Adaptive cruise control parameter calibration method and related device

Abstract

The invention discloses a parameter calibration method for adaptive cruise control and a related device, response data of a target vehicle is acquired in response to a received control signal, and the control signal is used for simulating a plurality of control cases in an adaptive cruise control process. And according to the plurality of control cases and the response data corresponding to the plurality of control cases, establishing a vehicle response characteristic relationship of the target vehicle. Initial parameters are obtained, wherein the initial parameters are self-adaptive cruise control parameters which are not adjusted yet; and adjusting the initial parameter according to the vehicle response characteristic relation to obtain a target parameter of the target vehicle. Therefore, by establishing the vehicle response characteristic relation of the target vehicle and performing targeted adjustment on the initial parameters according to the vehicle response characteristic relation, the target parameters capable of adapting to the response characteristics of the target vehicle are obtained, and the accuracy of the parameters is improved; therefore, more accurate control can be realized when the target vehicle performs adaptive cruise control according to the target parameters, and the safety is improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a parameter calibration method for adaptive cruise control and related devices. Background Art

[0002] Adaptive Cruise Control (ACC) technology is an assisted driving technology. Through ACC technology, the vehicle can automatically adjust the speed, thereby automating driving processes such as following the vehicle, cornering, and cruising.

[0003] In related technologies, adaptive cruise control is implemented through preset parameters, for example, cruise control parameters are used to implement constant speed cruising on a highway with no preceding vehicle, or following a vehicle automatically is implemented through following vehicle control parameters.

[0004] However, the parameters used for adaptive cruise control in related technologies are not adjusted to account for the differences between different vehicles. One parameter is applied to multiple vehicles, resulting in low accuracy. Summary of the Invention

[0005] In response to the above problems, the present application provides a parameter calibration method and related devices for adaptive cruise control, which are used to improve the accuracy of the parameters by adjusting the parameters of the adaptive cruise control according to the differences between different vehicles.

[0006] Based on this, this application discloses the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for calibrating parameters of an adaptive cruise control, the method comprising:

[0008] Acquiring response data of a target vehicle after receiving a control signal, wherein the control signal is used to simulate multiple control use cases during an adaptive cruise control process;

[0009] establishing a vehicle response characteristic relationship of the target vehicle based on the plurality of control use cases and the response data respectively corresponding to the plurality of control use cases;

[0010] Acquiring initial parameters, where the initial parameters are used to control an adaptive cruise control process of the target vehicle;

[0011] The initial parameters are adjusted according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

[0012] Optionally, adjusting the initial parameters according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle includes:

[0013] Acquiring a standard response characteristic relationship, where the standard response characteristic relationship is used to indicate a response characteristic relationship of the vehicle corresponding to the initial parameters;

[0014] determining a first adjustment coefficient of the initial parameter according to a first difference between the vehicle response characteristic relationship and the standard response characteristic relationship;

[0015] The initial parameter is adjusted using the first adjustment coefficient to obtain the target parameter.

[0016] Optionally, the method further includes:

[0017] Acquiring suspension system data of the target vehicle;

[0018] The establishing of a vehicle response characteristic relationship of the target vehicle based on the plurality of control use cases and the response data respectively corresponding to the plurality of control use cases includes:

[0019] A vehicle response characteristic relationship of the target vehicle is established based on the response characteristics of the target vehicle indicated by the suspension system data, the multiple control use cases, and the response data corresponding to the multiple control use cases.

[0020] Optionally, the method further includes:

[0021] Acquiring a plurality of training parameters and a plurality of evaluation scores obtained by the target vehicle during the adaptive cruise control process by applying the training parameters;

[0022] According to the multiple training parameters and the multiple evaluation scores, the target parameters are optimized by a machine learning algorithm to obtain optimized parameters.

[0023] Optionally, establishing a vehicle response characteristic relationship of the target vehicle according to the multiple control use cases and the response data respectively corresponding to the multiple control use cases includes:

[0024] Get the linear regression model;

[0025] The multiple control use cases and the response data respectively corresponding to the multiple control use cases are fitted by the linear regression model to obtain a vehicle response characteristic relationship of the target vehicle.

[0026] Optionally, the method further includes:

[0027] Get target weather data;

[0028] Adjusting the initial parameters according to the road friction coefficient indicated by the target weather data to obtain first optimized initial parameters;

[0029] The first optimization initial parameters are adjusted according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

[0030] Optionally, the method further includes:

[0031] Acquire a target driving type of a target user, where the target driving type is used to indicate a driving behavior type of the target user;

[0032] Adjusting the initial parameters according to the target driving type to obtain second optimized initial parameters;

[0033] The second optimization initial parameters are adjusted according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

[0034] In a second aspect, an embodiment of the present application provides a parameter calibration device for adaptive cruise control, the device comprising: an acquisition unit, a construction unit, and an adjustment unit:

[0035] The acquisition unit is configured to acquire response data of the target vehicle in response to receiving a control signal, wherein the control signal is used to simulate multiple control use cases in an adaptive cruise control process;

[0036] The construction unit is configured to establish a vehicle response characteristic relationship of the target vehicle based on the plurality of control use cases and the response data respectively corresponding to the plurality of control use cases;

[0037] The acquiring unit is further configured to acquire initial parameters, where the initial parameters are adaptive cruise control parameters that have not been adjusted;

[0038] The adjustment unit is used to adjust the initial parameters according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

[0039] In a third aspect, an embodiment of the present application provides a computer device, the computer device including a processor and a memory:

[0040] The memory is used to store a computer program and transmit the computer program to the processor;

[0041] The processor is configured to execute the method according to the first aspect of claim 1 according to the computer program.

[0042] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method described in the first aspect above.

[0043] In a fifth aspect, an embodiment of the present application provides a computer program product comprising a computer program, which, when executed on a computer device, enables the computer device to execute the method described in the first aspect above.

[0044] It can be seen from the above technical solutions that this application has at least the following beneficial effects:

[0045] This application no longer applies a single parameter to multiple vehicles, but calibrates parameters for vehicles with different response characteristics. Taking a target vehicle as an example, in response to receiving a control signal, the response data of the target vehicle is obtained, and the control signal is used to simulate multiple control use cases in the adaptive cruise control process. Based on the multiple control use cases and the response data corresponding to the multiple control use cases, a vehicle response characteristic relationship of the target vehicle is established. Initial parameters are obtained, and the initial parameters are adaptive cruise control parameters that have not yet been adjusted. The initial parameters are adjusted according to the vehicle response characteristic relationship to obtain target parameters for the target vehicle. Thus, by establishing the vehicle response characteristic relationship of the target vehicle and making targeted adjustments to the initial parameters according to the vehicle response characteristic relationship, target parameters that can adapt to the response characteristics of the target vehicle are obtained, thereby improving the accuracy of the parameters, so that when the target vehicle performs adaptive cruise control according to the target parameters, more precise control can be achieved, thereby improving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 A flow chart of a method for calibrating parameters of an adaptive cruise control provided in an embodiment of the present application;

[0048] Figure 2 A schematic diagram of a process for obtaining response data based on a host computer provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of a process for establishing a vehicle response characteristic relationship provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of a flow chart of a parameter calibration scenario for an adaptive cruise control provided in an embodiment of the present application;

[0051] Figure 5 A schematic diagram of a flow chart of a parameter calibration scenario for an adaptive cruise control provided in an embodiment of the present application;

[0052] Figure 6 A schematic structural diagram of a parameter calibration device for adaptive cruise control provided in an embodiment of the present application;

[0053] Figure 7 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following describes embodiments of the present application in more detail with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are for illustrative purposes only and are not intended to limit the scope of protection of the present application.

[0055] Related technologies calibrate adaptive cruise control parameters using fixed values ​​or simple preset rules. This approach fails to fully consider the varying speeds at which different vehicles respond to a control signal until their actual motion reaches the target value indicated by the control signal. These differences are due to differences in vehicle response characteristics, such as varying response signal delays and pressure reduction response speeds. Consequently, applying a single parameter to multiple vehicles results in low accuracy and reduced safety.

[0056] Based on this, an embodiment of the present application provides a parameter calibration method and related devices for adaptive cruise control. By establishing a vehicle response characteristic relationship of a target vehicle, the initial parameters are adjusted in a targeted manner according to the vehicle response characteristic relationship, and target parameters that can adapt to the response characteristics of the target vehicle are obtained, thereby improving the accuracy of the parameters, so that when the target vehicle performs adaptive cruise control according to the target parameters, more precise control can be achieved, thereby improving safety.

[0057] The adaptive cruise control parameter calibration method provided in this application can be applied to computer devices with parameter calibration capabilities, such as terminal devices and servers. Specifically, the terminal device can be a desktop computer, laptop computer, mobile phone, tablet computer, etc.; the server can be a standalone physical server, a server cluster composed of multiple physical servers, or a distributed system. The terminal device and server can be connected directly or indirectly via wired or wireless communication, which is not limited in this application.

[0058] See also Figure 1, which is a flow chart of the parameter calibration method for adaptive cruise control provided by an embodiment of the present application. For ease of description, the following embodiment is introduced by taking the execution subject of the parameter calibration method for adaptive cruise control as an example. Figure 1 As shown, the parameter calibration method of the adaptive cruise control includes S101-S104.

[0059] S101: Acquire response data of the target vehicle after receiving the control signal.

[0060] The target vehicle is the vehicle used for parameter calibration. The control signals are used to simulate multiple control use cases during adaptive cruise control. Those skilled in the art can configure control use cases based on potential control requests during adaptive cruise control. For example, control requests may include a primary ramp request (one-stage acceleration), a secondary ramp request (two-stage acceleration), and acceleration / deceleration switching requests.

[0061] like Figure 2 As shown, Figure 2 This is a schematic diagram of a process for obtaining response data based on a host computer. During the parameter calibration process, a host computer corresponding to the actuator for open-loop verification can be developed based on the actuator's communication protocol to match the actuator's interface specifications and command set. After the host computer instructs the actuator to issue control signals simulating multiple control use cases, the host computer collects the target vehicle's response data after receiving the control signals. This application does not specifically limit the type of actuator, such as EMS (Engine Management System), VCU (Vehicle Control Unit), ESC (Electronic Stability Control), VLC (Vehicle Longitudinal Controller), etc.

[0062] Response data is feedback data generated by the vehicle in response to receiving a control signal. It reflects the speed at which the vehicle's actual motion reaches the target value indicated by the control signal. Response data can be statistically calculated from basic feedback data such as the target vehicle's acceleration time, acceleration, braking distance, and braking time after receiving the control signal. For example, response data includes response delay time, response overshoot, and pressure relief delay time.

[0063] The response delay time is the time interval from when the vehicle issues a control signal to when the vehicle actually starts to respond. The response delay time includes multiple influencing factors, such as sensor delay, control algorithm processing time, actuator response time, etc. For example, if the target vehicle starts to decelerate 0.05 seconds after the brake signal is issued, then 0.05 seconds is the response delay time of the target vehicle.

[0064] Response overshoot is the maximum deviation of the vehicle's actual output value from the target value when responding to a control signal. For example, if the turning signal instructs the vehicle's front wheels to tilt 10 degrees, and the target vehicle's front wheels tilt 11 degrees in response to the turning signal, the target vehicle's response overshoot for that signal is 10%.

[0065] The pressure relief delay time is the time interval from the issuance of the pressure relief command to the time when the vehicle's brake system starts to reduce pressure. For example, if the target vehicle starts to reduce pressure 0.13 seconds after the pressure relief command is issued, then 0.13 seconds is the pressure relief delay time of the target vehicle.

[0066] From this, it can be seen that the response data, as the embodiment of the vehicle response characteristics in the data dimension, can reflect the response speed of the vehicle in response to the control signal. Different response speeds make the vehicle reach different target values ​​indicated by the control signal at the physical level. Therefore, it is necessary to calibrate the parameters of the adaptive cruise control separately according to the response characteristics of the target vehicle to improve the accuracy of the parameters, thereby improving the precision and safety of the adaptive cruise control.

[0067] S102: Establishing a vehicle response characteristic relationship of the target vehicle according to the plurality of control use cases and the response data respectively corresponding to the plurality of control use cases.

[0068] A control use case refers to a specific operational request set during adaptive cruise control to simulate different driving scenarios. As previously mentioned, the control signal is used to simulate the control use cases during adaptive cruise control. Different control use cases correspond to different control signals, resulting in different response data for the target vehicle when receiving different control signals. By establishing a vehicle response characteristic relationship between the control use case and the response data for the target vehicle, the vehicle response characteristic relationship is used to quantify the response characteristics of the target vehicle.

[0069] In the process of establishing the vehicle response characteristic relationship of the target vehicle, a control signal for simulating a control use case can be sent multiple times for a control use case to obtain multiple response data of the target vehicle for the control use case. Alternatively, multiple control signals for simulating multiple control use cases can be sent to obtain multiple response data corresponding to multiple control use cases of the target vehicle. The embodiments of the present application are not limited here.

[0070] For example, consider a control case with an acceleration request and response data with response delay time. For example, control case A is an acceleration request to accelerate the target vehicle to 60 kilometers per hour (km / h) to achieve the cruising goal of continuously following the vehicle ahead. By obtaining the target vehicle's response delay time after receiving control signal A, the time elapsed between the target vehicle receiving control signal A and the start of acceleration can be determined. Multiple response delay times can be obtained by sending control signal A multiple times, or by sending multiple control signals (e.g., control signal A instructing the target vehicle to accelerate to 60 km / h, control signal B instructing the target vehicle to accelerate to 50 km / h, and control signal C instructing the target vehicle to accelerate to 40 km / h). The target vehicle's response characteristic relationships can then be determined through averaging, regression model fitting, neural network prediction, and other methods. As an implementation approach, multiple vehicle response characteristic relationships can be established for different types of control signals or response data.

[0071] In one possible implementation, the embodiment of the present application provides an implementation method for obtaining a vehicle response characteristic relationship through linear regression fitting. Obtain a linear regression model, which is used to determine the relationship between a control case and response data, and attempts to describe how the response data changes with changes in the control case by finding a best-fitting straight line. Fit multiple control cases and the response data corresponding to the multiple control cases through the linear regression model to obtain the vehicle response characteristic relationship of the target vehicle. Figure 3 As shown, the response data includes response delay time, response overshoot and pressure relief delay time. By performing linear regression analysis on the response data obtained by the actuator, a vehicle response characteristic model (a response characteristic relationship of the target vehicle) can be obtained.

[0072] For example, assuming the control case is an acceleration request and the response data is the response time, the response time is the time it takes for the vehicle to reach the target value indicated by the control signal. Feature extraction can be used to determine the acceleration corresponding to the control case. The target vehicle's response time is then obtained for different accelerations. Multiple accelerations and their corresponding response times are then input into a linear regression model. The linear regression model minimizes the predicted value (the response time predicted by the initial model parameters) and the observed value (the actual response time). By adjusting the initial model parameters, the target linear regression model is obtained, thereby determining the response characteristics of the target vehicle. For example, the slope of the fitted line can be used to determine the speed at which the target vehicle reaches the target value indicated by the control signal; a larger slope indicates a slower speed.

[0073] The result of linear regression model fitting is a linear expression of the target vehicle's response time as it changes with the control use case. Therefore, when the response characteristic relationship of the target vehicle is established through the linear regression model, a more interpretable response characteristic relationship can be obtained, which is more helpful for analyzing the response characteristics of the target vehicle and adjusting the initial parameters of the target vehicle according to the response characteristic relationship, thereby obtaining target parameters that can more accurately reflect the response characteristics of the target vehicle.

[0074] The suspension system is an important component of a car. It not only directly affects the vehicle's handling, comfort, and safety, but also indirectly affects the vehicle's response characteristics. This embodiment of the application also provides a specific implementation method for establishing a vehicle response characteristic relationship based on suspension system data.

[0075] Obtain the target vehicle's suspension system data.

[0076] The suspension system data is the index data describing the suspension system.

[0077] For example, suspension system data includes suspension stiffness and damping. Suspension stiffness measures the suspension system's ability to resist compression or tension deformation. Damping measures the ability of the shock absorber in the suspension system to control spring vibration. The response characteristics of the target vehicle can be determined based on suspension stiffness and damping. Higher suspension stiffness and damping indicate faster response to control signals, while lower suspension stiffness and damping indicate faster response to control signals.

[0078] Thus, the suspension system data can indicate the response characteristics of the target vehicle. Therefore, a vehicle response characteristic relationship for the target vehicle can be established in conjunction with the suspension system data. Specifically, a vehicle response characteristic relationship for the target vehicle can be established based on the response characteristics indicated by the suspension system data, multiple control use cases, and the response data corresponding to each of the multiple control use cases.

[0079] For example, if the target vehicle has higher suspension stiffness and damping, the braking-related follow-stop control parameters in the initial parameters can be adjusted by combining the vehicle response characteristics of the suspension system data to increase the brake pedal opening during braking.

[0080] Therefore, by combining the suspension system data to establish the vehicle response characteristic relationship, the data dimension for establishing the vehicle response characteristic relationship is expanded, making the vehicle response characteristic relationship more comprehensive and accurate, and the target parameters obtained by adjustment are also more accurate.

[0081] S103: Acquire initial parameters.

[0082] Initial parameters are parameters that have not yet been fully adjusted and are used to control the adaptive cruise control process of the target vehicle. For example, the initial parameters can be a previously calibrated parameter that applies to all vehicle models. Initial parameters can also be initial default values ​​set by those skilled in the art based on actual parameter adjustment needs. The present application adjusts the initial parameters based on the vehicle response characteristics of the target vehicle to obtain target parameters that accurately reflect the response characteristics of the target vehicle.

[0083] S104: Adjust the initial parameters according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

[0084] After establishing a vehicle response characteristic relationship for the target vehicle's response characteristics, with the adaptive cruise control parameters adapting to the target vehicle's response characteristics as the adjustment target, an adjustment coefficient can be determined based on the difference between the initial parameters and the satisfaction of the adjustment target, and the initial parameters can be adjusted to obtain target parameters adapted to the target vehicle's response characteristics. For example, if the target vehicle's vehicle response characteristic relationship indicates that the target vehicle has a low response delay, a corresponding adjustment coefficient can be determined based on the target vehicle's response delay time. The following control parameters included in the initial parameters can be adjusted using this adjustment coefficient to reduce the safety distance threshold. For example, if the original safety distance threshold is the distance at the current vehicle speed for 3 seconds, the safety distance threshold can be adjusted downward to the distance at the current vehicle speed for 2.5 seconds by determining the adjustment coefficient.

[0085] The embodiment of the present application does not specifically limit how to adjust the initial parameters according to the vehicle response characteristic relationship. The following is an example of an adjustment method, see A1-A3.

[0086] A1: Obtain the standard response characteristic relationship.

[0087] The standard response characteristic relationship indicates the response characteristic relationship of a vehicle based on the initial parameters. If the initial parameters are previously calibrated and applied to all vehicle types, the standard response characteristic relationship is used to quantify the response characteristics of a universal vehicle.

[0088] A2: Determine a first adjustment coefficient of the initial parameter based on a first difference between the vehicle response characteristic relationship and the standard response characteristic relationship.

[0089] The first difference is the difference between the target vehicle's vehicle response characteristic relationship and the standard response characteristic relationship. For example, for the response data of response delay time, the difference in the slope between the vehicle response characteristic relationship and the standard response characteristic relationship established by the linear regression model is the first difference.

[0090] The first adjustment coefficient is determined based on the first difference. The first difference between the vehicle response characteristic relationship and the standard response characteristic relationship is determined, thereby determining the difference between the target vehicle's response characteristics and the response characteristics corresponding to the initial parameters. The first adjustment coefficient is then determined with the goal of reducing the first difference.

[0091] A3: Adjust the initial parameters using the first adjustment coefficient to obtain the target parameters.

[0092] As an implementation manner, multiple iterative adjustments may be performed, that is, the first adjustment coefficient may be updated by continuously determining the first difference, so that the parameter continuously approaches the target of adapting to the vehicle response characteristic relationship of the target vehicle.

[0093] Thus, by adjusting the initial parameters according to the first difference between the vehicle response characteristic relationship and the standard response characteristic relationship, the response characteristics adapted by the initial parameters are closer to the response characteristics of the target vehicle during the adjustment process, thereby obtaining target parameters with higher accuracy.

[0094] In order to improve the accuracy of the parameters, before adjusting the initial parameters according to the vehicle response characteristics, the embodiment of the present application also provides two optimization methods for the initial parameters, which are described below respectively.

[0095] Optimization method 1: optimize the initial parameters based on weather data.

[0096] Weather data is data reflecting weather conditions, and may include weather conditions and a road friction coefficient corresponding to the current weather conditions.

[0097] By optimizing the initial parameters for different weather data, the initial parameters can be adapted to the road conditions indicated by the different weather data, thereby enabling the optimized initial parameters to adapt to various weather conditions during adaptive cruise control. The following example illustrates the optimization of initial parameters for target weather data.

[0098] Obtain target weather data, where the target weather data is weather data from among a plurality of weather data used to optimize and adjust initial parameters. Adjust the initial parameters based on a road friction coefficient indicated by the target weather data to obtain first optimized initial parameters, where the first optimized initial parameters are parameters obtained by optimizing and adjusting the initial parameters based on the weather data.

[0099] A higher road friction coefficient indicates a drier road and less likely the tires to slip. A lower road friction coefficient indicates a wetter road and more likely the tires to slip. This allows adaptive adjustment of initial parameters based on the road friction coefficient to meet the road conditions indicated by the target weather data. For example, taking the road friction coefficient range of 0-1 as an example, if the target weather data is {weather condition is heavy rain, road friction coefficient is 0.3}, then the cornering control parameters related to cornering speed can be adjusted based on the data table that corresponds to the road friction coefficient and safe cornering speed to reduce cornering speed. For another example, if the target weather data is {light snow, road friction coefficient is 0.1}, then in addition to adjusting the cornering control parameters, the following control parameters related to following distance can be adjusted based on the data table that corresponds to the road friction coefficient and safe following distance to increase the following distance.

[0100] After optimizing the initial parameters according to the target weather data to obtain the first optimized initial parameters, the first optimized initial parameters are adjusted according to the vehicle response characteristic relationship to obtain the target parameters of the target vehicle. The adjustment process refers to the process of adjusting the initial parameters in S104 and will not be repeated here.

[0101] Therefore, by optimizing and adjusting the initial parameters according to weather data, the first optimized initial parameters are obtained, and then a secondary adjustment is performed in combination with the vehicle response characteristics relationship, so that the target parameters can not only adapt to the response characteristics of the target vehicle, but also adapt to road conditions under different weather conditions, thereby improving the accuracy of the initial parameters and the safety of the adaptive cruise control process.

[0102] The second optimization method is to optimize the initial parameters according to the user's driving type.

[0103] Users are categorized into different driving types based on their driving behaviors. These types of drivers correspond to different driving behaviors, such as following distance, acceleration frequency, accelerator pedal opening, braking frequency, and brake pedal opening. For example, for driving types categorized as conservative, robust, and aggressive, aggressive users brake more frequently and follow closer, while conservative users brake less frequently and follow farther.

[0104] The following is an example of optimizing initial parameters based on the target driving type of the target user.

[0105] Obtaining a target driving type for a target user. The target driving type indicates the target user's driving behavior type and is one of multiple driving types used to optimize and adjust initial parameters. This embodiment of the present application does not specifically limit how the target driving type is obtained. For example, the target driving type can be statistically determined based on the target user's historical driving data or uploaded by the target user.

[0106] According to the target driving type, the initial parameters are adjusted to obtain second optimized initial parameters. The second optimized initial parameters are parameters obtained by optimizing and adjusting the initial parameters according to the target driving type.

[0107] Based on the driving behavior indicated by the target driving type, the adaptive cruise control parameters in the initial parameters related to that driving behavior are optimized and adjusted. The goal of this optimization process is to narrow the gap between the adaptive cruise control process using the initial parameters and the driving behavior indicated by the target driving type. For example, if an aggressive user's average accelerator pedal opening during acceleration is 40%, while the average accelerator pedal opening for mainstream users is 25%, the stop-and-follow control parameters related to acceleration can be adjusted to increase the acceleration threshold. Alternatively, if an aggressive user's following distance on urban roads is 3 meters, while the average following distance for mainstream users is 5 meters, the stop-and-follow control parameters related to following can be adjusted to reduce the following distance.

[0108] After optimizing the initial parameters according to the target driving type to obtain the second optimized initial parameters, the second optimized initial parameters are adjusted according to the vehicle response characteristic relationship to obtain the target parameters of the target vehicle. The adjustment process refers to the process of adjusting the initial parameters in S104 and is not repeated here.

[0109] Therefore, by optimizing and adjusting the initial parameters according to the target driving type of the target user, the second optimized initial parameters are obtained, and then a second adjustment is performed in combination with the vehicle response characteristics. This makes the target parameters not only adaptable to the response characteristics of the target vehicle, but also makes the adaptive cruise control process using the target parameters closer to the user's driving type, providing a more personalized driving experience.

[0110] After adjusting the initial parameters according to the vehicle response characteristic relationship to obtain the target parameters, the embodiment of the present application also provides an implementation method for further optimizing the target parameters through a machine learning algorithm.

[0111] A plurality of training parameters and a plurality of evaluation scores obtained by a target vehicle applying the training parameters during an adaptive cruise control process are obtained.

[0112] Training parameters are the adaptive cruise control parameters used to test the target vehicle. By applying multiple training parameters to the target vehicle, testers score the adaptive cruise control process corresponding to each training parameter. This results in a score based on testers' assessment of ride comfort, safety, responsiveness, and other factors. For example, if the system can smoothly follow the vehicle ahead without sudden braking, a higher score may be awarded; otherwise, a lower score may be awarded. During testing, various road conditions can be tested to obtain scores that are suitable for a wide range of road scenarios.

[0113] Based on multiple training parameters and multiple evaluation scores, the target parameters are optimized using machine learning algorithms to obtain optimized parameters. The machine learning algorithms include decision trees, random forests, support vector machines, neural networks, etc.

[0114] Specifically, multiple training parameters and corresponding multiple evaluation scores are used as training data for training a machine learning model. These are input into an initial machine learning model, and the model parameters of the initial machine learning model are adjusted with a training target close to the highest evaluation score to obtain a target machine learning model. By inputting the target parameters into the trained target machine learning model, optimized parameters that can obtain a higher evaluation score are obtained.

[0115] Therefore, by collecting the evaluation scores corresponding to different training parameters, the target machine learning model is obtained based on the machine learning algorithm training, and the correlation relationship between the evaluation scores and the training parameters is established through the model parameters of the target machine learning model, so as to obtain the optimized parameters that can obtain higher evaluation scores.

[0116] As can be seen from the above technical solution, the embodiment of the present application no longer applies a single parameter to multiple vehicles, but calibrates the parameters for vehicles with different response characteristics. Taking the target vehicle as an example, in response to receiving a control signal, the response data of the target vehicle is obtained, and the control signal is used to simulate multiple control use cases in the adaptive cruise control process. Based on the multiple control use cases and the response data corresponding to the multiple control use cases, a vehicle response characteristic relationship of the target vehicle is established. Initial parameters are obtained, and the initial parameters are adaptive cruise control parameters that have not yet been adjusted. The initial parameters are adjusted according to the vehicle response characteristic relationship to obtain the target parameters of the target vehicle. Therefore, by establishing the vehicle response characteristic relationship of the target vehicle and making targeted adjustments to the initial parameters according to the vehicle response characteristic relationship, target parameters that can adapt to the response characteristics of the target vehicle are obtained, thereby improving the accuracy of the parameters, so that when the target vehicle performs adaptive cruise control according to the target parameters, more precise control can be achieved, thereby improving safety.

[0117] See below Figure 4 and Figure 5 , an exemplary introduction is given to the parameter calibration method of the adaptive cruise control provided in an embodiment of the present application.

[0118] First, open-loop data acquisition is performed through the actuators and control system to obtain vehicle acceleration, braking, and suspension system data. This data is then preprocessed to remove noise and outliers to ensure data accuracy and reliability. Data analysis techniques, such as regression analysis and neural networks, are then used to establish a vehicle suspension system response characteristic model based on the suspension system data. Acceleration and vibration data are then used to generate a vehicle acceleration and deceleration response characteristic model. These two response characteristic models are combined to create a complete vehicle response characteristic model (vehicle response characteristic relationship) for the target vehicle. This complete vehicle response characteristic model is then validated and optimized. A machine learning algorithm is then used to adjust calibration parameters (including initial parameters for cruise control, following control, and cornering control) based on road conditions (road curvature, traffic flow), weather conditions (rainy and snowy data), and driver preferences (driving styles are categorized as conservative, robust, and aggressive). This results in target parameters that better reflect the target vehicle's response characteristics, reflecting road conditions, weather conditions, and driver preferences. These parameters are then applied to a real vehicle (the target vehicle), making the adaptive cruise control process more accurate and safer.

[0119] See also Figure 6 , Figure 6 The embodiment of the present application provides a parameter calibration device for adaptive cruise control, wherein the device 600 includes: an acquisition unit 601, a construction unit 602, and an adjustment unit 603:

[0120] The acquisition unit 601 is configured to acquire response data of the target vehicle in response to receiving a control signal, wherein the control signal is used to simulate multiple control use cases in an adaptive cruise control process;

[0121] The construction unit 602 is configured to establish a vehicle response characteristic relationship of the target vehicle based on the plurality of control use cases and the response data corresponding to the plurality of control use cases;

[0122] The acquisition unit 601 is further configured to acquire initial parameters, where the initial parameters are adaptive cruise control parameters that have not been adjusted.

[0123] The adjusting unit 603 is configured to adjust the initial parameters according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

[0124] As can be seen from the above technical solution, the present application no longer applies a single parameter to multiple vehicles, but rather calibrates parameters for vehicles with different response characteristics. Taking a target vehicle as an example, in response to receiving a control signal, an acquisition unit acquires response data of the target vehicle, and the control signal is used to simulate multiple control use cases during the adaptive cruise control process. A construction unit establishes a vehicle response characteristic relationship for the target vehicle based on the multiple control use cases and the response data corresponding to the multiple control use cases. The acquisition unit acquires initial parameters, which are adaptive cruise control parameters that have not yet been adjusted. The adjustment unit adjusts the initial parameters based on the vehicle response characteristic relationship to obtain target parameters for the target vehicle. Thus, by establishing the vehicle response characteristic relationship for the target vehicle and making targeted adjustments to the initial parameters based on the vehicle response characteristic relationship, target parameters that are adapted to the response characteristics of the target vehicle are obtained, thereby improving the accuracy of the parameters. This allows for more precise control and improved safety when the target vehicle performs adaptive cruise control based on the target parameters.

[0125] As a possible implementation manner, the adjustment unit is specifically configured to:

[0126] Acquiring a standard response characteristic relationship, where the standard response characteristic relationship is used to indicate a response characteristic relationship of the vehicle corresponding to the initial parameters;

[0127] determining a first adjustment coefficient of the initial parameter according to a first difference between the vehicle response characteristic relationship and the standard response characteristic relationship;

[0128] The initial parameter is adjusted using the first adjustment coefficient to obtain the target parameter.

[0129] As a possible implementation, the device further includes a suspension data acquisition unit, configured to:

[0130] Acquiring suspension system data of the target vehicle;

[0131] The building block is specifically used for:

[0132] A vehicle response characteristic relationship of the target vehicle is established based on the response characteristics of the target vehicle indicated by the suspension system data, the multiple control use cases, and the response data corresponding to the multiple control use cases.

[0133] As a possible implementation, the device further includes a secondary adjustment unit, configured to:

[0134] Acquiring a plurality of training parameters and a plurality of evaluation scores obtained by the target vehicle during the adaptive cruise control process by applying the training parameters;

[0135] According to the multiple training parameters and the multiple evaluation scores, the target parameters are optimized by a machine learning algorithm to obtain optimized parameters.

[0136] As a possible implementation, the construction unit is specifically used to:

[0137] Get the linear regression model;

[0138] The multiple control use cases and the response data respectively corresponding to the multiple control use cases are fitted by the linear regression model to obtain a vehicle response characteristic relationship of the target vehicle.

[0139] As a possible implementation, the method further includes:

[0140] Get target weather data;

[0141] Adjusting the initial parameters according to the road friction coefficient indicated by the target weather data to obtain first optimized initial parameters;

[0142] The first optimization initial parameters are adjusted according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

[0143] As a possible implementation, the device further includes a driving type calibration unit, configured to:

[0144] Acquire a target driving type of a target user, where the target driving type is used to indicate a driving behavior type of the target user;

[0145] Adjusting the initial parameters according to the target driving type to obtain second optimized initial parameters;

[0146] The second optimization initial parameters are adjusted according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

[0147] See also Figure 7 , an embodiment of the present application further provides a computer device, the computer device comprising a memory 701 and a processor 702:

[0148] The memory is used to store a computer program and transmit the computer program to the processor;

[0149] The processor is configured to execute the method of the above method embodiment according to the computer program.

[0150] An embodiment of the present application further provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method of the above method embodiment.

[0151] An embodiment of the present application further provides a computer program product including a computer program, which, when executed on a computer device, enables the computer device to execute the method of the above method embodiment.

[0152] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the systems or devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0153] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0154] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or plural.

[0155] It should also be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0156] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0157] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A parameter calibration method for adaptive cruise control, characterized in that: The method comprises: Acquiring response data of a target vehicle after receiving a control signal, wherein the control signal is used to simulate multiple control use cases during an adaptive cruise control process; establishing a vehicle response characteristic relationship of the target vehicle based on the plurality of control use cases and the response data respectively corresponding to the plurality of control use cases; Acquiring initial parameters, where the initial parameters are used to control an adaptive cruise control process of the target vehicle; The initial parameters are adjusted according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

2. The method according to claim 1, characterized in that The adjusting the initial parameters according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle includes: Acquiring a standard response characteristic relationship, where the standard response characteristic relationship is used to indicate a response characteristic relationship of the vehicle corresponding to the initial parameters; determining a first adjustment coefficient of the initial parameter according to a first difference between the vehicle response characteristic relationship and the standard response characteristic relationship; The initial parameter is adjusted using the first adjustment coefficient to obtain the target parameter.

3. The method according to claim 1, characterized in that The method further comprises: Acquiring suspension system data of the target vehicle; The establishing of a vehicle response characteristic relationship of the target vehicle based on the plurality of control use cases and the response data respectively corresponding to the plurality of control use cases includes: A vehicle response characteristic relationship of the target vehicle is established based on the response characteristics of the target vehicle indicated by the suspension system data, the multiple control use cases, and the response data corresponding to the multiple control use cases.

4. The method according to claim 1, wherein The method further comprises: Acquiring a plurality of training parameters and a plurality of evaluation scores obtained by the target vehicle during the adaptive cruise control process by applying the training parameters; According to the multiple training parameters and the multiple evaluation scores, the target parameters are optimized by a machine learning algorithm to obtain optimized parameters.

5. The method according to claim 1, wherein The establishing of a vehicle response characteristic relationship of the target vehicle based on the plurality of control use cases and the response data respectively corresponding to the plurality of control use cases includes: Get the linear regression model; The multiple control use cases and the response data respectively corresponding to the multiple control use cases are fitted by the linear regression model to obtain a vehicle response characteristic relationship of the target vehicle.

6. The method according to claim 1, characterized in that The method further comprises: Get target weather data; Adjusting the initial parameters according to the road friction coefficient indicated by the target weather data to obtain first optimized initial parameters; The first optimization initial parameters are adjusted according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

7. The method according to any one of claims 1 to 7, characterized in that The method further comprises: Acquire a target driving type of a target user, where the target driving type is used to indicate a driving behavior type of the target user; Adjusting the initial parameters according to the target driving type to obtain second optimized initial parameters; The second optimization initial parameters are adjusted according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

8. A parameter calibration device for adaptive cruise control, characterized in that: The device comprises an acquisition unit, a construction unit and an adjustment unit: The acquisition unit is configured to acquire response data of the target vehicle in response to receiving a control signal, wherein the control signal is used to simulate multiple control use cases in an adaptive cruise control process; The construction unit is configured to establish a vehicle response characteristic relationship of the target vehicle based on the plurality of control use cases and the response data respectively corresponding to the plurality of control use cases; The acquiring unit is further configured to acquire initial parameters, where the initial parameters are adaptive cruise control parameters that have not been adjusted; The adjustment unit is used to adjust the initial parameters according to the vehicle response characteristic relationship to obtain target parameters of the target vehicle.

9. A computer device, characterized in that: The computer device includes a processor and a memory: The memory is used to store a computer program and transmit the computer program to the processor; The processor is configured to execute the method according to any one of claims 1 to 7 according to the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method according to any one of claims 1 to 7.

Images