Pedal feel control method, computing device, vehicle, and readable storage medium

Abstract

The application discloses a pedal feeling control method, a computing device, a vehicle and a storage medium. The method comprises the following steps: obtaining character feature information of a current driver; matching a target pedal feeling strategy associated with the character feature information, wherein the target pedal feeling strategy is obtained by performing model training on brake control data corresponding to the character feature information according to a preset model; and responding according to the target pedal feeling strategy. In this way, after identifying the current driver, the pedal feeling strategy trained and output by the brake control data of the current driver is taken as the target pedal feeling strategy, the pedal feeling strategy configuration of the vehicle is completed, the current driver can more intuitively perceive the response state of the vehicle brake system based on the brake control habit of the current driver, and the brake degree is accurately controlled. Therefore, the pedal feeling strategy configuration of the vehicle can be completed to accurately match the brake control habit of the driver, and the purpose of improving the driving experience is achieved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method for controlling pedal feel, a computing device, a vehicle, and a computer-readable storage medium. Background Technology

[0002] Brake pedal feel (or simply pedal feel) has a significant impact on driving safety and handling performance. A good brake pedal feel allows the driver to more intuitively perceive the response of the vehicle's braking system, thereby precisely controlling the braking force. This "road feel" not only enhances the driver's grasp of the vehicle's dynamics but also helps the driver react quickly and correctly in emergencies, effectively shortening braking distance and significantly reducing the probability of traffic accidents. Furthermore, brake pedal feel improves the overall driving experience. It makes every braking operation predictable and controllable, reducing discomfort caused by sudden changes in braking force and making the driving process smoother and more fluid. This subtle feedback is particularly important at high speeds or in complex road conditions, helping the driver anticipate and adjust speed accordingly, avoiding unnecessary sudden braking, ensuring driving safety while also improving passenger comfort. In short, brake pedal feel is a crucial bridge connecting the driver and the vehicle; its quality directly affects driving safety, handling, and comfort. By optimizing the design and tuning of the braking system and improving the quality of the pedal feel, the overall performance of the vehicle can be further enhanced, providing the driver with a safer and more enjoyable driving experience. Currently, some vehicles come pre-installed with various brake pedal feel strategies to meet the different needs of different drivers for brake pedal feel.

[0003] However, the current factory-configured brake pedal feel strategies in vehicles are difficult to accurately match the individual braking habits of drivers, thus the driving experience needs improvement. Therefore, how to configure the vehicle's pedal feel strategy to accurately match the individual braking habits of drivers is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this application is to provide a method for controlling pedal feel, a computing device, a vehicle, and a computer-readable storage medium, which can realize the configuration of the vehicle's pedal feel strategy to accurately match the driver's personal braking habits and improve the driving experience.

[0005] To achieve the above objectives:

[0006] In a first aspect, embodiments of this application provide a method for controlling pedal feel, comprising: acquiring the current driver's personal characteristic information; matching a target pedal feel strategy associated with the personal characteristic information, wherein the target pedal feel strategy is obtained by training a preset model based on braking control data corresponding to the personal characteristic information; and responding according to the target pedal feel strategy.

[0007] In one embodiment, before the step of obtaining the current driver's personal characteristic information, the method includes: obtaining the driver's personal characteristic information in response to meeting the conditions for creating pedal feel; collecting braking control data of the driver driving the vehicle corresponding to the personal characteristic information according to a preset data acquisition strategy, and constructing at least one dataset, wherein the braking control data includes first correspondence information between deceleration and pedal force and / or second correspondence information between deceleration and pedal travel; training a preset model based on the braking control data in the dataset to output a pedal feel strategy, wherein the pedal feel strategy includes correspondence information between deceleration and pedal force and / or pedal travel; and storing the personal characteristic information in association with the pedal feel strategy.

[0008] In one embodiment, a preset data acquisition strategy includes: when the braking control state is determined to be a deep pedal press state, acquiring first braking control data at a preset sampling frequency; and when the braking control state is determined to be a light pedal press state, acquiring second braking control data at a preset sampling frequency; and constructing at least one dataset based on the acquired first and second braking control data.

[0009] In one embodiment, the pedal feel strategy includes at least one of the following: deceleration versus pedal force curve information that is suitable for fitting a fifth-order polynomial; and deceleration versus pedal travel curve information that is suitable for fitting a fifth-order polynomial.

[0010] In one embodiment, the conditions for creating pedal feel include at least one of the following:

[0011] Received preset command;

[0012] Based on the current driver's personal characteristics, the current driver is determined to be a new driver;

[0013] The system determines that the new driver has driven the vehicle more than the preset number of times.

[0014] The system determines that the new driver's cumulative driving time on the vehicle exceeds the preset time limit.

[0015] In one embodiment, after the step of responding according to the target pedal feel strategy, the method includes: detecting that the current driver has changed to a new driver, determining the attributes of the new driver; when the attribute determination result indicates a temporary user, determining a temporary pedal feel strategy from at least one preset universal pedal feel strategy; and responding according to the temporary pedal feel strategy.

[0016] In one embodiment, when the attribute determination result represents a temporary user, the step of determining a temporary pedal feel strategy from at least one preset universal pedal feel strategy includes: when the attribute determination result represents a temporary user, obtaining the temporary user's population attributes and the temporary user's driving data; determining the corresponding driving style based on the population attributes and driving data; and selecting a universal pedal feel strategy that matches the driving style from at least one preset universal pedal feel strategy as the temporary pedal feel strategy.

[0017] Secondly, embodiments of this application provide a computing device, including: a processor and a memory storing a computer program, wherein when the processor runs the computer program, the steps of the pedal feel control method as described in any of the preceding claims are implemented.

[0018] Thirdly, embodiments of this application provide a vehicle, and the vehicle includes the aforementioned computing device.

[0019] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the pedal feel control method as described in any of the preceding claims.

[0020] The pedal feel control method, computing device, vehicle, and computer-readable storage medium provided in this application embodiment include: acquiring the current driver's personal characteristic information; matching a target pedal feel strategy associated with the personal characteristic information, wherein the target pedal feel strategy is obtained by training a preset model based on braking control data corresponding to the personal characteristic information; and responding according to the target pedal feel strategy. This technical solution enables the vehicle's pedal feel strategy configuration by identifying the current driver and using the pedal feel strategy output from the model trained on the current driver's braking control data as the target pedal feel strategy. This allows the current driver to more intuitively perceive the response state of the vehicle's braking system (i.e., a good brake pedal feel) based on their own braking control habits, thereby accurately controlling the braking degree. This not only enhances the current driver's grasp of vehicle dynamics but also helps the current driver make a quick and correct reaction in emergency situations, effectively shortening the braking distance and significantly reducing the probability of traffic accidents. Therefore, this technical solution can complete the vehicle's pedal feel strategy configuration to accurately match the driver's personal braking control habits, achieving the goal of improving the driving experience. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0022] Figure 1 This is a flowchart illustrating the pedal feel control method provided in an embodiment of this application.

[0023] Figure 2 This is a schematic diagram of the flow framework of the pedal feel control method as an example of this application.

[0024] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of this application.

[0025] The realization of the objectives, functional features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and textual descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0026] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0027] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0028] It should be understood that although the terms first, second, third, etc., may be used herein to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this document, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if," as used herein, can be interpreted as "when," "when," or "in response to determination." Furthermore, as used herein, the singular forms "a," "an," and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising," "including," indicate the presence of the stated feature, step, operation, element, component, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or" and "and / or" as used herein are to be interpreted as inclusive, or mean any one or any combination thereof. Therefore, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A, B, and C". Exceptions to this definition will only occur if the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0029] It should be understood that although the steps in the flowcharts of this application's 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 of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0030] It should be noted that step designations such as S11 and S12 are used in this document for the purpose of more clearly and concisely describing the corresponding content, and do not constitute a substantial limitation on the order. In specific implementation, those skilled in the art may execute S12 first and then S11, etc., but these should all be within the protection scope of this application.

[0031] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0032] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0033] See Figure 1 This application provides a method for controlling pedal feel, which can be executed by a computing device provided in this application. The computing device can be implemented in software and / or hardware. Examples of computing devices include in-vehicle terminals and servers.

[0034] This embodiment provides a method for controlling pedal feel, including the following steps (e.g., steps S11 to S13):

[0035] Step S11: Obtain the current driver's character information.

[0036] In one implementation, the personal characteristic information can characterize the human features that can uniquely identify a specific person.

[0037] In one embodiment, the personal feature information includes facial information, iris information, and fingerprint information. Optionally, the facial information and iris information can be collected by a camera in the vehicle. Optionally, the fingerprint information can be collected by a fingerprint sensor in the vehicle.

[0038] In one implementation, the current driver can represent the person in the main cockpit of the vehicle.

[0039] In one embodiment, before obtaining the current driver's character information in step S11, the method may include: obtaining the driver's character information in response to meeting the conditions for creating pedal feel; collecting braking control data of the driver driving the vehicle corresponding to the character information according to a preset data collection strategy, and constructing at least one dataset, wherein the braking control data includes a first correspondence between deceleration and pedal force and / or a second correspondence between deceleration and pedal travel; training a preset model based on the braking control data in the dataset to output a pedal feel strategy, wherein the pedal feel strategy includes the correspondence information between deceleration and pedal force and / or pedal travel; and storing the character information and the pedal feel strategy in association.

[0040] Thus, the technical solution of this embodiment can determine the personal characteristics of a specific driver when creating a pedal sensing strategy, and collect braking operation data (first correspondence information between deceleration and pedal force and / or second correspondence information between deceleration and pedal travel) of the specific driver when pressing the brake pedal in a natural driving scenario of the specific driver. A dataset is constructed based on the collected braking operation data, and the data in the dataset is input into a preset model so that the preset model outputs a pedal sensing strategy (correspondence information between deceleration and pedal force and / or pedal travel) that matches the braking operation habits of the specific driver. The personal characteristics of the specific driver are associated with the pedal sensing strategy and stored for subsequent matching and retrieval.

[0041] It should be understood that braking control data includes, but is not limited to, the first correspondence between deceleration and pedal force and / or the second correspondence between deceleration and pedal travel. For example, it may also include a third correspondence between pedal force and vehicle braking system response speed, a fourth correspondence between pedal travel and vehicle braking system response speed, etc. Specifically, braking control data can characterize various parameters that can affect pedal feel, and / or the correspondence between various parameters.

[0042] In one embodiment, the deceleration in the braking control data can be detected by an acceleration sensor in the vehicle. The pedal force in the braking control data can be detected by a force sensor installed at the brake pedal. The pedal travel in the braking control data can be detected by a displacement sensor at the brake pedal.

[0043] In one implementation, the preset model may be, but is not limited to, a BP neural network model. For example, it may also be a support vector machine, a random forest, etc.

[0044] In one embodiment, the step of training a preset model based on braking control data in the dataset to output a pedal feel strategy may include: extracting features from the braking control data in the dataset to obtain feature parameters, including pedal travel, pedal force, and deceleration; and inputting the feature parameters into a BP neural network model for model training to output a pedal feel strategy.

[0045] In one embodiment, pedal travel can characterize the distance the brake travels from the moment the brake pedal is depressed until a certain amount of force is applied to the brake disc. The length of the pedal travel affects the sensitivity of the brakes and the driver's braking experience. A shorter travel results in a faster braking response, but too short a travel may lead to overly sensitive braking, affecting comfort; a longer travel results in a slower braking response, but may provide a more comfortable driving experience.

[0046] In one embodiment, pedal force can characterize the amount of resistance felt by the driver when pressing the brake pedal. This resistance is an important feedback from the driver to the vehicle's braking system, and it represents the following aspects: (1) Braking response: Pedal force can reflect the response speed of the braking system; if the pedal force is moderate and increases linearly with the pedal travel, it usually means that the braking system is responsive and can respond quickly to the driver's operation. (2) Braking force prediction: The size of the pedal force can help the driver predict the vehicle's braking force; in emergency braking or when precise control of braking force is required, this predictive ability is crucial for avoiding accidents. (3) Driving comfort: The size and variation of the pedal force affect driving comfort; if the pedal force is too small, it may cause the brake pedal to feel "soft," making the driver feel that the braking effect is poor; if the pedal force is too large, it may cause driver fatigue. (4) Safety: Appropriate pedal force helps ensure that the vehicle can provide reliable braking performance under various road conditions, thereby improving driving safety. (5) Correlation between subjective evaluation and objective data: Pedal force is the bridge between subjective evaluation of pedal feel and objective test data; by objectively measuring physical quantities such as pedal force and pedal travel, the driver's subjective feeling about pedal feel can be quantified. Therefore, pedal force is an important component of pedal feel, which not only affects the driving experience, but also directly relates to the vehicle's braking performance and driving safety.

[0047] In one embodiment, pedal travel, along with pedal force and deceleration, constitutes the evaluation dimension of pedal feel, which is an important factor affecting the driver's braking operation and the overall vehicle braking performance. The length of pedal travel directly affects the sensitivity and immediacy of the braking system. For example, a shorter initial pedal travel may result in a rapid braking response, but may also make the driver feel that the brakes are too sensitive; while a longer pedal travel may make the driver feel more comfortable, but may reduce the immediacy of braking.

[0048] In one embodiment, a pedal feel strategy can improve pedal feel, for example, by adjusting pedal travel to ensure both good braking performance and driving comfort and safety. Alternatively, the pedal travel can be adjusted, for example, by adjusting braking system parameters such as brake pedal leverage ratio and brake system free travel, thereby improving pedal feel.

[0049] In one embodiment, the pedal feel strategy output by the preset model can take into account the response speed of the braking system and the pedal force to ensure that appropriate braking performance can be provided under different driving conditions.

[0050] In one embodiment, the pedal feel strategy can characterize the specific parameters of adjusting pedal force and / or pedal travel based on the driver's depressing of the brake pedal.

[0051] In one embodiment, the pedal feel strategy is used to adjust the pedal force and / or pedal travel to suit the specific driver under different deceleration demands, so as to accurately adapt to the specific driver's braking habits. Optionally, when the vehicle responds according to the pedal feel strategy, it enables the specific driver to obtain a good pedal feel.

[0052] In one embodiment, pedal feel refers to the feedback force and sensation that a driver experiences when pressing the brake pedal. It can primarily include factors such as pedal force, pedal travel, and deceleration. A good pedal feel is crucial for driving safety because it helps the driver accurately judge the vehicle's braking force, thereby better controlling vehicle speed and distance and reducing the risk of accidents. Simultaneously, it can improve driving comfort and reduce driver fatigue during long drives. Pedal feel can be evaluated from multiple dimensions, including pedal force, pedal travel, pedal force and return hysteresis, vehicle braking system response speed, and vehicle deceleration. These factors work together to influence the driver's perception of the vehicle's braking performance. For example, the relationship between pedal travel and vehicle deceleration, the relationship between pedal force and vehicle deceleration, and the firmness or softness of the pedal are all important aspects of evaluating brake pedal feel.

[0053] In one embodiment, the pedal feel strategy can determine target parameters and optimize them based on these parameters and related components of the braking system. For example, existing pedal feel can be significantly improved by reducing the gap between the brake disc and brake pads, increasing the Young's modulus of the brake hose, and increasing the stiffness of the rubber reaction disc.

[0054] In one embodiment, the conditions for creating pedal feel include at least one of the following:

[0055] Received preset command;

[0056] Based on the current driver's personal characteristics, the current driver is determined to be a new driver;

[0057] The system determines that the new driver has driven the vehicle more than the preset number of times.

[0058] The system determines that the new driver's cumulative driving time on the vehicle exceeds the preset time limit.

[0059] In one implementation, the preset command may correspond to the pedal feel creation function.

[0060] In one embodiment, the preset command can be triggered by voice or by the vehicle's virtual function buttons, physical buttons, etc.

[0061] The technical solution of this embodiment can directly determine whether the pedal feel creation conditions are met when a preset instruction is received, or it can determine whether the pedal feel creation conditions are met by receiving the preset instruction and combining other conditions and factors (such as the current driver's driver attributes, the number of times the new driver has driven, the cumulative driving time of the new driver, etc.).

[0062] In one implementation, the current driver is determined to be a new driver based on the current driver's personal characteristics information. Specifically, if the current driver's personal characteristics information does not match the pre-stored personal characteristics information, then the current driver's driver attribute is determined to be a new driver.

[0063] In this embodiment, the technical solution can determine whether the pedal feel creation conditions are met directly when the current driver is a new driver. Alternatively, it can determine whether the pedal feel creation conditions are met by determining whether the current driver is a new driver and combining other conditions and factors (such as whether a preset instruction has been received, the number of times the new driver has driven, the cumulative driving time of the new driver, etc.).

[0064] In one implementation, the preset number of times can be set arbitrarily according to requirements.

[0065] The technical solution of this embodiment determines that if a new driver has driven the vehicle more than a preset number of times, the conditions for creating pedal feel can be directly met. Thus, this embodiment can configure a pedal feel strategy that matches the braking habits of a new driver when the driver drives the vehicle multiple times, thereby improving the driving experience. Alternatively, this embodiment can also determine whether the conditions for creating pedal feel are met by combining other factors (such as whether a preset instruction has been received, the new driver's cumulative driving time, etc.) when the number of times the driver has driven the vehicle exceeds a preset number of times.

[0066] In one embodiment, the preset duration can be set to any length as needed. Optionally, determining that the new driver's cumulative driving time exceeds the preset duration can indicate that the new driver has been using the vehicle for a relatively long time.

[0067] The technical solution of this embodiment determines that if a new driver's cumulative driving time exceeds a preset time, the conditions for creating pedal feel are directly met. Thus, this embodiment can configure a pedal feel strategy that matches the braking habits of a new driver when driving the vehicle for an extended period, thereby improving the driving experience. Alternatively, this embodiment can determine whether the conditions for creating pedal feel are met by combining other factors (such as whether a preset instruction has been received, the number of times the new driver has driven the vehicle, etc.) when the number of times the new driver has driven the vehicle exceeds a preset number.

[0068] It should be understood that when the pedal feel creation conditions are constructed based on multiple conditions and factors, it is possible to avoid accidental activation of the pedal feel creation process that would consume the vehicle's computing resources, and / or to more accurately grasp the triggering timing of the pedal feel creation process, so as to configure a pedal feel strategy that matches the braking operation habits of new drivers under appropriate circumstances, thereby improving the driving experience.

[0069] In one implementation, the preset data acquisition strategy can characterize the specific way of constructing a dataset that matches the training requirements of the preset model.

[0070] In one embodiment, the preset data acquisition strategy may include: when the braking control state is determined to be a deep pedal press, acquiring first braking control data at a preset sampling frequency; and when the braking control state is determined to be a light pedal press, acquiring second braking control data at a preset sampling frequency; and constructing at least one dataset based on the acquired first and second braking control data. Thus, the technical solution of this embodiment can monitor the driver's deep and light pedal press actions while driving the vehicle, and acquire first braking control data at a preset sampling frequency when a deep press action is detected, and acquire second braking control data at a preset sampling frequency when a light press action is detected. Furthermore, one or more datasets can be constructed based on the acquired first and second braking control data respectively, or a single dataset can be constructed based on both the acquired first and second braking control data.

[0071] The technical solution of this embodiment can generalize data using a BP neural network model and braking control data from both deep and light pedal applications to predict the driver's braking control data under various degrees of pedal application. This allows for the determination of the relationship between pedal travel and vehicle deceleration under various pedal application conditions, as well as the relationship between pedal force and vehicle deceleration under various pedal application conditions, ultimately yielding a pedal feel strategy. Thus, the technical solution of this embodiment can provide a pedal feel strategy adapted to the driver's individual braking habits, thereby enhancing the driving experience.

[0072] It should be understood that the first braking control data and the second braking control data can be referred to with reference to the aforementioned definition of braking control data. Here, the terms "first" and "second" are used to describe the braking control data only for the purpose of distinguishing them from each other. The first braking control data represents the braking control data corresponding to a deep pressing action, and the second braking control data represents the braking control data corresponding to a light pressing action.

[0073] In one embodiment, determining that the braking control state is a deep pedal press state or determining that a deep pressing action is detected includes, but is not limited to, at least one of the following: the current pedal travel reaches the limit value or maximum proportion of the pedal travel; the current pressing force on the brake pedal exceeds a first pressing force threshold.

[0074] In one embodiment, determining that the braking control state is a light pedal press state or determining that a light pressing action is detected includes, but is not limited to, at least one of the following: the current pedal travel reaches a preset pedal travel (the preset pedal travel is less than the limit value of the pedal travel); the travel ratio of the current pedal travel to the limit value of the pedal travel is less than or equal to a travel ratio threshold (e.g., 50%); the pressing force on the brake pedal is within a preset pressing force range, and the maximum value within the preset pressing force range is less than a first pressing force threshold.

[0075] In one embodiment, the limit value or maximum proportion of pedal travel, the first pedal force threshold, the preset pedal travel, the travel proportion threshold, and the preset pedal force range can be set according to actual needs or the vehicle's factory design.

[0076] In one embodiment, the preset sampling frequency can be set according to the required acquisition accuracy. Optionally, the determination of the data sampling frequency is usually based on the Nyquist theorem, which states that in order to reconstruct a continuous signal without distortion, the sampling frequency needs to be at least twice the highest frequency component of the signal.

[0077] In one embodiment, the preset sampling frequency can be set to the sampling frequency of devices commonly used in vehicles, thus avoiding some technical barriers. For example, since most devices in vehicles currently have a sampling frequency of 2000 Hz, the preset sampling frequency for collecting braking control data can also be set to 2000 Hz.

[0078] In one implementation, the preset sampling frequency can be configured based on experimental testing. Specifically, an excessively high preset sampling frequency will result in larger sample sizes, excessive memory usage, and correspondingly higher storage requirements.

[0079] In one embodiment, the step of constructing at least one dataset based on the collected first braking control data and second braking control data includes: summarizing and recording the collected first braking control data into at least one first dataset according to the dataset recording frequency; summarizing and recording the collected second braking control data into at least one second dataset according to the dataset recording frequency; and summarizing all the first datasets and all the second datasets into a final dataset in response to the data acquisition termination condition being met.

[0080] In one embodiment, the dataset recording frequency can characterize the frequency at which multiple braking control data are aggregated. For example, with a preset sampling frequency of 2000 Hz, the dataset recording frequency can be 50 Hz. Thus, the sampling frequency for braking control data is 2000 Hz, and one dataset is recorded every 50 Hz, allowing 40 datasets to be recorded per second. This setting can improve the acquisition accuracy and more effectively fit the data, while also better reflecting real driving conditions.

[0081] In one implementation, the data acquisition termination condition includes, but is not limited to, at least one of the following:

[0082] The first cumulative duration for collecting the first braking control data reaches the first duration threshold.

[0083] The second cumulative duration for collecting the second braking control data reaches the second duration threshold.

[0084] The first cumulative data volume of the first braking control data collected reaches the first quantity threshold;

[0085] The second cumulative data volume of the second braking control data collected reaches the second quantity threshold.

[0086] In one embodiment, the first duration threshold and the second duration threshold may be the same or different.

[0087] In one embodiment, the first quantity threshold and the second quantity threshold may be the same or different.

[0088] In one embodiment, the aforementioned data collection termination condition can characterize a limitation setting on the amount of data in the dataset used for model training.

[0089] The technical solution of this embodiment can achieve faster and more effective data fitting to output pedal feel strategy by setting an appropriate sampling frequency and an appropriate amount of data for model training, while ensuring the accuracy of data acquisition. It can also ensure that the output pedal feel strategy is more in line with the actual driving situation (e.g., braking habits) of the corresponding driver. As a result, when the vehicle completes the configuration or response according to the pedal feel strategy corresponding to a specific driver, it can improve the driving experience of that specific driver.

[0090] In one embodiment, the pedal feel strategy includes at least one of the following: deceleration versus pedal force curve information that is suitable for fitting a fifth-order polynomial; and deceleration versus pedal travel curve information that is suitable for fitting a fifth-order polynomial.

[0091] In one embodiment, a quintic polynomial is a mathematical model. The technical solution of this embodiment can well describe and simulate the shape of the pedal feel curve using a quintic polynomial. This polynomial contains six unknown coefficients (C0 to C5), and the values ​​of these coefficients can be determined by solving a set of equations. The equation set can be established based on the dynamic characteristics of the pedal feel curve under different decelerations, including the relationship between pedal force and deceleration, and / or the relationship between pedal travel and deceleration.

[0092] In one embodiment, the technical solution of this embodiment can characterize the relationship between deceleration and pedal force and the relationship between deceleration and pedal travel through different curve information, which has the following advantages: (1) Intuitiveness: The pedal force and pedal travel under different decelerations can be intuitively displayed through the curve characterizing the pedal feel, so that relevant personnel can quickly understand the performance of the braking system and facilitate vehicle maintenance or testing; (2) Comparison between simulation and actual vehicle test: When the simulation results of the whole vehicle braking system model established by simulation software such as SimulationX are compared with the actual test results, the accuracy of verification and comparison can be improved based on the pedal feel curve.

[0093] In one embodiment, the step of associating driver characteristic information with pedal feel strategy may include: associating driver characteristic information with pedal feel strategy to obtain pedal feel association information; storing the pedal feel association information in the vehicle; and / or sending the pedal feel association information to a cloud server so that the cloud server stores the pedal feel association information. This embodiment's technical solution not only enables the vehicle to subsequently determine the target pedal feel strategy based on the current driver's characteristic information from the pedal feel association information stored within it, but also enables the vehicle to subsequently determine the target pedal feel strategy based on the current driver's characteristic information from the pedal feel association information stored in the cloud. Sending the pedal feel association information to the cloud server so that the cloud server stores the pedal feel association information avoids occupying the vehicle's storage space, and also allows the driver corresponding to the pedal feel association information to configure or respond based on the target pedal feel strategy obtained from the cloud server, regardless of whether the vehicle is changed or a different vehicle of the same model.

[0094] Step S12: Match the target pedal feel strategy associated with the character feature information. The target pedal feel strategy is obtained by training the preset model based on the braking control data corresponding to the character feature information.

[0095] In one embodiment, step S12: matching the target pedal feel strategy associated with the person's characteristic information may include: matching the target pedal feel strategy associated with the person's characteristic information based on the pedal feel association information and the person's characteristic information stored in the vehicle and / or cloud server.

[0096] Step S13: Respond according to the target pedal feel strategy.

[0097] In one embodiment, step S13, after responding according to the target pedal feel strategy, may include: detecting that the current driver has changed to a new driver, determining the attributes of the new driver; when the attribute determination result indicates a temporary user, determining a temporary pedal feel strategy from at least one preset universal pedal feel strategy; and responding according to the temporary pedal feel strategy. Thus, the technical solution of this embodiment can provide a quick configuration function for pedal feel strategies when the driver of the vehicle changes from the owner or an authorized person to another temporary user, enabling the temporary user to select a universal pedal feel strategy for temporary configuration, thereby improving the driving experience of the temporary user.

[0098] In one embodiment, detecting a change from the current driver to a new driver and determining the new driver's attributes may include: obtaining the current driver's current character feature information; determining that the current driver has changed to a new driver if the current character feature information differs from the historical character feature information stored in the vehicle at the last power-on time; obtaining the new driver's vehicle usage information, which includes at least one of the following: the number of times the vehicle has been driven and the cumulative driving time; determining whether the vehicle usage information meets the conditions for temporary vehicle use; if so, determining the current driver's character attribute as a temporary user; if not, triggering the pedal feel creation function based on the current character feature information.

[0099] In one embodiment, the temporary vehicle use conditions include, but are not limited to, at least one of the following:

[0100] The new driver is determined to have driven the vehicle less than or equal to a preset number of times.

[0101] The system determines that the new driver's cumulative driving time is less than or equal to the preset time.

[0102] In one embodiment, the universal pedal feel strategy can be a brake pedal feel strategy determined based on big data and associated with population attributes. Alternatively, the universal pedal feel strategy can be a factory-preset pedal feel strategy.

[0103] In one implementation, the universal pedal feel strategy is universal or general, and any driver can select and associate it.

[0104] In one embodiment, when the attribute determination result represents a temporary user, the step of determining a temporary pedal feel strategy from at least one preset universal pedal feel strategy may include: when the attribute determination result represents a temporary user, obtaining the temporary user's population attributes and the temporary user's driving data; determining the corresponding driving style based on the population attributes and driving data; and selecting a universal pedal feel strategy that matches the driving style from at least one preset universal pedal feel strategy as the temporary pedal feel strategy.

[0105] The technical solution of this embodiment can quickly predict the driving style of temporary users based on their demographic attributes and driving data. This allows for the rapid selection and recommendation of a suitable temporary pedal feel strategy from at least one preset universal pedal feel strategy, enabling temporary users to quickly choose a universal pedal feel strategy for temporary configuration and improving their driving experience.

[0106] In one embodiment, the driving data includes at least one of braking intensity, braking frequency, instantaneous vehicle speed, etc.

[0107] In one implementation, the population attribute can represent various attribute tags for a person, including but not limited to gender tags, age tags, etc.

[0108] In one embodiment, the crowd attributes can be automatically determined by collecting image information of temporary users through a camera and performing image recognition, or they can be set automatically in response to user settings.

[0109] In one implementation, the driving style includes one of the following: leisurely driving, normal driving, aggressive driving, etc.

[0110] This embodiment provides a method for controlling pedal feel, including: Step S11: acquiring the current driver's characteristic information; Step S12: matching a target pedal feel strategy associated with the characteristic information, wherein the target pedal feel strategy is obtained by training a preset model based on braking control data corresponding to the characteristic information; Step S13: responding according to the target pedal feel strategy. This embodiment's technical solution, after identifying the current driver, uses the pedal feel strategy output from the model trained on the current driver's braking control data as the target pedal feel strategy, completing the vehicle's pedal feel strategy configuration. This allows the current driver to more intuitively perceive the vehicle's braking system response state (i.e., a good brake pedal feel) based on their own braking habits, thereby accurately controlling the braking degree. This not only enhances the current driver's grasp of vehicle dynamics but also helps the current driver make a quick and correct reaction in emergency situations, effectively shortening the braking distance and significantly reducing the probability of traffic accidents. Therefore, this embodiment's technical solution can complete the vehicle's pedal feel strategy configuration to accurately match the driver's personal braking habits, achieving the goal of improving the driving experience.

[0111] Based on the same inventive concept as the foregoing embodiments, the following example illustrates a specific application scenario of the pedal feel control method to provide a detailed description of the foregoing embodiments:

[0112] This example demonstrates how a BP neural network model can be used to memorize training data and output a pedal feel strategy that conforms to the memory model.

[0113] See Figure 2 The specific implementation method in this example is as follows:

[0114] (1) When the camera recognizes the driver, it will collect the driver's information (i.e., personal feature information) and store it in the vehicle's storage chip. For example, after the cockpit camera recognizes person A, it will send person A to the vehicle's storage chip for storage.

[0115] (2) Based on the current driver's braking control data when pressing the brake pedal deeply and lightly, the braking control data includes the relationship between deceleration and pedal force and the relationship between deceleration and pedal travel.

[0116] The data sampling frequency is 2000Hz, with one dataset recorded every 50Hz, and 40 datasets can be recorded per second.

[0117] (3) Train the BP neural network model based on the currently sampled dataset. Specifically, the input parameters of the BP neural network model are: deceleration, pedal force, and pedal travel. The output of the BP neural network model is the pedal feel curve (i.e., the pedal feel strategy), which is fitted using a fifth-order polynomial to fit the pedal feel that matches the current driver's driving style (i.e., braking habits). This pedal feel is then associated with the current driver's information and recorded in the vehicle's storage chip. When the driver presses the brake pedal again or when the vehicle is identified as being driven by the same driver, the vehicle will automatically switch to a pedal feel that matches the driver's style.

[0118] For example, a pedal feel sensor monitors the brake pedal in real time. The sensor data is sampled at a frequency of 2000Hz to record the relationship between deceleration and pedal force, as well as the relationship between deceleration and pedal travel. This data is then used to build a dataset, which is imported into a backpropagation (BP) neural network model. The model is trained on this dataset to obtain the relevant data, and then fitted using a fifth-order polynomial to generate the pedal feel curve. This curve is stored as a pedal feel pattern A and associated with the driver's image A in the vehicle's storage chip. Subsequently, when the driver corresponding to image A is driving the vehicle, they can retrieve pedal feel pattern A from the vehicle's storage chip to control the brake pedal's output.

[0119] This example requires a pedal feel sensor with a sampling frequency of 2000Hz and an in-cabin camera with high-precision recognition capabilities, which can collect facial feature points of the driver to form stored data (driver information) and memorize it.

[0120] The technical solution in this example, based on existing pedal feel switching strategies, can create new pedal feel strategies in real time using a BP neural network model and a memory model for the current driver. The created pedal feel strategy allows the driver to more intuitively perceive the response state of the vehicle's braking system, thereby precisely controlling the braking force. This not only enhances the driver's control over vehicle dynamics but also helps the driver react quickly and correctly in emergencies, effectively shortening braking distance and significantly reducing the probability of traffic accidents. Furthermore, pedal feel improves the overall driving experience, especially at high speeds or in complex road conditions, helping the driver anticipate and adjust speed accordingly, ensuring driving safety while also improving passenger comfort.

[0121] The technical solution in this example can combine a BP neural network model, integrate cockpit camera data, pedal feel data (brake control data) collection, organize and fit the output, create a new pedal feel curve, and automatically store it in the vehicle's in-vehicle storage chip to match the braking control habits of a specific driver.

[0122] Based on the same inventive concept as the foregoing embodiments, this application provides a computing device, such as... Figure 3 As shown, the device includes: a processor 310 and a memory 311 storing a computer program; wherein, Figure 3 The processor 310 shown in the diagram does not indicate that there is only one processor 310, but only indicates the positional relationship of the processor 310 relative to other devices. In practical applications, there can be one or more processors 310; similarly, Figure 3 The memory 311 shown in the diagram has the same meaning, that is, it is only used to indicate the positional relationship of memory 311 relative to other devices. In practical applications, there can be one or more memories 311. When the processor 310 runs the computer program, it implements a control method for the pedal feel applied to the above-mentioned device.

[0123] The device may also include at least one network interface 312. The various components of the device are coupled together via a bus system 313. It is understood that the bus system 313 is used to implement communication between these components. In addition to a data bus, the bus system 313 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 3 The general designated all buses as Bus System 313.

[0124] The memory 311 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 311 described in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0125] The memory 311 in this embodiment is used to store various types of data to support the operation of the device. Examples of this data include any computer programs used to operate on the device, such as operating systems and applications. The operating system includes various system programs, such as framework layers, core library layers, and driver layers, used to implement various basic business functions and handle hardware-based tasks. Applications can include various applications, such as media players and browsers, used to implement various application services. Here, the program implementing the method of this embodiment can be included in the application.

[0126] Based on the same inventive concept as the foregoing embodiments, this embodiment also provides a computer-readable storage medium storing a computer program. The computer-readable storage medium can be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM), etc.; it can also be various devices including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc. When the computer program stored in the computer-readable storage medium is run by a processor, it implements the above method. For the specific steps implemented when the computer program is executed by the processor, please refer to [link to relevant documentation]. Figure 1 The description of the illustrated embodiments will not be repeated here.

[0127] 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.

[0128] In this document, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, which includes not only the elements listed but also other elements not expressly listed.

[0129] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for controlling pedal feel, characterized in that, include: Obtain the current driver's personal characteristics information; Matching a target pedal feel strategy associated with the character feature information, wherein the target pedal feel strategy is obtained by training a preset model based on the braking control data corresponding to the character feature information. Respond according to the target pedal feel strategy; Prior to the step of obtaining the current driver's personal characteristic information, the method includes: in response to meeting the conditions for creating pedal feel, training the preset model based on the obtained personal characteristic information of the driver and the braking control data when driving the vehicle, so as to output a pedal feel strategy associated with the personal characteristic information. The conditions for creating pedal feel include at least one of the following: Received preset command; Based on the current driver's personal characteristics, the current driver is determined to be a new driver; It is determined that the new driver has driven the vehicle more than a preset number of times; It is determined that the new driver's cumulative driving time in the vehicle exceeds a preset time.

2. The method according to claim 1, characterized in that, The step of responding to the condition for creating pedal feel by training the preset model based on the acquired driver's characteristic information and braking control data while driving the vehicle, and outputting a pedal feel strategy associated with the driver's characteristic information, includes: In response to meeting the conditions for creating pedal feel, the driver's personal characteristic information is obtained; According to the preset data acquisition strategy, the braking control data of the driver driving the vehicle corresponding to the person's characteristic information is collected, and at least one dataset is constructed. The braking control data includes a first correspondence information between deceleration and pedal force and / or a second correspondence information between deceleration and pedal travel. The preset model is trained based on the braking control data in the dataset to output a pedal feel strategy, which includes information on the correspondence between deceleration and pedal force and / or pedal travel. The character feature information is associated with and stored in relation to the pedal feel strategy.

3. The method according to claim 2, characterized in that, The preset data acquisition strategy includes: When the braking control state is determined to be a deep pedal press, the first braking control data at this time is collected according to the preset sampling frequency; and when the braking control state is determined to be a light pedal press, the second braking control data at this time is collected according to the preset sampling frequency. Based on the collected first braking control data and second braking control data, at least one of the datasets is constructed.

4. The method according to claim 2, characterized in that, The pedal feel strategy includes at least one of the following: The deceleration versus pedal force curve information is useful for fitting a fifth-order polynomial; The deceleration versus pedal travel curve information is useful for fitting a fifth-order polynomial.

5. The method according to any one of claims 1 to 4, characterized in that, After the step of responding according to the target pedal feel strategy, the following is included: Upon detecting that the current driver has been changed to a new driver, the attributes of the new driver are determined. When the attribute determination result represents a temporary user, a temporary pedal feel strategy is determined from at least one preset universal pedal feel strategy. Respond according to the temporary pedal feel strategy.

6. The method according to claim 5, characterized in that, The step of determining a temporary pedal feel strategy from at least one preset universal pedal feel strategy when the attribute determination result characterizes a temporary user includes: When the attribute determination result represents the temporary user, the population attribute of the temporary user and the driving data of the temporary user when driving the vehicle are obtained; Based on the aforementioned demographic attributes and driving data, a corresponding driving style is determined; Select the universal pedal feel strategy that matches the driving style from at least one preset universal pedal feel strategy to serve as the temporary pedal feel strategy.

7. A computing device, characterized in that, include: The processor and the memory storing a computer program implement the steps of the pedal feel control method according to any one of claims 1 to 6 when the processor runs the computer program.

8. A vehicle, characterized in that, The vehicle includes the computing device as described in claim 7.

9. A computer-readable storage medium, characterized in that, The device contains a computer program that, when executed by a processor, implements the steps of the pedal feel control method according to any one of claims 1 to 6.

Images