Vehicle lane centering control simulation test method, device and computer equipment

Abstract

The application relates to a simulation test method and device for vehicle lane centering control, a computer device, a storage medium and a computer program product. Vehicle state parameters of a controlled vehicle are obtained according to real vehicle test experiments, and vehicle position structure information of the controlled vehicle in a simulation lane is determined according to the vehicle state parameters of the controlled vehicle at a current time; two-side lane line information including two-side lane line fitting parameters is determined according to the vehicle position structure information; lane center line target fitting parameters are determined according to the two-side lane line fitting parameters; lane centering control is performed on the controlled vehicle based on the lane center line target fitting parameters, and a target error of the controlled vehicle after control deviating from the center line is calculated. According to the scheme, simulation tests are performed on the vehicle again after real vehicle test experiments, response errors of different steering systems between different vehicle individuals on the lane centering control software are avoided, and the test precision of the lane centering control software is improved.

Description

Technical Field

[0001] This application relates to the field of simulation testing technology, and in particular to a vehicle lane centering control simulation testing method, device, computer equipment, storage medium and computer program product. Background Technology

[0002] Lane centering control, as the lateral control component of a Level 2 autonomous driving system, can perceive and identify the lane lines of the current lane through a forward-facing camera and use control algorithms to correct the lateral error between the vehicle and the lane center line, ensuring that the vehicle travels along the lane center line. To improve the development and verification efficiency of the control algorithm, software simulation testing is required before real vehicle testing to ensure that the software can achieve the expected algorithm functions.

[0003] In related technologies, the testing of lane centering control software for L2-level intelligent driving systems involves first establishing a vehicle model based on historical experience for simulation testing, followed by real-vehicle testing. The results of these two tests determine the overall performance of the lane centering control software. However, due to differences in the types of steering system components and manufacturing and assembly processes among different vehicles, there are certain differences between the actual vehicles. The vehicle model established based on historical experience cannot reflect these differences, resulting in a significant error between the simulation test results and the real-vehicle test results. This affects the testing and debugging of the lane centering control software. Summary of the Invention

[0004] Therefore, it is necessary to provide an accurate and effective simulation test method, device, computer equipment, computer-readable storage medium, and computer program product for vehicle lane centering control to address the above-mentioned technical problems.

[0005] Firstly, this application provides a simulation testing method for vehicle lane centering control. The method includes:

[0006] Obtain the vehicle status parameters of the vehicle to be controlled at the current moment. Based on the vehicle status parameters of the vehicle to be controlled at the current moment, determine the vehicle orientation structure information of the vehicle to be controlled in the simulated lane. The initial values ​​of the vehicle status parameters are obtained based on the actual vehicle test of the vehicle to be controlled.

[0007] Based on the vehicle orientation structure information, determine the lane line information on both sides of the simulated lane. The lane line information on both sides includes the lane line fitting parameters on both sides.

[0008] Based on the lane line fitting parameters on both sides, determine the lane center line fitting parameters perceived by the vehicle to be controlled at the next moment. The reference points for determining the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are different, and the number of parameters of the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are the same.

[0009] Based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the current moment and the next moment, lane centering control is performed on the vehicle to be controlled, and the deviation error of the vehicle from the centerline target after control is calculated.

[0010] In one embodiment, the vehicle state parameters include steering wheel angle control parameters and lane centerline fitting parameters perceived by the vehicle under control; correspondingly, based on the vehicle state parameters of the vehicle under control at the current moment, the vehicle orientation structure information of the vehicle under control in the simulated lane is determined, including:

[0011] The current steering wheel angle control value and the lane centerline fitting parameters perceived by the vehicle under control are input into the vehicle simulation model of the vehicle under control to obtain the reference lane centerline fitting parameters.

[0012] Based on the vehicle state parameters at the current moment and the fitting parameters of the reference lane centerline, the vehicle orientation structure information of the vehicle to be controlled in the simulated lane is determined.

[0013] In one embodiment, the lane line information on both sides of the simulated lane is determined based on the vehicle orientation structure information, including:

[0014] Based on the vehicle's orientation and structural information, determine the lane information for the simulated lane;

[0015] Based on the lane information, the lane line information on both sides of the simulated lane is retrieved from the simulation model of the simulated lane.

[0016] In one embodiment, the reference point for determining the fitting parameters of the lane lines on both sides is a first reference point, and the reference point for determining the fitting parameters of the lane centerline perceived by the vehicle under control is a second reference point; accordingly, based on the fitting parameters of the lane lines on both sides, determining the fitting parameters of the lane centerline perceived by the vehicle under control at the next moment includes:

[0017] The orientation angle of the vehicle to be controlled in the simulated lane is determined based on the vehicle's orientation structure information.

[0018] Obtain the reference distance between the first reference point and the second reference point;

[0019] Based on the orientation angle, reference distance, and lane line fitting parameters on both sides, the transformation fitting parameters of the vehicle lines on both sides with the second reference point as the reference point are determined.

[0020] Based on the conversion fitting parameters of the lane lines on both sides, determine the lane centerline fitting parameters perceived by the vehicle to be controlled at the next moment in the current moment.

[0021] In one embodiment, the lane centerline fitting parameters perceived by the vehicle to be controlled at the current moment are determined based on the transition fitting parameters of the lane lines on both sides, including:

[0022] For any parameter of the lane centerline fitting parameters perceived by the vehicle under control, the average of the two parameters corresponding to the transformation fitting parameters of the lane lines on both sides is taken as the lane centerline fitting parameter of the vehicle under control at the next moment.

[0023] In one embodiment, the vehicle state parameters include steering wheel angle control parameters; correspondingly, based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the current moment and the next moment, lane centering control is performed on the vehicle to be controlled, and the deviation error of the controlled vehicle from the target centerline after control is calculated, including:

[0024] Based on the lane centerline fitting parameters perceived by the vehicle under control at the next moment from the current moment, calculate the initial error of the vehicle under control deviating from the centerline in the simulated lane.

[0025] Based on the initial error of deviation from the center line, determine the steering wheel angle control amount for the next moment at the current moment;

[0026] The steering wheel angle control value for the next moment is applied to the vehicle to be controlled, and the deviation error of the vehicle from the center line after application is obtained.

[0027] In one embodiment, the method further includes:

[0028] The lane centerline fitting parameters perceived by the vehicle under control at the current moment and the steering wheel angle control amount at the current moment and the next moment will be used as the vehicle state parameters of the vehicle under control at the current moment and the next moment.

[0029] Secondly, this application also provides a simulation testing device for vehicle lane centering control. The device includes:

[0030] Obtain the vehicle status parameters of the vehicle to be controlled at the current moment. Based on the vehicle status parameters of the vehicle to be controlled at the current moment, determine the vehicle orientation structure information of the vehicle to be controlled in the simulated lane. The initial values ​​of the vehicle status parameters are obtained based on the actual vehicle test of the vehicle to be controlled.

[0031] Based on the vehicle orientation structure information, determine the lane line information on both sides of the simulated lane. The lane line information on both sides includes the lane line fitting parameters on both sides.

[0032] Based on the lane line fitting parameters on both sides, determine the lane center line fitting parameters perceived by the vehicle to be controlled at the next moment. The reference points for determining the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are different, and the number of parameters of the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are the same.

[0033] Based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the current moment and the next moment, lane centering control is performed on the vehicle to be controlled, and the deviation error of the vehicle from the centerline target after control is calculated.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0035] Obtain the vehicle status parameters of the vehicle to be controlled at the current moment. Based on the vehicle status parameters of the vehicle to be controlled at the current moment, determine the vehicle orientation structure information of the vehicle to be controlled in the simulated lane. The initial values ​​of the vehicle status parameters are obtained based on the actual vehicle test of the vehicle to be controlled.

[0036] Based on the vehicle orientation structure information, determine the lane line information on both sides of the simulated lane. The lane line information on both sides includes the lane line fitting parameters on both sides.

[0037] Based on the lane line fitting parameters on both sides, determine the lane center line fitting parameters perceived by the vehicle to be controlled at the next moment. The reference points for determining the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are different, and the number of parameters of the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are the same.

[0038] Based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the current moment and the next moment, lane centering control is performed on the vehicle to be controlled, and the deviation error of the vehicle from the centerline target after control is calculated.

[0039] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0040] Obtain the vehicle status parameters of the vehicle to be controlled at the current moment. Based on the vehicle status parameters of the vehicle to be controlled at the current moment, determine the vehicle orientation structure information of the vehicle to be controlled in the simulated lane. The initial values ​​of the vehicle status parameters are obtained based on the actual vehicle test of the vehicle to be controlled.

[0041] Based on the vehicle orientation structure information, determine the lane line information on both sides of the simulated lane. The lane line information on both sides includes the lane line fitting parameters on both sides.

[0042] Based on the lane line fitting parameters on both sides, determine the lane center line fitting parameters perceived by the vehicle to be controlled at the next moment. The reference points for determining the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are different, and the number of parameters of the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are the same.

[0043] Based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the current moment and the next moment, lane centering control is performed on the vehicle to be controlled, and the deviation error of the vehicle from the centerline target after control is calculated.

[0044] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0045] Obtain the vehicle status parameters of the vehicle to be controlled at the current moment. Based on the vehicle status parameters of the vehicle to be controlled at the current moment, determine the vehicle orientation structure information of the vehicle to be controlled in the simulated lane. The initial values ​​of the vehicle status parameters are obtained based on the actual vehicle test of the vehicle to be controlled.

[0046] Based on the vehicle orientation structure information, determine the lane line information on both sides of the simulated lane. The lane line information on both sides includes the lane line fitting parameters on both sides.

[0047] Based on the lane line fitting parameters on both sides, determine the lane center line fitting parameters perceived by the vehicle to be controlled at the next moment. The reference points for determining the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are different, and the number of parameters of the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are the same.

[0048] Based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the current moment and the next moment, lane centering control is performed on the vehicle to be controlled, and the deviation error of the vehicle from the centerline target after control is calculated.

[0049] The aforementioned simulation test method, device, computer equipment, storage medium, and computer program product for vehicle lane centering control acquire the vehicle state parameters of the vehicle to be controlled at the current moment. Based on the vehicle state parameters, the vehicle's orientation structure information in the simulated lane is determined. The initial values ​​of the vehicle state parameters are obtained from actual vehicle testing. Based on the vehicle orientation structure information, the lane line information on both sides of the simulated lane is determined, including lane line fitting parameters. Based on the lane line fitting parameters, the lane centerline fitting parameters perceived by the vehicle at the next moment are determined. The reference points for determining the lane line fitting parameters and the lane centerline fitting parameters perceived by the vehicle are different, but the number of parameters is the same. Based on the lane centerline fitting parameters perceived by the vehicle at the next moment, lane centering control is performed on the vehicle, and the deviation error of the controlled vehicle from the target centerline after control is calculated. This solution improves the testing accuracy of the lane centering control software by conducting simulation tests on the vehicle after real-vehicle testing, thus avoiding response errors of different steering systems in different vehicles. Attached Figure Description

[0050] Figure 1 This is an application environment diagram of a simulation test method for vehicle lane centering control in one embodiment;

[0051] Figure 2 This is a flowchart illustrating a simulation test method for vehicle lane centering control in one embodiment.

[0052] Figure 3 This is a schematic diagram of lane line fitting parameters in one embodiment;

[0053] Figure 4 This is a flowchart illustrating a simulation test method for vehicle lane centering control in another embodiment;

[0054] Figure 5 This is a flowchart illustrating the simulation test method for vehicle lane centering control in yet another embodiment;

[0055] Figure 6 This is a structural block diagram of a simulation test device for vehicle lane centering control in one embodiment;

[0056] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0058] The simulation testing method for vehicle lane centering control provided in this application embodiment can be applied to, for example... Figure 1 The application environment is shown. Terminal 102 is a sensor capable of acquiring the vehicle's actual state parameters and operating environment parameters. Terminal 102 communicates with server 104 via a network, sending the collected data to server 104. Server 104 builds vehicle and environment models based on the data and performs simulation tests on the vehicle lane centering control software. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated on server 104 or placed on the cloud or other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0059] First, it should be noted that the simulation method provided in this application is a secondary simulation process for each individual vehicle based on real-vehicle data, which differs from the initial simulation in the development and production process, after actual vehicle measurement. In one embodiment, such as... Figure 2 As shown, a simulation test method for vehicle lane centering control is provided, and this method is applied to... Figure 1 Taking server 104 as an example, the following steps are included:

[0060] Step 202: Obtain the vehicle status parameters of the vehicle to be controlled at the current moment. Based on the vehicle status parameters of the vehicle to be controlled at the current moment, determine the vehicle orientation structure information of the vehicle to be controlled in the simulation lane. The initial values ​​of the vehicle status parameters are obtained based on the actual vehicle test of the vehicle to be controlled.

[0061] Vehicle status information includes various data describing the vehicle's operating status, specifications, and control parameters, such as vehicle weight, speed, steering wheel angle control, and initial position. Vehicle orientation structure information refers to the spatial position and status information of the vehicle's body structure in the world coordinate system, including lateral and longitudinal positions, yaw angle, speed, and heading angle. It should be noted that both vehicle status information and vehicle orientation structure information are in the world coordinate system, and the vehicle orientation structure information is obtained by connecting the controlled vehicle model with the environment model.

[0062] The vehicle's state information is perceived by multiple sensors on the vehicle under control, and then the vehicle's orientation and structure information is calculated using this state information. Specifically, a controlled vehicle model is built based on a neural network to reflect the actual characteristics of the controlled vehicle. It should be noted that the training of the controlled vehicle model is obtained based on the orthogonal experimental design of the controlled vehicle. The vehicle state information is input into the pre-trained controlled vehicle model to obtain the vehicle state information at the next moment, and then the vehicle's orientation and structure information is calculated based on the vehicle state information at the next moment.

[0063] Step 204: Based on the vehicle orientation structure information, determine the lane line information on both sides of the simulated lane. The lane line information on both sides includes the lane line fitting parameters on both sides.

[0064] The simulated lane is the simulated environment. During simulation testing, the simulated lane to be measured is retrieved from the environment database. Specifically, the environment database may contain data for three environment models: model 1 has a lane width of 3 meters, model 2 has a lane width of 4 meters, and model 3 has a lane width of 5 meters. The required environment model is determined by identifying environmental markers.

[0065] Lane information on both sides: The parameter information of the lane lines on the left and right sides of the simulated lane, such as lane line curvature, curvature change rate, lane line marking type, etc.

[0066] Step 206: Based on the lane line fitting parameters on both sides, determine the lane center line fitting parameters perceived by the vehicle to be controlled at the next moment. The reference points for determining the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are different, and the number of parameters of the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are the same.

[0067] Here, the fitting parameters refer to the parameters of the fitting curve obtained by fitting the lane line. In other words, the fitting curve is determined using the overfitting parameters, and the lane line is determined through the fitting curve. For example, the lane centerline perceived by the controlled vehicle is fitted with a cubic polynomial. At position x in front of the vehicle, the coordinates of the point on the lane line are represented as (x, c0+c1x+c2x). 2 +c3x3 Therefore, the lane centerline fitting parameters include c0, c1, c2, and c3, where, see [reference needed]. Figure 3 c0, c1, c2, and c3 represent the deviation distance of the lane line from the camera along the direction perpendicular to the vehicle's orientation, the lane line's directional angle relative to the vehicle, the lane line's curvature, and the rate of change of the lane line's curvature, respectively. Therefore, it can be known that since the lane centerline fitting parameters perceived by the controlled vehicle at the next moment are determined by the lane line fitting parameters on both sides, the number of fitting parameters in both sets of fitting parameters should be the same. The fitting polynomials of the lane lines on both sides and the lane centerline should have the same number of terms; otherwise, calculation is impossible, or the lane centerline fitting line cannot be quickly calculated from the lane line fitting lines on both sides.

[0068] It should be noted that after determining the simulated lane through the vehicle's orientation structure information, the lane line fitting parameters on both sides of the retrieved lane parameter information are obtained by measuring data with the rear axle center of the vehicle as the reference point. However, the lane centerline fitting parameters perceived by the vehicle under control are determined with the front camera of the vehicle as the reference point. Therefore, to determine the lane centerline fitting parameters perceived by the vehicle under control at the next moment based on the lane line fitting parameters on both sides, it is necessary to switch the reference point of the lane line fitting parameters on both sides from the rear axle center of the vehicle to the front camera.

[0069] Step 208: Based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the current time and the next time, lane centering control is performed on the vehicle to be controlled, and the deviation error of the vehicle from the centerline target after control is calculated.

[0070] The lane centering control action is performed by the lane centering control algorithm in the lane centering control software. Specifically, it calculates the vehicle's deviation error from the lane centerline based on the perceived data of the lane centerline (including lane centerline fitting parameters), then corrects the error through the control algorithm, and finally obtains a steering wheel angle control amount. It should be noted that there are various control algorithms, and this embodiment does not specifically limit the control algorithm used.

[0071] After completing the lane centering control simulation at the current moment, a steering wheel angle control value is obtained. This steering wheel angle control value and the lane centerline fitting parameters perceived by the vehicle to be controlled at the next moment are used as inputs for the simulation at the next moment.

[0072] In the method provided in the above embodiments, the vehicle state parameters of the vehicle to be controlled at the current moment are obtained. Based on the vehicle state parameters, the vehicle orientation structure information of the vehicle to be controlled in the simulated lane is determined. The initial values ​​of the vehicle state parameters are obtained based on the actual vehicle test. Based on the vehicle orientation structure information, the lane line information on both sides of the simulated lane is determined, including lane line fitting parameters. Based on the lane line fitting parameters, the lane centerline fitting parameters perceived by the vehicle to be controlled at the next moment are determined. The reference points for determining the lane line fitting parameters on both sides are different from those for the lane centerline fitting parameters perceived by the vehicle to be controlled, and the number of parameters is the same. Based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the next moment, lane centering control is performed on the vehicle to be controlled, and the deviation error of the controlled vehicle from the target centerline after control is calculated. This solution avoids the response error of different steering systems of different vehicles to the lane centering control software by re-simulating the vehicle after the actual vehicle test, thereby improving the test accuracy of the lane centering control software.

[0073] In one embodiment, referring to 4, the vehicle state parameters include the steering wheel angle control amount and the lane centerline fitting parameters perceived by the vehicle under control; correspondingly, based on the vehicle state parameters of the vehicle under control at the current moment, the vehicle orientation structure information of the vehicle under control in the simulated lane is determined, including:

[0074] Step 402: Input the current steering wheel angle control value and the lane centerline fitting parameters perceived by the vehicle under control into the vehicle simulation model of the vehicle under control to obtain the reference lane centerline fitting parameters.

[0075] Step 404: Determine the vehicle orientation structure information of the vehicle to be controlled in the simulated lane based on the vehicle state parameters at the current moment and the fitting parameters of the reference lane centerline.

[0076] The vehicle simulation model is determined based on real-vehicle test data of the controlled vehicle. It should be noted that a corresponding vehicle simulation model is built for each tested vehicle based on its test data. Therefore, differences between individual vehicles due to variations in steering system components, etc., are reflected in the vehicle simulation model. The vehicle simulation model can be built based on neural networks to determine the relationship between the vehicle's state after applying steering wheel angle control and its state before the input.

[0077] Specifically, for example, a vehicle simulation model is built based on a neural network. The training data for the model is collected using orthogonal experimental design. Seven parameters of the input layer (vehicle weight, vehicle speed, steering wheel angle control value, and fitting parameters c0, c1, c2, and c3) are used as seven factors in the orthogonal experiment. Each factor has nine levels, with nine levels evenly distributed across the parameter values. Based on the test cases obtained from the orthogonal experimental design, real-vehicle tests are conducted, and the parameter data for the input and output layers of the neural network are collected. Of the data obtained from the orthogonal experiment, 10% is randomly selected as the test set, and the remainder is used as the training set for neural network training. After training, the performance of the neural network is evaluated using the test set. It should be noted that the number of real-vehicle tests can be manually measured data or obtained by controlling the vehicle using a lane centering control algorithm on the tested vehicle.

[0078] Accordingly, in the above embodiments, the inputs to the vehicle simulation model include the vehicle weight, vehicle speed, steering wheel angle control amount, and lane centerline fitting parameters (c0, c1, c2, and c3) currently perceived by the L2 forward-looking camera. The output is the vehicle information after applying the steering wheel angle control amount, including the vehicle's current steering wheel angle and the lane centerline fitting parameters perceived by the L2 forward-looking camera at the next moment after applying the steering wheel angle control amount.

[0079] In addition, the hidden layer of the neural network can be set to contain 15 neurons according to Kolmogorov's theorem; the training data of the neural network is obtained through real vehicle data collection, and the training algorithm adopts the LM optimization algorithm.

[0080] Using the lane centerline fitting parameters sensed by the L2 forward-looking camera at the next moment after applying the steering wheel angle control value, as the model output, as the reference centerline fitting parameters, the vehicle's orientation structure information can then be calculated using the following formula. This information includes the vehicle's lateral and longitudinal positions in the world coordinate system (X...). w Y w ), speed (V) xw V yw ), yaw angle (θ) and yaw angular velocity (ω):

[0081] X w =X0+TV x cos C1

[0082] Y w =Y0-TV x sin C1

[0083] V xw =V x cos C1

[0084] Vyw =-V x sin C1

[0085]

[0086]

[0087] Where (X0, Y0) is the current position of the vehicle, V x C1 represents the vehicle's speed at the current moment, and C1 is the value of C1 in the reference lane centerline fitting parameters.

[0088] In the method provided in the above embodiments, the next moment's lane centerline fitting parameters and other information are determined by a single simulation model used to calculate the vehicle-connecting pipe orientation structure information. This can overcome the influence of differences between different vehicles and the components of the vehicle lane system on the simulation test results, and improve the simulation test accuracy of the lane centering control algorithm.

[0089] In one embodiment, the lane line information on both sides of the simulated lane is determined based on the vehicle orientation structure information, including:

[0090] Based on the vehicle's orientation and structural information, determine the lane information for the simulated lane;

[0091] Based on the lane information, the lane line information on both sides of the simulated lane is retrieved from the simulation model of the simulated lane.

[0092] Specifically, the environment model includes road parameter information, such as the number of lanes, lane width, the starting and ending points of the center lines of each lane, and the coordinates of control points. For example, in a single-lane model, the lane width is set to 3.75m based on highway lane parameters. The three-dimensional coordinates of the starting and ending points of the lane center lines and the control points are set according to the desired simulation scenario. For straight road scenarios, only the three-dimensional coordinates of the starting and ending points of the lane center lines are given. For curved road scenarios, the three-dimensional coordinates of the required control points are given in addition. For lanes with slopes, the three-dimensional coordinates of the control points are set.

[0093] The simulation lane is input into the simulation process by either identifying the test lane marker contained in the vehicle orientation structure information or manually determining the simulation lane based on the vehicle orientation structure information. After determining the simulation lane, the lane information of the simulation lane in the environment model is obtained. The lane information includes information such as lane line curvature, rate of change of curvature, orientation angle, lateral position, perception intensity, and width.

[0094] In the method provided in the above embodiments, a connection is established between the controlled vehicle and the lane, the lane information of the lane where the controlled vehicle is located is determined, and the accuracy of the lane centerline fitting parameters is provided.

[0095] In one embodiment, the reference point for determining the fitting parameters of the lane lines on both sides is a first reference point, and the reference point for determining the fitting parameters of the lane centerline perceived by the vehicle under control is a second reference point; accordingly, based on the fitting parameters of the lane lines on both sides, determining the fitting parameters of the lane centerline perceived by the vehicle under control at the next moment includes:

[0096] The orientation angle of the vehicle to be controlled in the simulated lane is determined based on the vehicle's orientation structure information.

[0097] Obtain the reference distance between the first reference point and the second reference point;

[0098] Based on the orientation angle, reference distance, and lane line fitting parameters on both sides, the transformation fitting parameters of the vehicle lines on both sides with the second reference point as the reference point are determined.

[0099] Based on the conversion fitting parameters of the lane lines on both sides, determine the lane centerline fitting parameters perceived by the vehicle to be controlled at the next moment in the current moment.

[0100] Since the input and output lane centerline fitting parameters of the vehicle model are measured with the front camera as the reference point, while the C0 parameter of the left and right lane line fitting parameters in the lane information of the simulated lane is measured with the rear axle center of the vehicle as the reference point, coordinate transformation is performed based on the distance between the L2 front camera and the rear axle center and the vehicle orientation angle. After the transformation, the fitting parameters of the left and right lane lines are calculated to obtain the lane centerline fitting parameters.

[0101] In the method provided in the above embodiments, the fitting parameters of the lane centerline are calculated by using the fitting parameters of the lane lines on both sides, so as to ensure the accuracy of the lane centerline fitting parameters and improve the accuracy of the simulation test.

[0102] In one embodiment, the lane centerline fitting parameters perceived by the vehicle to be controlled at the next moment are determined based on the transition fitting parameters of the lane lines on both sides, including:

[0103] For any parameter of the lane centerline fitting parameters perceived by the vehicle under control, the average of the two parameters corresponding to the transformation fitting parameters of the lane lines on both sides is taken as the lane centerline fitting parameter of the vehicle under control at the next moment.

[0104] Specifically, for example, regarding the lane centerline fitting parameter c1, the average of two corresponding values ​​in the transformed fitting parameters of the left and right lane lines is taken as the c1 value. The lane centerline fitting parameter is calculated using the transformed fitting parameters of the left and right lane lines, improving the accuracy and precision of the fitting parameters, and thus enhancing the testing accuracy of the lane centering control algorithm.

[0105] In one embodiment, see Figure 5 The vehicle state parameters include the steering wheel angle control value; correspondingly, based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the current moment and the next moment, lane centering control is performed on the vehicle to be controlled, and the deviation error of the vehicle from the target centerline after control is calculated, including:

[0106] Step 502: Calculate the initial error of the vehicle's deviation from the center line in the simulated lane based on the lane center line fitting parameters perceived by the vehicle at the next moment after the current moment.

[0107] Step 504: Based on the initial error of deviation from the center line, determine the steering wheel angle control amount for the next moment at the current moment;

[0108] Step 506: Apply the steering wheel angle control amount of the next moment to the vehicle to be controlled, and obtain the deviation error of the vehicle from the center line after application.

[0109] The error of the vehicle deviating from the lane centerline is calculated based on the perceived data of the lane centerline. This error is then corrected using a control algorithm, ultimately resulting in a steering wheel control angle and the corrected error, which is used as the target error. The target error is a parameter used to measure the consistency between the simulation environment and the real-vehicle testing environment. Since the evaluation of the lane centering control algorithm mainly assesses its lateral control error, for example, the control error in real-vehicle testing might be 0.1m, but the control error obtained in some simulation environments might only be 0.01m, a significant difference from the real-vehicle result. If a simulation environment can also achieve an error of 0.1m, it indicates that the simulation environment is effective and can reflect the control issues of the real vehicle.

[0110] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0111] Based on the same inventive concept, this application also provides a simulation test device for vehicle lane centering control, used to implement the simulation test method for vehicle lane centering control described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the simulation test device for vehicle lane centering control provided below can be found in the limitations of the simulation test method for vehicle lane centering control described above, and will not be repeated here.

[0112] In one embodiment, such as Figure 6 As shown, a simulation test device for vehicle lane centering control is provided, comprising: a vehicle simulation module 601, a lane simulation module 602, a parameter determination module 603, and a centering control module 604, wherein:

[0113] The vehicle simulation module 601 is used to obtain the vehicle state parameters of the vehicle to be controlled at the current time. Based on the vehicle state parameters of the vehicle to be controlled at the current time, the vehicle orientation structure information of the vehicle to be controlled in the simulation lane is determined. The initial values ​​of the vehicle state parameters are obtained based on the actual vehicle test of the vehicle to be controlled.

[0114] The lane simulation module 602 is used to determine the lane line information on both sides of the simulated lane based on the vehicle orientation structure information. The lane line information on both sides includes the lane line fitting parameters on both sides.

[0115] The parameter determination module 603 is used to determine the lane centerline fitting parameters perceived by the vehicle under control at the next moment based on the lane line fitting parameters on both sides. The reference points for determining the lane line fitting parameters on both sides and the lane centerline fitting parameters perceived by the vehicle under control are different, and the number of parameters of the lane line fitting parameters on both sides and the lane centerline fitting parameters perceived by the vehicle under control are the same.

[0116] The centering control module 604 is used to perform lane centering control on the vehicle under control based on the lane centerline fitting parameters perceived by the vehicle under control at the current time and the next time, and to calculate the deviation error of the vehicle under control from the centerline target after control.

[0117] In one embodiment, the vehicle simulation module 601 is further configured to:

[0118] The current steering wheel angle control value and the lane centerline fitting parameters perceived by the vehicle under control are input into the vehicle simulation model of the vehicle under control to obtain the reference lane centerline fitting parameters.

[0119] Based on the vehicle state parameters at the current moment and the fitting parameters of the reference lane centerline, the vehicle orientation structure information of the vehicle to be controlled in the simulated lane is determined.

[0120] In one embodiment, the lane simulation module 602 is further configured to:

[0121] Based on the vehicle's orientation and structural information, determine the lane information for the simulated lane;

[0122] Based on the lane information, the lane line information on both sides of the simulated lane is retrieved from the simulation model of the simulated lane.

[0123] In one embodiment, the parameter determination module 603 is further configured to:

[0124] The orientation angle of the vehicle to be controlled in the simulated lane is determined based on the vehicle's orientation structure information.

[0125] Obtain the reference distance between the first reference point and the second reference point;

[0126] Based on the orientation angle, reference distance, and lane line fitting parameters on both sides, the transformation fitting parameters of the vehicle lines on both sides with the second reference point as the reference point are determined.

[0127] Based on the conversion fitting parameters of the lane lines on both sides, determine the lane centerline fitting parameters perceived by the vehicle to be controlled at the next moment in the current moment.

[0128] In one embodiment, the parameter determination module 603 is further configured to:

[0129] For any parameter of the lane centerline fitting parameters perceived by the vehicle under control, the average of the two parameters corresponding to the transformation fitting parameters of the lane lines on both sides is taken as the lane centerline fitting parameter of the vehicle under control at the next moment.

[0130] In one embodiment, the centering control module 604 is further configured to:

[0131] Based on the lane centerline fitting parameters perceived by the vehicle under control at the next moment from the current moment, calculate the initial error of the vehicle under control deviating from the centerline in the simulated lane.

[0132] Based on the initial error of deviation from the center line, determine the steering wheel angle control amount for the next moment at the current moment;

[0133] The steering wheel angle control value for the next moment is applied to the vehicle to be controlled, and the deviation error of the vehicle from the center line after application is obtained.

[0134] In one embodiment, the centering control module 604 is further configured to:

[0135] The lane centerline fitting parameters perceived by the vehicle under control at the current moment and the steering wheel angle control amount at the current moment and the next moment will be used as the vehicle state parameters of the vehicle under control at the current moment and the next moment.

[0136] The modules in the aforementioned vehicle lane centering control simulation test device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0137] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores lane line fitting parameter data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a simulation test method for vehicle lane centering control.

[0138] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0139] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0140] Obtain the vehicle status parameters of the vehicle to be controlled at the current moment. Based on the vehicle status parameters of the vehicle to be controlled at the current moment, determine the vehicle orientation structure information of the vehicle to be controlled in the simulated lane. The initial values ​​of the vehicle status parameters are obtained based on the actual vehicle test of the vehicle to be controlled.

[0141] Based on the vehicle orientation structure information, determine the lane line information on both sides of the simulated lane. The lane line information on both sides includes the lane line fitting parameters on both sides.

[0142] Based on the lane line fitting parameters on both sides, determine the lane center line fitting parameters perceived by the vehicle to be controlled at the next moment. The reference points for determining the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are different, and the number of parameters of the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are the same.

[0143] Based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the current moment and the next moment, lane centering control is performed on the vehicle to be controlled, and the deviation error of the vehicle from the centerline target after control is calculated.

[0144] In one embodiment, the vehicle state parameters include steering wheel angle control parameters and lane centerline fitting parameters perceived by the vehicle under control; correspondingly, the processor also performs the following steps when executing the computer program:

[0145] The current steering wheel angle control value and the lane centerline fitting parameters perceived by the vehicle under control are input into the vehicle simulation model of the vehicle under control to obtain the reference lane centerline fitting parameters.

[0146] Based on the vehicle state parameters at the current moment and the fitting parameters of the reference lane centerline, the vehicle orientation structure information of the vehicle to be controlled in the simulated lane is determined.

[0147] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0148] Based on the vehicle's orientation and structural information, determine the lane information for the simulated lane;

[0149] Based on the lane information, the lane line information on both sides of the simulated lane is retrieved from the simulation model of the simulated lane.

[0150] In one embodiment, the reference point for determining the fitting parameters of the lane lines on both sides is the first reference point, and the reference point for determining the fitting parameters of the lane centerline perceived by the controlled vehicle is the second reference point; accordingly, when the processor executes the computer program, it also implements the following steps:

[0151] The orientation angle of the vehicle to be controlled in the simulated lane is determined based on the vehicle's orientation structure information.

[0152] Obtain the reference distance between the first reference point and the second reference point;

[0153] Based on the orientation angle, reference distance, and lane line fitting parameters on both sides, the transformation fitting parameters of the vehicle lines on both sides with the second reference point as the reference point are determined.

[0154] Based on the conversion fitting parameters of the lane lines on both sides, determine the lane centerline fitting parameters perceived by the vehicle to be controlled at the next moment in the current moment.

[0155] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0156] For any parameter of the lane centerline fitting parameters perceived by the vehicle under control, the average of the two parameters corresponding to the transformation fitting parameters of the lane lines on both sides is taken as the lane centerline fitting parameter of the vehicle under control at the next moment.

[0157] In one embodiment, the vehicle state parameters include a steering wheel angle control value; correspondingly, the processor, when executing the computer program, also performs the following steps:

[0158] Based on the lane centerline fitting parameters perceived by the vehicle under control at the next moment from the current moment, calculate the initial error of the vehicle under control deviating from the centerline in the simulated lane.

[0159] Based on the initial error of deviation from the center line, determine the steering wheel angle control amount for the next moment at the current moment;

[0160] The steering wheel angle control value for the next moment is applied to the vehicle to be controlled, and the deviation error of the vehicle from the center line after application is obtained.

[0161] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0162] The lane centerline fitting parameters perceived by the vehicle under control at the current moment and the steering wheel angle control amount at the current moment and the next moment will be used as the vehicle state parameters of the vehicle under control at the current moment and the next moment.

[0163] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0164] Obtain the vehicle status parameters of the vehicle to be controlled at the current moment. Based on the vehicle status parameters of the vehicle to be controlled at the current moment, determine the vehicle orientation structure information of the vehicle to be controlled in the simulated lane. The initial values ​​of the vehicle status parameters are obtained based on the actual vehicle test of the vehicle to be controlled.

[0165] Based on the vehicle orientation structure information, determine the lane line information on both sides of the simulated lane. The lane line information on both sides includes the lane line fitting parameters on both sides.

[0166] Based on the lane line fitting parameters on both sides, determine the lane center line fitting parameters perceived by the vehicle to be controlled at the next moment. The reference points for determining the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are different, and the number of parameters of the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are the same.

[0167] Based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the current moment and the next moment, lane centering control is performed on the vehicle to be controlled, and the deviation error of the vehicle from the centerline target after control is calculated.

[0168] In one embodiment, the vehicle state parameters include steering wheel angle control parameters and lane centerline fitting parameters perceived by the vehicle under control; correspondingly, when the computer program is executed by the processor, it also performs the following steps:

[0169] The current steering wheel angle control value and the lane centerline fitting parameters perceived by the vehicle under control are input into the vehicle simulation model of the vehicle under control to obtain the reference lane centerline fitting parameters.

[0170] Based on the vehicle state parameters at the current moment and the fitting parameters of the reference lane centerline, the vehicle orientation structure information of the vehicle to be controlled in the simulated lane is determined.

[0171] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0172] Based on the vehicle's orientation and structural information, determine the lane information for the simulated lane;

[0173] Based on the lane information, the lane line information on both sides of the simulated lane is retrieved from the simulation model of the simulated lane.

[0174] In one embodiment, the reference point for determining the fitting parameters of the lane lines on both sides is the first reference point, and the reference point for determining the fitting parameters of the lane centerline perceived by the controlled vehicle is the second reference point; accordingly, when the computer program is executed by the processor, it also implements the following steps:

[0175] The orientation angle of the vehicle to be controlled in the simulated lane is determined based on the vehicle's orientation structure information.

[0176] Obtain the reference distance between the first reference point and the second reference point;

[0177] Based on the orientation angle, reference distance, and lane line fitting parameters on both sides, the transformation fitting parameters of the vehicle lines on both sides with the second reference point as the reference point are determined.

[0178] Based on the conversion fitting parameters of the lane lines on both sides, determine the lane centerline fitting parameters perceived by the vehicle to be controlled at the next moment in the current moment.

[0179] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0180] For any parameter of the lane centerline fitting parameters perceived by the vehicle under control, the average of the two parameters corresponding to the transformation fitting parameters of the lane lines on both sides is taken as the lane centerline fitting parameter of the vehicle under control at the next moment.

[0181] In one embodiment, the vehicle state parameters include a steering wheel angle control value; correspondingly, when the computer program is executed by the processor, it also performs the following steps:

[0182] Based on the lane centerline fitting parameters perceived by the vehicle under control at the next moment from the current moment, calculate the initial error of the vehicle under control deviating from the centerline in the simulated lane.

[0183] Based on the initial error of deviation from the center line, determine the steering wheel angle control amount for the next moment at the current moment;

[0184] The steering wheel angle control value for the next moment is applied to the vehicle to be controlled, and the deviation error of the vehicle from the center line after application is obtained.

[0185] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0186] The lane centerline fitting parameters perceived by the vehicle under control at the current moment and the steering wheel angle control amount at the current moment and the next moment will be used as the vehicle state parameters of the vehicle under control at the current moment and the next moment.

[0187] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0188] Obtain the vehicle status parameters of the vehicle to be controlled at the current moment. Based on the vehicle status parameters of the vehicle to be controlled at the current moment, determine the vehicle orientation structure information of the vehicle to be controlled in the simulated lane. The initial values ​​of the vehicle status parameters are obtained based on the actual vehicle test of the vehicle to be controlled.

[0189] Based on the vehicle orientation structure information, determine the lane line information on both sides of the simulated lane. The lane line information on both sides includes the lane line fitting parameters on both sides.

[0190] Based on the lane line fitting parameters on both sides, determine the lane center line fitting parameters perceived by the vehicle to be controlled at the next moment. The reference points for determining the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are different, and the number of parameters of the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle to be controlled are the same.

[0191] Based on the lane centerline fitting parameters perceived by the vehicle to be controlled at the current moment and the next moment, lane centering control is performed on the vehicle to be controlled, and the deviation error of the vehicle from the centerline target after control is calculated.

[0192] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0193] The current steering wheel angle control value and the lane centerline fitting parameters perceived by the vehicle under control are input into the vehicle simulation model of the vehicle under control to obtain the reference lane centerline fitting parameters.

[0194] Based on the vehicle state parameters at the current moment and the fitting parameters of the reference lane centerline, the vehicle orientation structure information of the vehicle to be controlled in the simulated lane is determined.

[0195] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0196] Based on the vehicle's orientation and structural information, determine the lane information for the simulated lane;

[0197] Based on the lane information, the lane line information on both sides of the simulated lane is retrieved from the simulation model of the simulated lane.

[0198] In one embodiment, the reference point for determining the fitting parameters of the lane lines on both sides is the first reference point, and the reference point for determining the fitting parameters of the lane centerline perceived by the controlled vehicle is the second reference point; accordingly, when the computer program is executed by the processor, it also implements the following steps:

[0199] The orientation angle of the vehicle to be controlled in the simulated lane is determined based on the vehicle's orientation structure information.

[0200] Obtain the reference distance between the first reference point and the second reference point;

[0201] Based on the orientation angle, reference distance, and lane line fitting parameters on both sides, the transformation fitting parameters of the vehicle lines on both sides with the second reference point as the reference point are determined.

[0202] Based on the conversion fitting parameters of the lane lines on both sides, determine the lane centerline fitting parameters perceived by the vehicle to be controlled at the next moment in the current moment.

[0203] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0204] For any parameter of the lane centerline fitting parameters perceived by the vehicle under control, the average of the two parameters corresponding to the transformation fitting parameters of the lane lines on both sides is taken as the lane centerline fitting parameter of the vehicle under control at the next moment.

[0205] In one embodiment, the vehicle state parameters include a steering wheel angle control value; correspondingly, when the computer program is executed by the processor, it also performs the following steps:

[0206] Based on the lane centerline fitting parameters perceived by the vehicle under control at the next moment from the current moment, calculate the initial error of the vehicle under control deviating from the centerline in the simulated lane.

[0207] Based on the initial error of deviation from the center line, determine the steering wheel angle control amount for the next moment at the current moment;

[0208] The steering wheel angle control value for the next moment is applied to the vehicle to be controlled, and the deviation error of the vehicle from the center line after application is obtained.

[0209] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0210] The lane centerline fitting parameters perceived by the vehicle under control at the current moment and the steering wheel angle control amount at the current moment and the next moment will be used as the vehicle state parameters of the vehicle under control at the current moment and the next moment.

[0211] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0212] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0213] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A simulation test method for vehicle lane centering control, characterized in that, The method includes: Obtain the vehicle status parameters of the vehicle to be controlled at the current moment, and determine the vehicle orientation structure information of the vehicle to be controlled in the simulated lane based on the vehicle status parameters of the vehicle to be controlled at the current moment. The initial values ​​of the vehicle status parameters are obtained based on the actual vehicle test of the vehicle to be controlled. Based on the vehicle orientation structure information, the lane line information on both sides of the simulated lane is determined, and the lane line information on both sides includes lane line fitting parameters on both sides. Based on the lane line fitting parameters on both sides, the lane center line fitting parameters perceived by the vehicle under control at the next moment of the current moment are determined. The reference points for determining the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle under control are different. The number of parameters in the lane line fitting parameters on both sides and the lane center line fitting parameters perceived by the vehicle under control are the same. Based on the lane centerline fitting parameters perceived by the vehicle under control at the next time after the current time, lane centering control is performed on the vehicle under control, and the deviation target error of the vehicle under control from the centerline after control is calculated. The reference point for determining the fitting parameters of the lane lines on both sides is the first reference point, and the reference point for determining the fitting parameters of the lane centerline perceived by the vehicle under control is the second reference point; correspondingly, determining the fitting parameters of the lane centerline perceived by the vehicle under control at the next moment based on the fitting parameters of the lane lines on both sides includes: The orientation angle of the vehicle to be controlled in the simulated lane is determined based on the vehicle orientation structure information. Obtain the reference distance between the first reference point and the second reference point; Based on the orientation angle, the reference distance, and the fitting parameters of the lane lines on both sides, the transformation fitting parameters of the lane lines on both sides with the second reference point as the determining reference point are determined; Based on the conversion fitting parameters of the lane lines on both sides, determine the lane centerline fitting parameters perceived by the controlled vehicle at the next moment from the current moment.

2. The method according to claim 1, characterized in that, The vehicle state parameters include the steering wheel angle control value and the lane centerline fitting parameters perceived by the vehicle under control; correspondingly, determining the vehicle orientation structure information of the vehicle under control in the simulated lane based on the vehicle state parameters of the vehicle under control at the current moment includes: The steering wheel angle control value at the current moment and the lane center line fitting parameters perceived by the vehicle under control are input into the vehicle simulation model of the vehicle under control to obtain the reference lane center line fitting parameters. Based on the vehicle state parameters at the current moment and the fitting parameters of the reference lane centerline, the vehicle orientation structure information of the vehicle to be controlled in the simulated lane is determined.

3. The method according to claim 1, characterized in that, The step of determining the lane line information on both sides of the simulated lane based on the vehicle orientation structure information includes: Based on the vehicle orientation structure information, determine the lane information of the simulated lane; Based on the lane information, the lane line information on both sides of the simulated lane is retrieved from the simulation model of the simulated lane.

4. The method according to claim 1, characterized in that, The step of determining the lane centerline fitting parameters perceived by the controlled vehicle at the next moment based on the conversion fitting parameters of the lane lines on both sides includes: For any parameter of the lane centerline fitting parameters perceived by the vehicle under control, the average value of the two parameters corresponding to the parameter in the transformation fitting parameters of the lane lines on both sides is taken as the lane centerline fitting parameter of the vehicle under control at the next time of the current time.

5. The method according to claim 1, characterized in that, The vehicle state parameters include the steering wheel angle control value; correspondingly, the lane centerline fitting parameters perceived by the vehicle under control at the next moment after the current moment are used to perform lane centering control on the vehicle under control, and the deviation error of the vehicle under control from the centerline target after control are calculated, including: Based on the lane centerline fitting parameters perceived by the vehicle under control at the next time step, the initial error of the vehicle under control in the simulated lane deviating from the centerline is calculated. Based on the initial error of deviation from the center line, determine the steering wheel angle control amount for the next moment at the current moment; The steering wheel angle control value of the next moment from the current moment is applied to the vehicle under control, and the deviation of the vehicle from the center line target error of the vehicle under control after application is obtained.

6. The method according to claim 5, characterized in that, The method further includes: The lane centerline fitting parameters perceived by the vehicle under control at the next moment of the current moment and the steering wheel angle control amount at the next moment of the current moment are used as the vehicle state parameters of the vehicle under control at the next moment of the current moment.

7. A simulation test device for vehicle lane centering control, characterized in that, The device includes: The vehicle simulation module is used to obtain the vehicle status parameters of the vehicle to be controlled at the current moment, and to determine the vehicle orientation structure information of the vehicle to be controlled in the simulation lane based on the vehicle status parameters of the vehicle to be controlled at the current moment. The initial values ​​of the vehicle status parameters are obtained based on the actual vehicle test of the vehicle to be controlled. The lane simulation module is used to determine the lane line information on both sides of the simulated lane based on the vehicle orientation structure information, wherein the lane line information on both sides includes lane line fitting parameters on both sides. The parameter determination module is used to determine the lane centerline fitting parameters perceived by the vehicle under control at the next moment based on the lane line fitting parameters on both sides. The reference points for determining the lane line fitting parameters on both sides and the lane centerline fitting parameters perceived by the vehicle under control are different, and the number of parameters of the lane line fitting parameters on both sides and the lane centerline fitting parameters perceived by the vehicle under control are the same. The centering control module is used to perform lane centering control on the vehicle under control based on the lane centerline fitting parameters perceived by the vehicle under control at the next time after the current time, and to calculate the target error of the vehicle under control deviating from the centerline after control. The reference point for determining the fitting parameters of the lane lines on both sides is the first reference point, and the reference point for determining the fitting parameters of the lane centerline perceived by the vehicle under control is the second reference point; correspondingly, the parameter determination module is further used for: The orientation angle of the vehicle to be controlled in the simulated lane is determined based on the vehicle orientation structure information. Obtain the reference distance between the first reference point and the second reference point; Based on the orientation angle, the reference distance, and the fitting parameters of the lane lines on both sides, the transformation fitting parameters of the lane lines on both sides with the second reference point as the determining reference point are determined; Based on the conversion fitting parameters of the lane lines on both sides, determine the lane centerline fitting parameters perceived by the controlled vehicle at the next moment from the current moment.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images