR module creates a basic SVR model by introducing a Gaussian kernel function; The kernel parameters and regularization coefficients in the basic SVR model are optimized based on the Osprey optimization algorithm; The optimized base SVR model is trained based on a pre-stored training set; The feature data is input into the trained SVR model to generate vehicle driving path prediction data and vehicle state prediction data for the next few seconds. The vehicle lighting dynamic control module generates corresponding vehicle lighting control commands based on the driving path prediction data and the feature data. The motor module drives the vehicle lighting system to perform corresponding operations based on the beam angle control command of the vehicle light; The vehicle headlight projection subsystem controls the brightness of the vehicle headlight system and the image data to be projected based on the vehicle headlight brightness control command and the vehicle headlight projection spot shape control command. The real-time monitoring and feedback module monitors the illumination effect of the vehicle lights in real time through the vehicle-mounted camera, and compares it with the vehicle's driving path prediction data and vehicle status data generated by the SVR module for the next few seconds, as well as the road information ahead of the vehicle sent by the data processing module. Based on the comparison result, it sends control commands to the vehicle light dynamic control module, so that the vehicle light dynamic control module adaptively adjusts the control rules for generating vehicle light control commands based on the control commands.

Images