Scene adaptive calibration method, device and equipment of brake pedal feeling and medium

Abstract

The present application mainly relates to the technical field of automobile engineering. The present application discloses a brake pedal feeling scene adaptive calibration method, device, equipment and medium. The method comprises the following steps: obtaining target vehicle operation data, and extracting a plurality of characteristic factors of quantified pedal feeling characteristics; identifying a braking scene according to a current state of the vehicle; determining scene adaptation weights of the characteristic factors based on the braking scene and personalized preferences of a driver; identifying coupling relationships among the characteristic factors and generating a coupling inhibition matrix; performing decoupling transformation on the weighted characteristic factors to obtain a decoupled characteristic factor vector; converting the decoupled characteristic factor vector into execution parameters of a pedal feeling simulation device through a preset mapping model, and controlling the pedal feeling simulation device to operate according to the execution parameters. The present application can realize scene adaptation and personalized dynamic output of brake pedal feeling according to user preferences and real-time dynamic states of the vehicle.

Description

Technical Field

[0001] This invention relates to the field of automotive engineering technology, specifically to a method, apparatus, device, and medium for scene-adaptive tuning of brake pedal feel. Background Technology

[0002] With the development of automotive electrification and intelligence, electromechanical braking systems (EMB systems) have gradually become an important technological direction in the field of brake-by-wire due to their advantages such as fast response, simple structure, and ease of integration. Unlike traditional hydraulic braking systems, EMB pedal assemblies eliminate the master cylinder and booster, using a motor to directly drive the brake actuator. This means that there is no longer a fixed mechanical or hydraulic coupling relationship between pedal force, pedal travel, and braking pressure. The pedal feel of EMB is entirely defined by the control algorithm. By adjusting programmable parameters such as motor torque, transmission damping, and travel feedback, designers can freely shape the relationship between pedal force and displacement. This provides a theoretical possibility for the diversified design of brake pedal feel.

[0003] However, current mainstream EMB pedal feel tuning methods still follow the static calibration approach of traditional hydraulic braking systems. Specifically, engineers pre-set one or more fixed pedal force and displacement characteristic curves, such as linear, comfort, or sport curves, and embed these curves in the controller. Users can only switch between these curves using a limited set of driving mode options, such as Eco, Comfort, or Sport. Once selected, the corresponding pedal feel remains unchanged throughout the driving process. This static tuning logic of fixed parameters corresponding to fixed pedal feel has two fundamental limitations: First, it cannot adapt to the subjective preferences of different drivers. Different users have different preferences for the firmness, travel length, and initial free travel of the brake pedal, and static curves cannot meet diverse individual needs. Second, it cannot adjust the pedal feel in real time according to the vehicle's dynamic state. The vehicle's dynamic state includes current speed, load, road surface adhesion coefficient, and specific braking conditions. The ideal pedal force and travel relationship should differ between emergency braking and gradual deceleration, between unloaded and fully loaded conditions, and between dry and low-traction roads. However, static tuning logic lacks the ability to respond to such changes in scenarios. Therefore, existing technology fails to fully utilize the programmable control potential offered by the EMB system, cannot achieve adaptive adjustment of pedal feel to user subjective preferences and vehicle dynamics, and cannot support personalized dynamic tuning. Summary of the Invention

[0004] This invention provides a method, device, equipment, and medium for scene-adaptive tuning of brake pedal feel, which enables scene-adaptive and personalized dynamic output of brake pedal feel based on user subjective preferences and real-time vehicle dynamic status.

[0005] This invention provides a scene-adaptive tuning method for brake pedal feel, the method comprising: Acquire the operating data of the target vehicle, and extract multiple feature factors from the operating data to quantify the pedal feel characteristics; Identify the braking scenario currently in which the target vehicle is located based on the current state information of the target vehicle; Based on the braking scenario and the driver's personalized preference settings, determine the scenario adaptation weight corresponding to each feature factor; Based on the braking scenario, identify the coupling relationship between each feature factor and the target feature factor, and generate a coupling suppression matrix; The coupling suppression matrix is ​​used to decouple the feature factors after setting the scene adaptation weights to obtain the decoupled feature factor vector. Each of the decoupled feature factor vectors is transformed into execution parameters of the pedal feel simulation device through a preset mapping model; The pedal feel simulation device is controlled to operate according to the execution parameters to generate pedal feel.

[0006] Optionally, the scene-adaptive tuning method for brake pedal feel further includes: Obtain the pedal reaction force and pedal travel output by the pedal feel simulation device; Based on the pedal reaction force and the pedal travel, a relationship curve between the reaction force and the travel is determined, and the actual characteristic factor value is identified according to the relationship curve. The actual feature factor value is compared with the feature factor value of the set scene adaptation weight to obtain the feature factor deviation; The execution parameters output by the preset mapping model are adjusted using an iterative learning control algorithm until the deviation of the characteristic factor converges to a preset threshold range.

[0007] Optionally, the scene-adaptive tuning method for brake pedal feel further includes: Obtain the pedal feel preference parameters defined in the personalized preference settings; The values ​​of the feature factors of the set scenario adaptation weight are matched with the pedal feel preference parameters to generate an evaluation index for quantifying the degree of matching. The evaluation index is displayed through the in-vehicle interactive interface and fed back to the preset mapping model as a basis for adjusting the execution parameters.

[0008] Optionally, determining the scene adaptation weight corresponding to each feature factor based on the braking scenario and the driver's personalized preference settings includes: Obtain the basic weight matrix corresponding to the current driving mode from the personalized preference settings, wherein the basic weight matrix includes the basic weight value of each feature factor; The dynamic correction coefficient is determined based on the current state information of the target vehicle; The target base weight values ​​in the base weight matrix are adjusted using the dynamic correction coefficient to generate the final weight matrix, and each weight value in the final weight matrix is ​​used as the scene adaptation weight corresponding to the target feature factor.

[0009] Optionally, the step of converting each of the decoupled feature factor vectors into execution parameters of the pedal feel simulation device through a preset mapping model includes: The decoupled feature factor vector is input into a pre-trained neural network model; The execution parameters output by the neural network model are obtained, and the execution parameters include at least a motor torque command for controlling the pedal reaction force and a motor position command for controlling the pedal travel.

[0010] Optionally, among the plurality of characteristic factors, at least a linear characteristic factor, a response characteristic factor, and a no-run characteristic factor are included; The step of converting each decoupled feature factor vector into execution parameters of the pedal feel simulation device through a preset mapping model further includes: Obtain the basic torque value, basic damping value, and basic stroke value of the pedal feel simulation device; The torque factor is obtained by performing a positive relationship calculation between the linear characteristic factor that sets the scene adaptation weight and the corresponding scene adaptation weight, and the target torque command of the motor is generated by adjusting the basic torque value using the torque factor. The damping factor is obtained by performing an inverse relationship calculation between the response characteristic factor with the set scene adaptation weight and the corresponding scene adaptation weight, and the transmission damping command is generated by adjusting the basic damping value using the damping factor. The travel limit factor is obtained by performing a positive relationship calculation between the empty travel characteristic factor with the set scene adaptation weight and the corresponding scene adaptation weight. The travel limit factor is then used to adjust the basic travel value to generate an effective travel limit command.

[0011] Optionally, when the feature factor is a linear characteristic factor, the step of obtaining the linear characteristic factor includes: Multiple discrete data points are collected within the effective travel range of the pedal, and each data point corresponds to a travel position and actual pedal force. All the data points are fitted using the least squares method to obtain an ideal linear curve, wherein the ideal linear curve represents the expected relationship between pedal force and travel under ideal linear foot feel; Calculate the absolute value of the deviation between the actual pedal force at each data point and the ideal pedal force at the corresponding stroke on the ideal linear curve, and calculate the average ratio between the absolute value of the deviation and the maximum pedal force as the average deviation degree. The difference between the preset unit value and the average deviation is used as the linear characteristic factor, wherein the linear characteristic factor is positively correlated with the linearity characterizing the pedal feel.

[0012] The present invention also provides a scene-adaptive adjustment device for brake pedal feel, the device comprising: An extraction module is used to acquire the operating data of the target vehicle and extract multiple feature factors from the operating data to quantify the pedal feel characteristics. The identification module is used to identify the braking scenario currently in which the target vehicle is located based on the current state information of the target vehicle; The calculation module is used to determine the scene adaptation weight corresponding to each feature factor based on the braking scenario and the driver's personalized preference settings. The generation module is used to identify the coupling relationship between each feature factor and the target feature factor based on the braking scene, and to generate a coupling suppression matrix; The decoupling module is used to perform a decoupling transformation on the feature factors after setting scene adaptation weights using the coupling suppression matrix, so as to obtain the decoupled feature factor vector. The conversion module is used to convert each of the decoupled feature factor vectors into execution parameters of the pedal sensation simulation device through a preset mapping model. The control module is used to control the pedal feel simulation device to operate according to the execution parameters to generate pedal feel.

[0013] The present invention also provides an electronic device, the electronic device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the scene adaptive adjustment method for brake pedal feel as described in any of the preceding claims.

[0014] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the scene-adaptive tuning method for brake pedal feel as described in any of the preceding claims.

[0015] The present invention has at least the following beneficial effects: First, this technical solution retains the original scene recognition and weight allocation capabilities. The system identifies braking scenarios based on real-time conditions such as vehicle speed and load, and determines the basic weights of each feature factor based on the user's driving mode and personalized preferences. This provides the first layer of adaptation for personalized dynamic output. Second, the decoupling step solves the inherent coupling problem between feature factors. In different scenarios, factors such as idle travel and linearity, response and limits have mutual constraints. Without processing, changes in the weight of one factor will distort the actual expression of another factor, causing the final pedal feel to deviate from the user's expectations. By generating a coupling suppression matrix and decoupling the weighted feature vectors, the system can eliminate redundant interference between factors, allowing the independent contribution of each factor to be accurately reflected. Finally, the decoupled feature vectors are input into the mapping model and transformed into execution parameters such as motor torque, damping, and travel limits. Because the decoupling step makes the input signal purer and the physical meaning clearer, the mapping model can more accurately match user preferences with scenario requirements. The final pedal feel achieves scene adaptation while avoiding personalized deviations caused by factor coupling, thus achieving a realistic and stable personalized dynamic output effect. Attached Figure Description

[0016] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0017] Figure 1 This is a flowchart illustrating the steps of a scene-adaptive tuning method for brake pedal feel; Figure 2 This is a flowchart of step S103 in a scene-adaptive tuning method for brake pedal feel; Figure 3 This is a flowchart of the steps for obtaining the linear characteristic factor in a scene-adaptive tuning method for brake pedal feel; Figure 4 This is a schematic diagram of a scene-adaptive adjustment device for brake pedal feel; Figure 5 This is a schematic diagram of the structure of an electronic device. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0019] The researchers of this application discovered that with the development of electric vehicles and autonomous driving technology, braking systems are evolving towards lightweighting and intelligence. Electromechanical braking systems (EMBs), as a novel technology, employ a unique configuration distinct from current electro-hydraulic and purely mechanical braking systems. The brake pedal used in these systems has also shifted from a traditional mechanical brake pedal to an electromechanical brake pedal. Currently, brake pedal feel evaluation methods on the market are mainly divided into two categories: objective index quantification and a combination of subjective scoring. The core objective is to determine whether the pedal feel meets design standards. Although existing technologies have achieved an initial leap from mechanical hard tuning to software soft tuning, significant shortcomings remain in adapting to the programmable characteristics of EMBs, meeting all operating condition requirements, and catering to user personalization preferences. These core issues can be summarized into the following four categories: (1) The static scene adaptation makes it difficult to cover the needs of all working conditions. The tuning logic of the existing technology is essentially "fixed parameters corresponding to fixed scenes", without considering the differences in the requirements of the vehicle's dynamic state for pedal feel, resulting in insufficient adaptability under all working conditions.

[0020] (2) Insufficient quantification of subjective needs and lack of personalized adaptation capabilities. The "pedal feel" is essentially a subjective feeling of the user, but existing technologies cannot accurately convert vague needs such as "linear, solid, and sensitive" into calculable control parameters.

[0021] (3) The evaluation and execution are disconnected, resulting in low efficiency in calibration implementation. In the existing technology, "pedal feel evaluation" and "EMB execution parameter control" are two independent links with no direct connection, which leads to long calibration cycles and low accuracy.

[0022] (4) Lack of a closed-loop iterative mechanism, making it impossible to continuously optimize calibration accuracy. Existing technologies mostly perform one-time calibrations, with parameters fixed after completion, making it impossible to dynamically optimize based on actual driving data and user feedback.

[0023] To address the aforementioned technical problems, this technical solution provides a method, apparatus, device, and medium for scene-adaptive tuning of brake pedal feel, enabling scene-adaptive and personalized dynamic output of brake pedal feel based on user subjective preferences and the real-time dynamic state of the vehicle. The following are various embodiments of this technical solution.

[0024] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating the steps of a scene-adaptive tuning method for brake pedal feel.

[0025] This embodiment provides a scene-adaptive adjustment method for brake pedal feel, including: S101. Obtain the operating data of the target vehicle and extract multiple feature factors from the operating data to quantify the pedal feel characteristics.

[0026] S102. Identify the braking scenario of the target vehicle based on its current status information.

[0027] S103. Based on the braking scenario and the driver's personalized preference settings, determine the scenario adaptation weight corresponding to each feature factor.

[0028] S104. Identify the coupling relationship between each feature factor and the target feature factor based on the braking scenario, and generate a coupling suppression matrix; S105. Use the coupling suppression matrix to decouple the feature factors after setting the scene adaptation weights to obtain the decoupled feature factor vector. S106. Transform each decoupled feature factor vector into the execution parameters of the pedal sensation simulation device through a preset mapping model. S107. Control the pedal feel simulation device to generate pedal feel according to the execution parameters.

[0029] In this embodiment, the operational data includes three specific parameters: pedal force, pedal travel, and pedal speed. The pedal force, measured in Newtons (N), is collected by a force sensor embedded in the pedal and primarily reflects the user's pedaling intensity and correlates with feedback force requirements. The pedal travel, measured in millimeters (mm), is collected by a pedal displacement sensor and used to determine the pedal's current stage, such as idle travel, effective travel, or maximum travel. The pedal speed, measured in millimeters per second (mm / s), is obtained by taking the first derivative of the pedal travel time and is used to identify whether the user's pedaling intention is light or rapid.

[0030] In this embodiment, the status information includes four specific parameters: vehicle speed, braking deceleration, vehicle load, and road surface adhesion coefficient. Vehicle speed, measured in kilometers per hour, is acquired via the vehicle's CAN bus and its core function is to adapt to different pedal feel requirements in high-speed or low-speed scenarios. Braking deceleration, measured in meters per square second, is collected by the vehicle's acceleration sensor and is used to correlate pedal force with braking effect. Vehicle load, measured in kilograms, is estimated by the suspension pressure sensor and is used to correct the pedal force threshold during extreme braking. The road surface adhesion coefficient is estimated in real-time by the ESP system to avoid pedal feedback distortion on low-traction surfaces.

[0031] In this embodiment, personalized preference settings include two input parameters: driving mode and personalized preference. The driving mode is selected by the user, with options including Eco, Standard, or Sport mode, and its function is to preset the style guidance of pedal feel. Personalized preference is input through a custom slider, for example, the user can adjust parameters such as linearity or sensitivity, to refine subjective needs into quantifiable adjustment criteria.

[0032] Understandably, in this embodiment, firstly, the technical solution retains the original scene recognition and weight allocation capabilities. The system identifies braking scenarios based on real-time states such as vehicle speed and load, and determines the basic weights of each feature factor based on the user's driving mode and personalized preferences. This provides the first layer of adaptation for personalized dynamic output. Secondly, the decoupling step solves the inherent coupling problem between feature factors. In different scenarios, there are mutual constraints between factors such as idle travel and linearity, response and limits. If not handled properly, changes in the weight of one factor will distort the actual expression of another factor, causing the final pedal feel to deviate from the user's expectations. By generating a coupling suppression matrix and decoupling the weighted feature vectors, the system can eliminate redundant interference between factors, allowing the independent contribution of each factor to be accurately reflected. Finally, the decoupled feature vectors are input into the mapping model and transformed into execution parameters such as motor torque, damping, and travel limits. Because the decoupling step makes the input signal purer and its physical meaning clearer, the mapping model can more accurately match user preferences with scenario requirements. The final pedal feel not only achieves scene adaptation but also avoids personalized deviations caused by factor coupling, thus achieving a realistic and stable personalized dynamic output effect.

[0033] In some embodiments, based on the working characteristics of the EMB pedal assembly, the pedal feel is decomposed into four core dimensions: free travel characteristics, linear characteristics, response characteristics, and limit characteristics. Corresponding characteristic factors are calculated through real-time data to achieve objective quantification of subjective feelings.

[0034] Please refer to Figure 2 , Figure 2 This is a flowchart of step S103 in a scene-adaptive tuning method for brake pedal feel.

[0035] In some embodiments, step S103 includes: S201. Obtain the basic weight matrix corresponding to the current driving mode from the personalized preference settings. The basic weight matrix includes the basic weight value of each feature factor.

[0036] S202. Determine the dynamic correction coefficient based on the current status information of the target vehicle.

[0037] S203. After adjusting the target basic weight values ​​in the basic weight matrix using dynamic correction coefficients, the final weight matrix is ​​generated, and each weight value in the final weight matrix is ​​used as the scene adaptation weight corresponding to the target feature factor.

[0038] Understandably, this embodiment achieves deep decoupling and flexible integration of personalized preferences and real-time scenarios by introducing a two-layer weight generation mechanism that combines a basic weight matrix and dynamic correction coefficients. The basic weight matrix solidifies the user's pedal feel preferences in different driving modes, while the dynamic correction coefficients precisely adjust the target weights based on the vehicle's current state. This ensures that the final output scenario-adaptive weights reflect both the user's subjective settings and provide immediate responses to dynamic changes such as emergency braking and low-friction surfaces. This method improves the refinement and adaptability of weight allocation, further enhancing the balance between personalization and scenario adaptation in pedal feel.

[0039] In some embodiments, users have different priority requirements for the four feature factors of empty travel characteristics, linearity characteristics, response characteristics, and limit characteristics in different driving scenarios and vehicle states, and the final weight matrix needs to be determined.

[0040] First, based on the preset basic weight matrix (W0) of driving modes, the analytic hierarchy process (AHP) is used to construct the initial weights according to the core requirements of Eco mode, Standard mode, and Sport mode, as shown in Table 1: Table 1 - Basic Weight Values ​​of Characteristic Factors

[0041] Then, adjustments are made based on the vehicle's condition.

[0042] Adjust the base weight values ​​for dynamic parameters such as vehicle speed, load, and road surface adhesion coefficient:

[0043] in, The corrected weight of the i-th factor; Basic weights; Correction coefficient (value range: -0.2~0.3, obtained by mapping vehicle state. Different vehicle states have corresponding correction systems). ,For example: When the vehicle speed Vc > 100 km / h, α (response characteristics) = +0.2 (weight for improving sensitivity) and α (limit characteristics) = +0.1 (weight for improving limit stability).

[0044] In the case of a load m>2000kg, α (limiting characteristic) = +0.3 (increasing the gradual requirement of the limiting force).

[0045] In the case of road surface μ < 0.3 (wet and slippery road surface), α (response characteristics) = -0.2 (reduce sensitivity and avoid sudden braking).

[0046] In some embodiments, step S106 includes: The decoupled feature factor vector is input into the pre-trained neural network model; the execution parameters output by the neural network model are obtained, including at least the motor torque command for controlling the pedal reaction force and the motor position command for controlling the pedal travel.

[0047] Optionally, among the multiple characteristic factors, at least a linear characteristic factor, a response characteristic factor, and a no-travel characteristic factor are included.

[0048] Step S106 also includes: The system acquires the basic torque, basic damping, and basic travel values ​​of the pedal feel simulation device. It then performs a forward correlation calculation between the linear characteristic factor (with set scene adaptation weights) and the corresponding scene adaptation weights to obtain the torque factor. This torque factor is used to adjust the basic torque value and generate the target torque command for the motor. Finally, it performs a reverse correlation calculation between the response characteristic factor (with set scene adaptation weights) and the corresponding scene adaptation weights to obtain the damping factor. This damping factor is used to adjust the basic damping value and generate the transmission damping command. Finally, it performs a forward correlation calculation between the idle travel characteristic factor (with set scene adaptation weights) and the corresponding scene adaptation weights to obtain the travel limit factor. This travel limit factor is used to adjust the basic travel value and generate the effective travel limit command.

[0049] Understandably, this embodiment constructs a dual-mode mapping mechanism that parallels the neural network model and the physical rule model. The neural network directly maps multiple feature factors to motor torque and position commands, possessing advantages such as strong nonlinear fitting ability and fast response speed. Simultaneously, for the three core factors of linearity, response characteristics, and idle travel characteristics, physical rule mappings based on forward or reverse weighting operations are designed respectively. These weight values ​​are transformed into torque factors, damping factors, and travel limit factors, and the basic parameters are adjusted to generate specific commands. The two mapping methods complement each other, both enhancing the richness and accuracy of execution parameters through data-driven approaches and ensuring a clear causal logic between key factors and executed physical quantities through rule mapping, thereby enhancing the interpretability and engineering implementation reliability of the solution.

[0050] In some embodiments, a BP neural network is used to train the mapping model, with inputs of "K0, KFS, Kdelay, Klimit, W1~W4" and outputs three EMB execution parameters. (1) Target torque of the motor ( Unit: N m: Determines the magnitude of the pedal feedback force, and is positively correlated with KFS (the higher the linearity, the more precise the linear increase of torque with stroke).

[0051] (2) Damping of transmission mechanism (D, unit: N) s / mm: Affects the smoothness of pedal movement and is negatively correlated with Kdelay (the smaller the damping, the more sensitive the response).

[0052] (3) Effective travel limit (S) e (Unit: mm): Controls the ratio of idle stroke to effective stroke, positively correlated with K0 (the larger K0 is, the more effective the stroke). e The larger the value, the smaller the empty travel.

[0053] The characteristic factors are converted into execution parameters according to the following formula:

[0054]

[0055]

[0056] in, , , All are basic EMB hardware parameters (defined by the manufacturer); , , All of these are the adjusted weight values ​​of the corresponding feature factors.

[0057] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the steps involved in obtaining the linear characteristic factor in a scene-adaptive tuning method for brake pedal feel.

[0058] In some embodiments, when the feature factor is a linear characteristic factor, the step of obtaining the linear characteristic factor includes: S301. Collect multiple discrete data points within the effective travel range of the pedal. Each data point corresponds to a travel position and the actual pedal force.

[0059] S302. Use the least squares method to fit all data points to obtain an ideal linear curve, where the ideal linear curve represents the expected relationship between pedal force and travel under ideal linear foot feel.

[0060] S303. Calculate the absolute value of the deviation between the actual pedal force at each data point and the ideal pedal force at the corresponding stroke on the ideal linear curve, and calculate the average ratio between the absolute value of the deviation and the maximum pedal force as the average deviation.

[0061] S304. The difference between the preset unit value and the average deviation is used as the linear characteristic factor, wherein the linear characteristic factor is positively correlated with the linearity that characterizes the pedal feel.

[0062] Specifically, within the effective travel range, the linear relationship between pedal force (F) and travel (S) determines the "expected match between pedaling force and braking effect," which is the core indicator of pedal feel. The formula for calculating the linear characteristic factor is: Collect discrete data points {(S1,F1), (S2,F2), ..., (S...} within the effective travel range. n ,F n )}.

[0063] Fitting an ideal linear curve using the least squares method: =k·S+b (k is the ideal slope, b is the intercept).

[0064] Calculate the deviation between the actual curve and the ideal curve:

[0065] Linearity factor:

[0066] Wherein, Fmax: the maximum pedal force within the effective stroke (determined by hardware limits, such as 800N); The value range is 0~1. The closer it is to 1, the more linear the feel.

[0067] In some embodiments, when the feature factor is an idle travel characteristic factor, the step of obtaining the idle travel characteristic factor includes: During the initial pedal depress phase, the travel distance from the start of force application until the pedal force reaches a preset threshold and the braking deceleration is still lower than the preset deceleration value is measured, and this travel distance is defined as the no-travel distance.

[0068] Obtain the preset effective total stroke of the braking system.

[0069] Calculate the ratio of idle travel to total effective travel.

[0070] The difference between the unit value and the ratio is used as the free travel characteristic factor. The larger the factor value, the smaller the pedal free travel and the more solid the pedal feel.

[0071] Specifically, free travel is the pedal travel during the initial press when there is no braking response, directly affecting the "feel" of the pedal. The formula for calculating the free travel characteristic factor is:

[0072] in, : Measured no-travel (maximum travel when pedal force ≥ 5N and deceleration a < 0.2m / s²); EMB preset effective travel (calibrated by the braking system hardware, such as 150mm); The value range is 0~1. The closer it is to 1, the smaller the free travel and the more solid the pedal.

[0073] In some embodiments, when the feature factor is a response characteristic factor, the step of obtaining the response characteristic factor includes: The response lag time is measured and defined as the time difference from when the pedal force exceeds a preset force threshold until the braking deceleration reaches or exceeds a preset deceleration threshold.

[0074] Obtain the preset hysteresis coefficient, which is used to amplify the impact of hysteresis time on foot feel.

[0075] The product of the lag effect coefficient and the response lag time is used as the exponential part of the exponential function, and the value of the exponential function is calculated with the natural constant as the base.

[0076] The result of the exponential function is used as the response characteristic factor. The larger the value of the factor, the higher the sensitivity of the braking response and the less obvious the hysteresis.

[0077] Specifically, the "response timeliness," reflecting the change in braking deceleration from pedal operation, is related to the EMB motor start-up delay and transmission response. The formula for calculating the response characteristic factor is:

[0078] in, : Response lag time (the time difference between the pedal force exceeding the threshold Fthresh (e.g., 20N) and the deceleration a≥0.5m / s², unit: s); λ: Lag effect coefficient (empirical value, taken as 5~8, to amplify the effect of lag on foot feel); The value range is 0 to 1. The closer it is to 1, the more sensitive the response.

[0079] In some embodiments, when the characteristic factor is a limiting characteristic factor, the step of obtaining the limiting characteristic factor includes: Determine the maximum deceleration that can be achieved during braking, and collect two key pedal force values: one is the pedal force corresponding to 90% of the maximum deceleration, and the other is the pedal force corresponding to the maximum deceleration.

[0080] Calculate the ratio of the pedal force corresponding to 90% of the maximum deceleration to the pedal force corresponding to the maximum deceleration.

[0081] Using this ratio as the limit characteristic factor, the closer the value of this factor is to one, the smoother the foot feel and the better the gradualness in the limit stage.

[0082] Specifically, when braking nears its limit (deceleration a ≥ 0.8g, where g is the acceleration due to gravity), the "gradualness" of the pedal force determines whether a "sudden feeling" occurs. The formula for calculating the limiting characteristic factor is:

[0083] in, The pedal force required when the deceleration reaches 90% of the maximum deceleration; : The pedal force corresponding to the maximum deceleration; The value range is 0.7~1.0. The closer it is to 1.0, the smoother the feel is during the extreme stage.

[0084] In some embodiments, the scene-adaptive tuning method for brake pedal feel further includes: Obtain the pedal reaction force and pedal travel output by the pedal sensation simulation device; based on the pedal reaction force and pedal travel, determine the relationship curve between the reaction force and the travel, and identify the actual feature factor value according to the relationship curve; compare the actual feature factor value with the feature factor value of the set scene adaptation weight to obtain the feature factor deviation; use the iterative learning control algorithm to adjust the execution parameters output by the preset mapping model until the feature factor deviation converges to the preset threshold range.

[0085] Understandably, this embodiment introduces a closed-loop correction mechanism based on actual feedback. By real-time acquisition of pedal reaction force and travel, identifying actual characteristic factor values, comparing them with target characteristic factor values ​​to obtain deviations, and then using an iterative learning control algorithm to adjust the execution parameters successively. This closed-loop structure can compensate for the effects of system nonlinearity, parameter drift, and external disturbances, ensuring that the pedal feel of each braking output continuously approaches the preset target, thereby significantly improving calibration accuracy, consistency, and self-convergence capability.

[0086] Specifically, the characteristic factor deviation is calculated as follows: Collect the pedal FS curve and user feedback scores (1-5 points) during actual driving, and calculate the actual characteristic factors. With target feature factors Deviation:

[0087] If ΔK i If the deviation is greater than 0.1 (exceeding the standard), then the weight coefficients of the mapping model or the parameters of the neural network are corrected in reverse. For example: if (i.e., insufficient actual linearity), then increase T. m right Sensitivity.

[0088] In practical applications, the static calibration phase is iterated once every 10 tests, while mass-produced vehicles achieve dynamic iteration every 1,000 kilometers based on user feedback via OTA.

[0089] In some embodiments, the scene-adaptive tuning method for brake pedal feel further includes: Obtain the pedal feel preference parameters defined in the personalized preference settings; match the values ​​of the feature factors with the set scene adaptation weights with the pedal feel preference parameters and generate an evaluation index for quantifying the degree of matching. The evaluation index is used to display through the in-vehicle interactive interface and is fed back to the preset mapping model as a basis for adjusting the execution parameters.

[0090] Specifically, the score is calculated as an evaluation indicator using the following formula:

[0091] in, The value range is 0~100 points. ≥85 points is displayed as “Excellent Adaptation”, 70~84 points is displayed as “Acceptable Adaptation”, and <70 points is displayed as “Needs Iteration Correction”.

[0092] Understandably, this embodiment establishes a quantitative evaluation and visual feedback link between personalized preferences and execution output. By matching weighted feature factors with user-defined preference parameters to generate evaluation indicators, on the one hand, the degree to which the current pedal feel matches the user's expectations can be intuitively displayed on the in-vehicle interface, improving the user's interactive experience and sense of trust; on the other hand, this indicator is fed back to the mapping model as an adjustment basis, enabling the system to continuously converge towards the user's desired pedal feel, enhancing the transparency and self-optimization capability of personalized tuning.

[0093] This technical solution also provides a specific embodiment of the scenario-adaptive tuning method for achieving the aforementioned brake pedal feel. This embodiment takes a family sedan equipped with an electromechanical braking system as an example. Assume a family sedan equipped with an electromechanical braking system is currently in a low-speed urban following scenario, with a speed of approximately 20 kilometers per hour, and the road surface is dry asphalt. The driver selects the comfort driving mode on the central control screen and sets the "foot feel linearity" slider in the personalized preferences to a higher value and the "response sensitivity" slider to a medium value.

[0094] Step 1: Extracting Operational Data and Feature Factors. The vehicle control system collects the following operational data in real time from the sensors embedded in the pedals: the pedal force generated when the driver presses the brake pedal, the distance the pedal travels, and the instantaneous speed of the pedal movement. Based on this operational data, combined with the vehicle's current braking deceleration, the system automatically calculates three core feature factors for quantifying pedal feel: a free travel characteristic factor reflecting the amount of pedal play, a linear characteristic factor reflecting the smoothness of pedal force increase with travel, and a response characteristic factor reflecting the speed of braking response from pedal depressing.

[0095] In this example, the specific values ​​of the three characteristic factors calculated by the system are as follows: the free travel characteristic factor is at a high level, indicating that the current pedal play is small and the foot feel is relatively solid; the linear characteristic factor is at a medium level, indicating that the pedal force fluctuates to some extent as the travel increases; and the response characteristic factor is at a high level, indicating that the braking response is relatively timely.

[0096] Step 2: Identify the braking scenario. Based on information such as current vehicle speed, vehicle load, and road surface adhesion coefficient, determine that the current situation is a "low-speed urban following scenario." In this scenario, the driver typically needs to frequently perform small braking operations, requiring high linearity and smoothness of the initial pedal response, while the need for extreme braking is lower.

[0097] Step 3: Determine the scenario adaptation weights. Based on the comfort driving mode and the driver's preference for linearity, assign initial weights to each feature factor. Among them, the linearity characteristic factor is set to the highest weight, the idle travel characteristic factor to a medium weight, and the response characteristic factor to the second highest weight.

[0098] Step 4: Identify coupling relationships and generate a coupling suppression matrix. Further analysis reveals an inherent coupling relationship between characteristic factors in the current low-speed scenario: the idle travel characteristic factor and the linear characteristic factor mutually constrain each other. Specifically, if the idle travel is set too small, the pedal will generate a high reaction force in the initial stage, which will mask or interfere with the true performance of the linear segment force increasing with travel, leading to distortion in the measured value of the linear characteristic factor. Conversely, if the idle travel is set too large, the pedal will be too soft in the initial stage, causing the starting point of the linear segment to shift backward, similarly affecting the perception of linearity.

[0099] To address this issue, a coupling suppression matrix is ​​generated by invoking the internally stored coupling rule base based on the current braking scenario and the established base weights. The core function of this matrix is ​​to decouple the mutual influence between the idle travel characteristic factor and the linear characteristic factor. In this example, because the driver places particular emphasis on linearity, the coupling suppression matrix appropriately reduces the interference weight of the idle travel characteristic factor on the linear characteristic factor, while preserving the independent adjustment capability of the idle travel itself.

[0100] Subsequently, the three weighted feature factor vectors, which were originally coupled, are operated on with the coupling suppression matrix to obtain a set of decoupled feature factor vectors. The result of decoupling is that the effective contribution of the linear characteristic factor is enhanced, the indirect influence of the idle stroke characteristic factor on the linear segment is reduced, and the response characteristic factor remains basically unchanged.

[0101] Step 5: Generate execution parameters through the mapping model. Input the decoupled feature factor vector into the pre-trained neural network mapping model. Based on the input values, the model outputs three execution parameters for controlling the pedal feel simulation device: the motor target torque for controlling the magnitude of the pedal feedback force, the transmission mechanism damping for controlling the smoothness of the pedal movement, and the effective travel limit for controlling the effective braking range.

[0102] Because the decoupling process eliminates unnecessary interference from the idle travel factor on the linear segment in advance, the mapping model can more accurately generate motor torque commands based on the linearity preferences that the driver truly values. The resulting pedal feel for the driver is: moderate initial idle travel, neither too loose nor too tight; as the travel increases, the pedal force increases smoothly and linearly, without any abruptness or sudden changes caused by an excessively small idle travel setting; simultaneously, the braking response is timely but not abrupt, perfectly meeting the comfort expectations for low-speed urban driving scenarios.

[0103] The technical effects achievable by the above embodiments include: First, dynamic scenario-based adjustment, breaking through the traditional fixed parameter tuning method, dynamically adjusting weights according to the real-time vehicle status such as vehicle speed and load, meeting the pedal feel requirements under all working conditions; Second, quantifying subjective feelings, transforming vague user terms such as linearity and sensitivity into calculable feature factors, solving the problem of subjective evaluation being difficult to implement in engineering; Third, deep coupling with the electromechanical braking system, directly mapping core control parameters such as motor torque and transmission damping, realizing an integrated process of evaluation, calculation, and execution, without the need for additional tuning middleware; Fourth, closed-loop self-optimization, combining user feedback and actual operating data for iterative correction, adapting to the differences in habits among different drivers.

[0104] Please refer to Figure 4 , Figure 4 This is a schematic diagram of a scene-adaptive adjustment device for brake pedal feel.

[0105] This embodiment also provides a scene-adaptive adjustment device for brake pedal feel, including: Extraction module 401 is used to acquire the operating data of the target vehicle and extract multiple feature factors from the operating data to quantify the pedal feel characteristics. The identification module 402 is used to identify the braking scenario of the target vehicle based on the current status information of the target vehicle. The calculation module 403 is used to determine the scene adaptation weight corresponding to each feature factor based on the braking scenario and the driver's personalized preference settings. The generation module 404 is used to identify the coupling relationship between each feature factor and the target feature factor based on the braking scene, and to generate a coupling suppression matrix; The decoupling module 405 is used to decouple the feature factors after setting the scene adaptation weights using the coupling suppression matrix to obtain the decoupled feature factor vector. The conversion module 406 is used to convert each decoupled feature factor vector into the execution parameters of the pedal sensation simulation device through a preset mapping model. The control module 407 is used to control the operation of the pedal feel simulation device to generate pedal feel according to the execution parameters.

[0106] It will be understood by those skilled in the art that all or some of the steps and apparatuses in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. As is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0107] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0108] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the above-mentioned scene adaptive adjustment methods for brake pedal feel.

[0109] refer to Figure 5 , Figure 5 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 501 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0110] The memory 502 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 502 can store operating devices and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 502 and is called by the processor 501 to execute the scene adaptive adjustment method for brake pedal feel of the embodiments of this application.

[0111] The input / output interface 503 is used to implement information input and output.

[0112] The communication interface 504 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0113] Bus 505 transmits information between various components of the device, such as processor 501, memory 502, input / output interface 503, and communication interface 504.

[0114] The processor 501, memory 502, input / output interface 503, and communication interface 504 are connected to each other within the device via bus 505.

[0115] It is understood that the content of the above method embodiments is applicable to the embodiments of this electronic device. The specific functions implemented by the embodiments of this electronic device are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0116] This application also provides a computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to implement the scene-adaptive tuning method for brake pedal feel as described in any of the above specific embodiments.

[0117] This application also discloses a computer program product, including a computer program or computer instructions, which are stored in a computer-readable storage medium. The processor of the computer device reads the computer program or computer instructions from the computer-readable storage medium and executes the computer program or computer instructions, causing the computer device to perform the scene adaptive tuning method for brake pedal feel as described in any of the preceding embodiments.

[0118] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0119] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. It should be understood that in this application, “at least one” means one or more, and “more than one” means two or more.

[0120] In the several embodiments provided in this application, it should be understood that the disclosed apparatus, devices, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0121] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0122] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0123] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0124] Although the description of this application has been quite detailed and particularly focused on several of the described embodiments, it is not intended to limit itself to any of these details or embodiments or any particular embodiment. Rather, it should be considered as effectively covering the intended scope of this application by referring to the appended claims and taking into account the prior art, which provides for a broad possible interpretation of these claims. Furthermore, the foregoing description of this application with respect to embodiments foreseeable by the inventors is intended to provide a useful description, and non-substantial modifications to this application that have not yet been foreseen may still represent equivalent modifications.

Claims

1. A scene-adaptive tuning method for brake pedal feel, characterized in that, The method includes: Acquire the operating data of the target vehicle, and extract multiple feature factors from the operating data to quantify the pedal feel characteristics; Identify the braking scenario currently in which the target vehicle is located based on the current state information of the target vehicle; Based on the braking scenario and the driver's personalized preference settings, determine the scenario adaptation weight corresponding to each feature factor; Based on the braking scenario, identify the coupling relationship between each feature factor and the target feature factor, and generate a coupling suppression matrix; The coupling suppression matrix is ​​used to decouple the feature factors after setting the scene adaptation weights to obtain the decoupled feature factor vector. Each of the decoupled feature factor vectors is transformed into execution parameters of the pedal feel simulation device through a preset mapping model; The pedal feel simulation device is controlled to operate according to the execution parameters to generate pedal feel.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the pedal reaction force and pedal travel output by the pedal feel simulation device; Based on the pedal reaction force and the pedal travel, a relationship curve between the reaction force and the travel is determined, and the actual characteristic factor value is identified according to the relationship curve. The actual feature factor value is compared with the feature factor value of the set scene adaptation weight to obtain the feature factor deviation; The execution parameters output by the preset mapping model are adjusted using an iterative learning control algorithm until the deviation of the characteristic factor converges to a preset threshold range.

3. The method according to claim 1, characterized in that, The method further includes: Obtain the pedal feel preference parameters defined in the personalized preference settings; The values ​​of the feature factors of the set scenario adaptation weight are matched with the pedal feel preference parameters to generate an evaluation index for quantifying the degree of matching. The evaluation index is displayed through the in-vehicle interactive interface and fed back to the preset mapping model as a basis for adjusting the execution parameters.

4. The method according to any one of claims 1 to 3, characterized in that, The determination of the scenario adaptation weight for each feature factor based on the braking scenario and the driver's personalized preference settings includes: Obtain the basic weight matrix corresponding to the current driving mode from the personalized preference settings, wherein the basic weight matrix includes the basic weight value of each feature factor; The dynamic correction coefficient is determined based on the current state information of the target vehicle; The target base weight values ​​in the base weight matrix are adjusted using the dynamic correction coefficient to generate the final weight matrix, and each weight value in the final weight matrix is ​​used as the scene adaptation weight corresponding to the target feature factor.

5. The method according to any one of claims 1 to 3, characterized in that, The step of converting each decoupled feature factor vector into execution parameters of the pedal feel simulation device through a preset mapping model includes: The decoupled feature factor vector is input into a pre-trained neural network model; The execution parameters output by the neural network model are obtained, and the execution parameters include at least a motor torque command for controlling the pedal reaction force and a motor position command for controlling the pedal travel.

6. The method according to claim 5, characterized in that, Among the plurality of characteristic factors, at least linear characteristic factor, response characteristic factor and idle travel characteristic factor are included; The step of converting each decoupled feature factor vector into execution parameters of the pedal feel simulation device through a preset mapping model further includes: Obtain the basic torque value, basic damping value, and basic stroke value of the pedal feel simulation device; The torque factor is obtained by performing a positive relationship calculation between the linear characteristic factor that sets the scene adaptation weight and the corresponding scene adaptation weight, and the target torque command of the motor is generated by adjusting the basic torque value using the torque factor. The damping factor is obtained by performing an inverse relationship calculation between the response characteristic factor with the set scene adaptation weight and the corresponding scene adaptation weight, and the transmission damping command is generated by adjusting the basic damping value using the damping factor. The travel limit factor is obtained by performing a positive relationship calculation between the empty travel characteristic factor with the set scene adaptation weight and the corresponding scene adaptation weight. The travel limit factor is then used to adjust the basic travel value to generate an effective travel limit command.

7. The method according to claim 6, characterized in that, When the feature factor is a linear characteristic factor, the steps for obtaining the linear characteristic factor include: Multiple discrete data points are collected within the effective travel range of the pedal, and each data point corresponds to a travel position and actual pedal force. All the data points are fitted using the least squares method to obtain an ideal linear curve, wherein the ideal linear curve represents the expected relationship between pedal force and travel under ideal linear foot feel; Calculate the absolute value of the deviation between the actual pedal force at each data point and the ideal pedal force at the corresponding stroke on the ideal linear curve, and calculate the average ratio between the absolute value of the deviation and the maximum pedal force as the average deviation degree. The difference between the preset unit value and the average deviation is used as the linear characteristic factor, wherein the linear characteristic factor is positively correlated with the linearity characterizing the pedal feel.

8. A scene-adaptive adjustment device for brake pedal feel, characterized in that, The device includes: An extraction module is used to acquire the operating data of the target vehicle and extract multiple feature factors from the operating data to quantify the pedal feel characteristics. The identification module is used to identify the braking scenario currently in which the target vehicle is located based on the current state information of the target vehicle; The calculation module is used to determine the scene adaptation weight corresponding to each feature factor based on the braking scenario and the driver's personalized preference settings. The generation module is used to identify the coupling relationship between each feature factor and the target feature factor based on the braking scene, and to generate a coupling suppression matrix; The decoupling module is used to perform a decoupling transformation on the feature factors after setting scene adaptation weights using the coupling suppression matrix, so as to obtain the decoupled feature factor vector. The conversion module is used to convert each of the decoupled feature factor vectors into execution parameters of the pedal sensation simulation device through a preset mapping model. The control module is used to control the pedal feel simulation device to operate according to the execution parameters to generate pedal feel.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the scene-adaptive tuning method for brake pedal feel as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the scene-adaptive tuning method for brake pedal feel as described in any one of claims 1 to 7.

Images