Method, device and storage medium for adjusting steering feel softness of steering wheel

Abstract

The application relates to the technical field of steering wheel adjustment, in particular to a steering wheel control softness adjustment method, device and storage medium. The method comprises the following steps: collecting data related to vehicle steering wheel control; understanding and reasoning the data to obtain a first softness range; performing multi-objective optimization on steering wheel adjustment parameters, and the second softness range corresponding to the optimized steering wheel adjustment parameters is within the first softness range; selecting a target softness from the second softness range, and sending the steering wheel adjustment parameters corresponding to the target softness to a steering wheel electronic assistance system. The application realizes individualized, automatic and fine-grained adjustment of steering wheel control softness.

Description

Technical Field

[0001] This application relates to the field of steering wheel adjustment technology, and more specifically, to a method, device, and storage medium for adjusting the softness of steering wheel handling feel. Background Technology

[0002] The softness of steering wheel handling refers to the feedback force and control resistance felt by the driver when operating the steering wheel. For example, different steering wheel weight and sensitivity will affect the degree of softness.

[0003] In the existing technology, vehicles offer a limited number of driving mode options, such as Eco, Comfort, and Sport modes. Each driving mode corresponds to fixed steering wheel adjustment parameters (e.g., the power steering gain coefficient), providing the driver with a fixed level of handling softness.

[0004] The aforementioned method of adjusting the softness of the steering wheel through driving modes uses discrete classification settings, supporting only a limited number of mode switches. This makes it difficult to cover the fine-grained needs of different drivers for steering wheel handling feel in different scenarios, resulting in insufficient personalized adaptability. In view of this, this application is made. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, and storage medium for adjusting the softness of steering wheel handling, so as to achieve personalized, automated, and fine-grained adjustment of the softness of steering wheel handling.

[0006] To achieve the above objectives, this application adopts the following technical solution:

[0007] Firstly, this application provides a method for adjusting the softness of the steering wheel's handling feel, including:

[0008] Collect data related to vehicle steering wheel operation;

[0009] By understanding and reasoning about the data, a first softness range is obtained;

[0010] The steering wheel adjustment parameters are optimized for multiple objectives, and the second softness range corresponding to the optimized steering wheel adjustment parameters is within the first softness range; wherein, the multi-objective optimization includes steering wheel handling comfort optimization, steering wheel handling energy efficiency optimization, and steering wheel handling responsiveness optimization;

[0011] Select a target softness from the second softness range and send the steering wheel adjustment parameters corresponding to the target softness to the electronic power steering system.

[0012] Secondly, this application provides an electronic device, comprising:

[0013] At least one processor, and a memory communicatively connected to at least one of the processors;

[0014] The memory stores instructions that can be executed by at least one of the processors, which are executed by at least one of the processors to enable the at least one of the processors to perform the above-described method for adjusting the softness of the steering wheel's handling feel.

[0015] Thirdly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the above-described method for adjusting the softness of the steering wheel's handling feel.

[0016] Compared with the prior art, the beneficial effects of this application are as follows:

[0017] This application integrates data related to vehicle steering wheel control, analyzes and infers from this data, and can accurately understand the driver's adjustment needs for the steering wheel in the current scenario. This breaks away from the limitations of fixed driving modes in traditional systems, enabling differentiated adjustments. Through a multi-objective optimization strategy considering comfort, responsiveness, and fuel efficiency, this application outputs optimal steering wheel adjustment parameters, precisely driving the electronic power steering system to achieve the best balance of softness while meeting multiple performance requirements. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating a method for adjusting the softness of a steering wheel's handling feel according to an embodiment of this application;

[0020] Figure 2 This is a schematic diagram of the steering wheel softness adjustment interface provided in an embodiment of this application;

[0021] Figure 3 This is a flowchart of another method for adjusting the softness of steering wheel handling provided in an embodiment of this application;

[0022] Figure 4 This is a flowchart illustrating the understanding and reasoning of collected data provided in an embodiment of this application;

[0023] Figure 5 This is a schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0024] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0025] The present application will be further described in detail below with reference to the embodiments.

[0026] Figure 1 This is a flowchart illustrating a method for adjusting the softness of a steering wheel's handling feel, provided in an embodiment of this application. This method can be executed by a computer program and integrated into an electronic device, which can be an Electronic Control Unit (ECU) or a Telematics Box (T-box). This embodiment uses a steering wheel handling feel softness adjustment method integrated in the ECU or T-box to determine the softness in real time and sends the corresponding steering wheel adjustment parameters to the electronic power steering system for softness adjustment. Figure 1 As shown, this embodiment provides a method for adjusting the softness of the steering wheel's handling feel, including the following steps:

[0027] S110: Collect data related to vehicle steering wheel operation.

[0028] This embodiment can collect data from vehicle-side sensors, the CAN network, and the cloud. Optionally, it can collect driver behavior data (such as steering wheel angle, steering speed, and frequency of change), vehicle status data (such as vehicle speed, yaw rate, acceleration, and current driving mode), environmental perception data (such as road condition information, coefficient of friction, and weather), driver voice commands (i.e., voice commands for steering wheel adjustment), and driver's historical operation preference data (such as driving style, past steering wheel adjustment records, and driver's steering wheel operation habits). All data is aggregated in real time to provide data support for subsequent analysis.

[0029] S120. Understand and reason about the data to obtain the first softness range.

[0030] Based on all collected data, semantic and intent understanding is performed on the data through model algorithms, and logical reasoning is applied to the understood content to obtain the first softness range of the driver's steering wheel handling feel (which can be simply referred to as steering wheel softness). Optionally, the total range of softness is predefined as [0,1], where 0 represents the softest and 1 represents the hardest. This first softness range includes an upper limit and a lower limit, for example, [0.1, 0.9].

[0031] S130. Perform multi-objective optimization on the steering wheel adjustment parameters, and the second softness range corresponding to the optimized steering wheel adjustment parameters is within the first softness range.

[0032] Steering wheel adjustment parameters are parameters for adjusting the electronic power steering system. Different values ​​of these parameters directly affect the softness of the steering wheel's handling feel. Optionally, steering wheel adjustment parameters may include at least: the output current value of the electric power steering motor (i.e., the actual current output by the motor), the power steering gain coefficient (which determines the strength of the power steering system and is related to steering wheel torque and vehicle speed), the inertia compensation coefficient (used to compensate for response delays caused by inertia, friction, and other factors in the motor or mechanical structure), and the return-to-center control coefficient (used to adjust the dynamic characteristics of the return-to-center control).

[0033] Multi-objective optimization includes optimizing steering wheel handling comfort, fuel efficiency, and responsiveness. Different values ​​of the steering wheel adjustment parameters correspond to different levels of steering wheel handling comfort, fuel efficiency, and responsiveness. Furthermore, the steering wheel adjustment parameters are mapped to a certain softness; different values ​​of these parameters also provide different levels of softness to the driver's steering wheel input. This step iterates through all softness levels within the first softness range to find a second softness range that satisfies the multi-objective optimization.

[0034] S140. Select the target softness from the second softness range and send the steering wheel adjustment parameters corresponding to the target softness to the steering wheel electronic power steering system.

[0035] The target softness is any softness within the second softness range. Optionally, the second softness range is provided to the driver (e.g., via image or voice); in response to the driver's softness selection operation (e.g., operating the screen where the image is located or issuing a voice selection command), the target softness is determined from the second softness range.

[0036] Figure 2This is a schematic diagram of the steering wheel softness adjustment interface provided in this application embodiment. The second softness range is displayed on the vehicle's human-machine interface, and fine-tuning commands from the user are received. Specifically, through the interactive interface of the central control screen, instrument panel, head-up display, or in-vehicle voice assistant, the recommended target softness and its current second softness range are displayed to the driver in real time. Figure 2 The second softness range is [0.35, 0.85], and the recommended steering wheel softness parameter is 0.65. If the driver has a subjective preference for the current recommended value, the user can make minor adjustments within the second softness range using methods such as knobs, touch controls, sliders, and voice commands. For example... Figure 2 In the process, the softness parameter can be selected by sliding the progress bar.

[0037] The system sends the steering wheel adjustment parameters, corresponding to the driver's fine-tuning of the steering wheel's softness, to the electronic power steering system. This allows the system to adjust accordingly, ensuring the driver experiences the target softness when steering. Finally, the system's execution information is fed back to the interface or backend, and the driver's adjustments are simultaneously updated to the cloud.

[0038] Optionally, a target softness can be selected from the second softness range based on the driver's historical softness preference data. For example, the softness selected by the driver over a recent period (e.g., one week) can be obtained, and the softness preference data can be averaged across multiple softness values, such as 0.6. If 0.6 is within the second softness range, then 0.6 is selected as the target softness. If 0.6 is not within the second softness range, then the softness closest to 0.6 is selected from the second softness range. For example, if the second softness range is [0.3, 0.5], then 0.5, which is closest to 0.6, is selected as the target softness.

[0039] This application integrates data related to vehicle steering wheel control, analyzes and infers from this data, and can accurately understand the driver's adjustment needs for the steering wheel in the current scenario. This breaks away from the limitations of fixed driving modes in traditional systems, enabling differentiated adjustments. Through a multi-objective optimization strategy considering comfort, responsiveness, and fuel efficiency, this application outputs optimal steering wheel adjustment parameters, precisely driving the electronic power steering system to achieve the best balance of softness while meeting multiple performance requirements.

[0040] Figure 3 This is a flowchart of another method for adjusting the softness of steering wheel handling provided in this application embodiment. Based on the above embodiment, a determination adjustment stage and a safety boundary verification stage are added. Figure 3 The methods provided include:

[0041] S210: Collect data related to vehicle steering wheel operation.

[0042] S220. Understand and reason about the data to obtain the first softness range.

[0043] Figure 4 This is a block diagram illustrating the understanding and reasoning of collected data, as provided in an embodiment of this application. See also... Figure 4 This involves understanding driver behavior data, vehicle status data, and environmental perception data to derive driving behavior and driving scenarios. Specifically, driver behavior data, vehicle status data, and environmental perception data are input into a driving behavior and scenario understanding model. This model can be a Transformer multimodal fusion perception model incorporating Long Short-Term Memory (LSTM) to model the context of driver behavior data, vehicle status data, and environmental perception data. By understanding the current driving behavior pattern in real time and combining it with the current environmental perception data, it outputs driving behavior and driving scenarios. Examples include: driving in congested urban areas, driving on highways, driving at low speeds on mountain roads, driving around curves on elevated roads, and driving on off-road sections.

[0044] The driver's voice is recognized to determine their desired level of softness / flexibility. (See also...) Figure 4 The driver's voice data is input into a speech recognition model (e.g., Wav2Vec 2.0). The speech recognition model converts the voice data into text, which is then sent to the BERT+IntentClassifier model framework. BERT uses a bidirectional Transformer architecture to pre-train language representations, enabling it to capture contextual information. IntentClassifier is a classifier containing dropout layers and linear layers. In this embodiment, BERT extracts features from the converted text, and then IntentClassifier uses these extracted features to accurately understand the driver's desired steering wheel firmness. For example, the model framework outputs steering wheel firmness requirements such as softer steering wheel, firmer steering wheel, 30% softer steering wheel, 30% firmer steering wheel, and 30% higher steering wheel.

[0045] By analyzing the driver's historical operational preference data, the driver's flexibility preference can be obtained. (See also...) Figure 4The system inputs historical operation preference data, such as driving style, past steering wheel adjustment records, and driver steering wheel handling habits, into a historical operation preference analysis model. This model is a long-series Transformer model. The model extracts individual driving style and adjustment preferences from the historical operation preference data and predicts the driver's preferred steering wheel softness in different driving scenarios. For example, the driver's preferred steering wheel softness is 0.7 when driving on highways, 0.75 when driving on off-road sections, and 0.6 when driving in congested urban areas.

[0046] Next, a weight-based rule engine is used to obtain the first softness range based on driving behavior, driving scenario, softness requirements, and softness preferences.

[0047] Specifically, a rule base is pre-built, including upper and lower limits of flexibility corresponding to different driving behaviors, driving scenarios, flexibility requirements, and flexibility preferences. These upper and lower limits constitute the recommended flexibility range. The driving behaviors, driving scenarios, flexibility requirements, and flexibility preferences obtained above are matched against the rule base to obtain recommended flexibility ranges 1-4 for each driving behavior, driving scenario, flexibility requirement, and flexibility preference. The weights of driving behaviors, driving scenarios, flexibility requirements, and flexibility preferences are determined based on the current driving scenario. For example, in highway driving scenarios, where driving behaviors and driving scenarios are given more weight, their weights are increased, and the weights of driving behaviors, driving scenarios, flexibility requirements, and flexibility preferences are summed to 1. Based on these weights, a weighted average is calculated on the upper limits of flexibility corresponding to driving behaviors, driving scenarios, flexibility requirements, and flexibility preferences to obtain the upper limit of the first flexibility range; similarly, a weighted average is calculated on the lower limits of flexibility corresponding to driving behaviors, driving scenarios, flexibility requirements, and flexibility preferences to obtain the lower limit of the first flexibility range. See the following formula:

[0048] Res_s=0.25×A_s+0.25×S_s+0.25×V_s+0.25×R_s;Formula (1)

[0049] Res_x=0.35×A_x+0.35×S_x+0.2×V_x+0.1×R_x;Formula (2)

[0050] Where Res_s is the upper limit of the first softness range, Res_x is the lower limit of the first softness range, A_s is the upper limit of softness corresponding to driving behavior, S_s is the upper limit of softness corresponding to driving scenario, V_s is the upper limit of softness corresponding to softness demand, R_s is the upper limit of softness corresponding to softness preference, and 0.25 is the weight. A_x is the lower limit of softness corresponding to driving behavior, S_x is the lower limit of softness corresponding to driving scenario, V_x is the lower limit of softness corresponding to softness demand, and R_x is the lower limit of softness corresponding to softness preference. Formula (1) is applicable to driving scenarios on urban roads, and Formula (2) is applicable to driving scenarios on highways, with the weights of driving behavior and driving scenario increasing to 0.35.

[0051] S230: Calculate the distance between the vehicle's current softness level and the first softness level range, and determine the relationship between this distance and a set value. If the distance is greater than the set value, execute S240; otherwise, execute S210.

[0052] If the current softness is within the first softness range, the distance is 0; if the current softness is outside the first softness range, the smaller value between the current softness and the upper and lower limits of the first softness range is used as the distance between the current softness and the first softness range.

[0053] For example, if the first softness range is [0.3, 0.8] and the current softness is 0.5, then the current softness is within the first softness range. The distance between the current softness and the first softness range is 0, which is less than the set value of 0.2. Therefore, there is no need to adjust the steering wheel, and the system returns to continue collecting data related to vehicle steering wheel operation.

[0054] For example, if the first softness range is [0.3, 0.8] and the current softness is 0.05, then the distance between the current softness and the lower limit of the first softness range is 0.25, which is greater than the set value of 0.2. Therefore, the current softness is significantly different from the first softness range, and S240 is executed for further judgment.

[0055] S240: Determine whether to trigger a multi-objective optimization operation for the steering wheel adjustment parameters based on the current driving scenario. If yes, execute S250; otherwise, execute S210.

[0056] Several dangerous driving scenarios that are pre-set to be unsuitable for adjusting steering wheel softness are included, such as lane changing, turning, high-speed driving, steep slopes, and icy / snowy roads. If the current driving scenario falls under one of the pre-set dangerous driving scenarios, adjusting the steering wheel softness is prohibited, and the system returns to continue collecting data related to vehicle steering wheel control. If the current driving scenario does not fall under any of the pre-set dangerous driving scenarios, adjusting the steering wheel softness is allowed.

[0057] S250, Perform multi-objective optimization on the steering wheel adjustment parameters, and the second softness range corresponding to the optimized steering wheel adjustment parameters is within the first softness range.

[0058] First, the range of steering wheel adjustment parameters is iterated to obtain multiple sets of steering wheel adjustment parameters with different values. These sets include the electric power steering motor output current value, power steering gain coefficient, inertia compensation coefficient, and return-to-center control coefficient. Assuming the electric power steering motor output current value ranges from 1 to 10, the power steering gain coefficient ranges from 0.1 to 1, the inertia compensation coefficient ranges from 0.1 to 1, and the return-to-center control coefficient ranges from 0.1 to 1, with a step size of 0.1, 100 × 10 × 10 × 10 = 100,000 sets of steering wheel adjustment parameters are obtained.

[0059] Then, the actual softness is obtained according to each steering wheel adjustment parameter group. According to the structural design of the electronic power steering system, if a steering wheel adjustment parameter group is determined, the steering wheel will exhibit a corresponding softness of handling feel (for ease of distinction, this softness is referred to as the actual softness), and there is a corresponding relationship between the steering wheel adjustment parameters and the actual softness.

[0060] In this embodiment, a steering wheel perception function S(x1, x2, x3, x4) is constructed, which ranges from steering wheel adjustment parameters to softness. x1, x2, x3, and x4 are the output current value of the electric power steering motor, the power steering gain coefficient, the inertia compensation coefficient, and the return-to-center control coefficient, respectively, and S is the softness.

[0061] First, the output current value, assist gain coefficient, inertia compensation coefficient, and homing control coefficient of the electric assist motor are divided by their respective maximum values ​​and normalized to obtain four normalized parameters, as shown in the following formula:

[0062] x1_norm = x1 / 20.0;

[0063] x2_norm = x2 / 5.0;

[0064] x3_norm = x3 / 0.5;

[0065] x4_norm = x4 / 20.0;

[0066] Where 20.0 is the maximum output current of the electric assist motor, 5.0 is the maximum assist gain coefficient, 0.5 is the maximum inertia compensation coefficient, and 20.0 is the maximum homing control coefficient. x1_norm is the normalized output current of the electric assist motor, x2_norm is the normalized assist gain coefficient, x3_norm is the normalized inertia compensation coefficient, and x4_norm is the normalized homing control coefficient.

[0067] Then, the four normalized parameters are combined nonlinearly, as shown in the following equation:

[0068] feature1 = np.tanh(x1_norm×x2_norm);

[0069] feature2 = np.exp(-x3_norm^2);

[0070] feature3 = np.sin(np.pi×x4_norm / 2);

[0071] feature4 = x1_norm×x3_norm×x4_norm;

[0072] Among them, feature1, feature2, feature3, and feature4 are four eigenvalues ​​obtained through nonlinear operations. np.tanh is used to calculate the hyperbolic tangent of (x1_norm × x2_norm), np.exp is used to calculate the exponent of (-x3_norm^2), and np.sin is used to calculate the sine of (np.pi × x4_norm / 2). np.pi is the standard constant used to represent pi.

[0073] Next, a weighted summation is performed on the aforementioned four characteristic values ​​to obtain the softness S:

[0074] S =0.4×feature1 + 0.3×feature2 + 0.2×feature3 + 0.1×feature4;

[0075] Finally, saturated nonlinearity is applied to ensure that the softness S output is within a reasonable range.

[0076] S = np.clip(S, 0, 1);

[0077] The np.clip parameter is used to limit the softness S to a specified minimum value of 0 and a maximum value of 1.

[0078] This embodiment does not limit the specific form of the steering wheel sensing function; it can be any multivariate nonlinear function. Each set of steering wheel adjustment parameters is input into the steering wheel sensing function to obtain the corresponding actual softness.

[0079] In this embodiment, the constraint of multi-objective optimization is that the actual softness needs to be within a first softness range. If the actual softness is not within the first softness range, the steering wheel adjustment parameter group is discarded, and the process continues to traverse the next steering wheel adjustment parameter group. If the actual softness is within the first softness range, the steering wheel handling comfort, steering wheel handling fuel efficiency, and steering wheel handling responsiveness are calculated based on the steering wheel adjustment parameter group to determine whether the actual softness meets the multi-objective optimization requirements. The process of multi-objective optimization is explained in detail below:

[0080] The steering wheel adjustment parameters determine the electromechanical performance of the steering wheel, thus affecting its handling comfort, energy efficiency, and responsiveness. For example, the absolute value of the residual yaw rate after releasing the steering wheel can be obtained from the return-to-center control coefficient, used to evaluate the comfort of steering return. Based on the output current of the electric power steering motor, combined with the motor's output voltage and time, the energy consumption of the electronic power steering system can be calculated; lower energy consumption indicates higher energy efficiency. In return-to-center control, the power assist gain coefficient determines the magnitude of the return-to-center torque. When the steering wheel angle is large, an increase in the power assist gain coefficient will quickly generate return-to-center torque, shortening the return-to-center time and improving responsiveness. The inertia compensation coefficient uses the steering wheel angular acceleration signal to adjust the power assist torque in real time, reducing the inertial delay during steering of heavy vehicles, thereby improving response speed; a larger inertia compensation coefficient results in higher responsiveness.

[0081] It should be noted that the calculation methods for steering wheel handling comfort, steering wheel handling fuel efficiency, and steering wheel handling responsiveness described above are merely examples. Those skilled in the art can construct and calculate the formulas for steering wheel handling comfort, steering wheel handling fuel efficiency, and steering wheel handling responsiveness themselves. This embodiment focuses on selecting steering wheel adjustment parameter groups to meet the requirements of steering wheel handling comfort, fuel efficiency, and responsiveness, providing the driver with a good handling experience while simultaneously achieving vehicle fuel economy.

[0082] If the steering wheel handling comfort, steering wheel handling energy efficiency, and steering wheel handling responsiveness all exceed the set thresholds, the optimization requirements are met, and a second softness range is obtained based on the actual softness. After traversing all steering wheel adjustment parameter groups, all actual softness levels are obtained, forming the second softness range. Therefore, the second softness range is within the first softness range.

[0083] S260. Determine the safety boundaries of flexibility based on the current vehicle status and driving scenario.

[0084] To ensure driving safety of the softness adjustment behavior, the second softness range is verified and limited. During the vehicle testing phase before collecting data related to vehicle steering wheel control, a function of the safety boundary is obtained through testing methods, including a function of the upper limit of the safety boundary and a function of the lower limit of the safety boundary.

[0085] Optionally, under different vehicle states (e.g., high speed / low speed) and different driving scenarios (e.g., straight / curved, dry / slippery road surfaces), test the vehicle's handling safety indicators (e.g., steering response delay time, maximum lateral acceleration, maximum yaw rate, etc.) at different levels of softness. For example, set a certain level of softness on the vehicle, control the vehicle in a certain state and driving scenario, and collect values ​​such as steering angle, time, lateral acceleration, and yaw rate through sensors on the vehicle. Calculate the handling safety indicator values ​​from the collected values; the specific calculation formulas are found in existing technologies and will not be elaborated here. In this way, handling safety indicator values ​​corresponding to multiple levels of softness can be obtained for a vehicle state and a driving scenario.

[0086] Under a given vehicle state and driving scenario, the handling safety index values ​​are compared with set threshold values ​​(e.g., maximum steering response delay time threshold, maximum lateral acceleration threshold, maximum yaw rate threshold). A softness level below the set threshold is selected, and the upper and lower limits of the selected softness level constitute the safety boundary. For example, under a given vehicle state and driving scenario, if softness levels below the set threshold values ​​are selected as 0.2, 0.3, 0.4, and 0.5, the safety boundary is [0.2, 0.5], with a lower limit of 0.2 and an upper limit of 0.5. This ultimately forms a point set representing the vehicle state, driving scenario, and the upper / lower limits of the safety boundary.

[0087] Based on the aforementioned point set, construct functions mapping from vehicle state and driving scenario to the upper limit of the safety boundary, and functions mapping from vehicle state and driving scenario to the lower limit of the safety boundary. If the parameters of vehicle state and driving scenario are few, linear interpolation is used to linearly interpolate the vehicle state, driving scenario, and upper limit of the safety boundary, and then linearly fits the interpolated point set to obtain the function of the upper limit of the safety boundary; similarly, linear interpolation is used to linearly interpolate the vehicle state, driving scenario, and lower limit of the safety boundary, and then linearly fits the interpolated point set to obtain the function of the lower limit of the safety boundary. See the following equation:

[0088] Y_s=a_1×m1+b_1×m2+c_1;

[0089] Y_x=a_2×m1+b_2×m2+c_2;

[0090] Where Y_s is the upper limit of the safety boundary, Y_x is the lower limit of the safety boundary, a_1, b_1, c_1, a_2, b_2, and c_2 are all parameters to be fitted, m1 is the variable of the vehicle state (i.e., the quantized value of the vehicle state), and m2 is the variable of the driving scenario (i.e., the quantized value of the driving scenario).

[0091] If there are many parameters related to vehicle state and driving scenario, multinomial fitting is used to fit the vehicle state, driving scenario, and upper / lower safety boundary limits. Specifically, multinomial fitting is performed using the vehicle state, driving scenario, and lower safety boundary limit to obtain a function representing the lower safety boundary limit; multinomial fitting is performed using the vehicle state, driving scenario, and upper safety boundary limit to obtain a function representing the upper safety boundary limit. See the following formula:

[0092] Y_s=n_0+n_1×m1+n_2×m2+n_3×m1 2 +n_4×m2 2 +n_5×m1×m2;

[0093] Y_x=p_0+p_1×m1+p_2×m2+p_3×m1 2 +p_4×m2 2 +p_5×m1×m2;

[0094] Where Y_s is the upper limit of the safety boundary, Y_x is the lower limit of the safety boundary, n_0, n_1, n_3, n_4, n_5, p_0, p_1, p_2, p_3, p_4, and p_5 are all parameters to be fitted, m1 is the variable of the vehicle state (i.e., the quantized value of the vehicle state), and m2 is the variable of the driving scenario (i.e., the quantized value of the driving scenario).

[0095] This embodiment achieves polarization-free security constraints by converting the point set into the form of a continuous function.

[0096] In this step, the current vehicle state and driving scenario are input into the function of the upper limit of the safety boundary to obtain the upper limit of the safety boundary; the current vehicle state and driving scenario are input into the function of the lower limit of the safety boundary to obtain the upper limit of the safety boundary. The upper and lower limits of the safety boundary together constitute the safety boundary of the softness.

[0097] S270. Determine whether the second softness range exceeds the safety boundary. If so, execute S280; otherwise, execute S290.

[0098] S280. Limit the range of the second softness according to the safety boundary.

[0099] If the second softness range is not within the safety boundary, it means that the second softness range exceeds the safety boundary. The excess part will affect the vehicle's handling safety, and the excess part will be restricted. For example, if the second softness range is [0.2, 0.5] and the safety boundary is [0.3, 0.8], then the part of the second softness range [0.2, 0.3) will affect the vehicle's handling safety. The restricted second softness range is [0.3, 0.5].

[0100] If the second softness range is within the safety boundary, no compression treatment is required.

[0101] S290. Select the target softness from the second softness range and send the steering wheel adjustment parameters corresponding to the target softness to the electronic power steering system.

[0102] If the second softness range has been narrowed, this step requires selecting the target softness within the narrowed second softness range.

[0103] In summary, the embodiments of this application have the following technical effects:

[0104] 1. Achieve personalized adjustment of steering wheel feel: By integrating multi-source data such as driver behavior, vehicle status, environmental perception, voice input, and historical preferences, and using a large model for understanding and reasoning, it can accurately understand the driver's adjustment needs in different scenarios, breaking the limitations of the fixed driving mode in traditional driving modes and achieving differentiated adjustment.

[0105] 2. Enhance the intelligence level of steering wheel adjustment: Through a large model, the system understands multi-source data such as driving behavior, voice commands, and historical preferences, automatically identifies adjustment needs, and intelligently determines whether to perform the adjustment action to avoid invalid or unsafe operations.

[0106] 3. Improve the safety and reliability of system response: By introducing a safety boundary verification mechanism based on real vehicle testing, it is ensured that the recommended or driver adjustment values ​​are always within the safety boundary, effectively avoiding driving risks in extreme scenarios and ensuring driving control safety.

[0107] 4. Introducing multi-objective optimization to enhance the overall driving experience: Through multi-objective optimization strategies of comfort, responsiveness and fuel efficiency, the optimal combination of steering wheel adjustment parameters is output to precisely drive the electronic power steering system and achieve the optimal matching of softness to meet multiple performance requirements.

[0108] 5. Supports driver participation in fine-tuning, enhancing interactivity and sense of control: This embodiment supports the driver to make controllable fine-tuning based on the second softness range, and provides feedback through head-up display / voice / touch, etc., to improve driver satisfaction and confidence in operation.

[0109] 6. Closed-loop feedback mechanism and data update: All steering wheel adjustment results and driver operation behavior are uploaded to the cloud in sync, which can be used for subsequent preference modeling and personalized learning, enhancing the adaptability and continuous optimization capability of the adjustment method.

[0110] like Figure 5 As shown, this embodiment provides an electronic device, including:

[0111] At least one processor; and

[0112] A memory that is communicatively connected to at least one processor; wherein,

[0113] The memory stores instructions executable by at least one processor, which, when executed, enables the processor to perform the described method. Since at least one processor in this electronic device is capable of performing the described method, it possesses at least the same advantages as the described method.

[0114] Optionally, the electronic device also includes interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The components are interconnected using different buses and can be mounted on a common motherboard or otherwise installed as needed. The processor can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI (Graphical User Interface) on an external input / output device (such as a display device coupled to the interface). In other embodiments, multiple processors can be used with multiple memories, and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple electronic devices (e.g., as a server array, a group of blade servers, or a multiprocessor system) can be connected, each providing some of the necessary operations. Figure 5 Take processor 301 as an example.

[0115] The memory 302, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the steering wheel handling feel adjustment method in this embodiment. The processor 301 executes various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 302, thereby realizing the aforementioned steering wheel handling feel adjustment method.

[0116] The memory 302 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on terminal usage. Furthermore, the memory 302 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 302 may further include memory remotely located relative to the processor 301, which can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0117] The electronic device may further include an input device 303 and an output device 304. The processor 301, memory 302, input device 303, and output device 304 can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0118] Input device 303 can receive input digital or character information, and output device 304 may include a display device, an auxiliary lighting device (e.g., an LED), and a haptic feedback device (e.g., a vibration motor). The display device may include, but is not limited to, a liquid crystal display (LCD), a light-emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touchscreen.

[0119] This embodiment provides a computer-readable storage medium storing computer instructions for causing a computer to perform the methods described above. The computer instructions on this computer-readable storage medium, used to cause a computer to perform the methods described above, thus have at least the same advantages as the methods described above.

[0120] The medium in this application may be any combination of one or more computer-readable media. The medium may be a computer-readable signal medium or a computer-readable storage medium. The medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the medium (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, the medium may be any tangible medium containing or storing a program that may be used by or in connection with an instruction execution system, apparatus, or device.

[0121] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0122] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF (Radio Frequency), or any suitable combination thereof.

[0123] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0124] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means, such as coaxial cable, optical fiber, digital subscriber line (DSL), or wireless means, such as infrared, wireless, microwave, etc. The computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium, or a semiconductor medium, etc. It is worth noting that the computer-readable storage medium mentioned in the embodiments of this application can be a non-volatile storage medium, in other words, it can be a non-transient storage medium.

[0125] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0126] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method of adjusting the softness of the steering feel of a steering wheel, characterized in that, The method comprises the following steps: collecting data related to steering wheel operation of the vehicle; understanding and reasoning the data to obtain a first softness range; multi-objective optimization of steering wheel adjustment parameters, and the second softness range corresponding to the optimized steering wheel adjustment parameters is within the first softness range; wherein the multi-objective optimization includes steering wheel operation comfort optimization, steering wheel operation energy saving optimization and steering wheel operation response optimization; selecting a target softness from the second softness range, and sending the steering wheel adjustment parameters corresponding to the target softness to the steering wheel electronic power system; understanding and reasoning the data to obtain a first softness range, comprising: understanding the driver behavior data, vehicle state data and environment perception data to obtain driving behavior and driving scene; recognizing the driver's voice to obtain the driver's softness demand; understanding the driver's historical operation preference data to obtain the driver's softness preference; using a weight-based rule engine to obtain the first softness range according to the driving behavior, driving scene, softness demand and softness preference; multi-objective optimization of steering wheel adjustment parameters, and the second softness range corresponding to the optimized steering wheel adjustment parameters is within the first softness range, comprising: traversing the range of steering wheel adjustment parameters to obtain a plurality of steering wheel adjustment parameter groups with different values; wherein the steering wheel adjustment parameter group includes electric power motor output current value, power gain coefficient, inertia compensation coefficient and return control coefficient; obtaining the corresponding actual softness according to each steering wheel adjustment parameter group; if the actual softness is within the first softness range, calculating the steering wheel operation comfort, steering wheel operation energy saving and steering wheel operation response according to the steering wheel adjustment parameter group; if the steering wheel operation comfort, steering wheel operation energy saving and steering wheel operation response all meet the optimization requirements, obtaining the second softness range according to the actual softness.

2. The method of adjusting the softness of the steering feeling of a steering wheel according to claim 1, characterized by, After understanding and reasoning the data to obtain a first softness range, it further comprises: calculating the distance between the current softness of the vehicle and the first softness range; if the distance is greater than a set value, determining whether to trigger the operation of multi-objective optimization of steering wheel adjustment parameters according to the current driving scene.

3. The method of adjusting the softness of the steering feeling of a steering wheel according to claim 1, characterized by, After multi-objective optimization of steering wheel adjustment parameters, and the second softness range corresponding to the optimized steering wheel adjustment parameters is within the first softness range, it further comprises: determining the safety boundary of softness according to the current vehicle state and driving scene; if the second softness range exceeds the safety boundary, limiting the second softness range according to the safety boundary.

4. The method of adjusting the softness of the steering feeling of a steering wheel according to claim 3, characterized by, Before collecting data related to steering wheel operation of the vehicle, it further comprises: testing the steering wheel operation safety index value of the vehicle under different softness in different vehicle states and different driving scenes; determining the safety boundary of softness by comparing the steering wheel operation safety index value with the set index threshold in a vehicle state and a driving scene, forming a point set of vehicle state, driving scene and safety boundary; According to the point set, a function mapping from a vehicle state and a driving scene to the upper limit of the safety boundary is constructed, and a function mapping to the lower limit of the safety boundary is constructed; According to the current vehicle state and the driving scene, a safety boundary of softness is determined, comprising: The current vehicle state and the driving scene are brought into the function of the upper limit of the safety boundary and the function of the lower limit of the safety boundary to obtain the safety boundary of softness.

5. The method of adjusting the softness of the steering feeling of a steering wheel according to claim 1, characterized by, Selecting a target softness from the second softness range, comprising: Providing the second softness range to the driver; determining a target softness from the second softness range in response to a softness selection operation of the driver; Or, selecting a target softness from the second softness range according to historical softness preference data of the driver.

6. The method of adjusting the softness of the steering feeling of a steering wheel according to claim 1, characterized by, Using a weight-based rule engine, a first softness range is obtained according to driving behavior, driving scene, softness requirement and softness preference, comprising: A rule base is constructed in advance, the rule base including softness upper limits and softness lower limits corresponding to different driving behaviors, different driving scenes, different softness requirements and different softness preferences respectively; The driving behavior, the driving scene, the softness requirement and the softness preference are matched in the rule base to obtain the softness upper limit and the softness lower limit corresponding to the driving behavior, the driving scene, the softness requirement and the softness preference respectively; The weights of the driving behavior, the driving scene, the softness requirement and the softness preference are determined according to the current driving scene respectively; According to the weights, the softness upper limits corresponding to the driving behavior, the driving scene, the softness requirement and the softness preference are weighted and averaged to obtain the upper limit of the first softness range; According to the weights, the softness lower limits corresponding to the driving behavior, the driving scene, the softness requirement and the softness preference are weighted and averaged to obtain the lower limit of the first softness range.

7. An electronic device, comprising: Comprising: At least one processor and a memory communicatively connected to the at least one processor; Wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steering wheel softness adjustment method of any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The medium stores computer instructions, and the computer instructions are used to enable a computer to execute the steering wheel softness adjustment method of any one of claims 1-6.

Images