A hardware-in-the-loop calibration method and device, electronic equipment and vehicle

Abstract

The application relates to a hardware-in-the-loop calibration method and device, electronic equipment and a vehicle, and comprises the following steps: creating a vehicle dynamics model and an intelligent driving control system model of a vehicle; constructing a plurality of typical working conditions and a plurality of intelligent driving scenes of the vehicle; constructing a HiL bench test environment based on the vehicle dynamics model and the intelligent driving control system model, the HiL bench test environment being used for calibrating an intelligent driving system and a chassis electric control steering system under the plurality of typical working conditions and the plurality of intelligent driving scenes; and adopting the HiL bench test environment to open-loop calibrate the chassis electric control steering system and / or close-loop calibrate the intelligent driving system. According to the embodiment of the application, the calibration efficiency can be improved by calibrating in the HiL environment, real vehicle tests do not need to be frequently carried out, test cost is saved, safety is enhanced, and a plurality of working conditions can be comprehensively covered.

Description

Technical Field

[0001] This invention relates to the field of vehicle parameter calibration technology, specifically to a hardware-in-the-loop calibration method, apparatus, electronic device, and vehicle. Background Technology

[0002] As automobiles develop towards electrification, intelligence, connectivity, and sharing, the automotive chassis is showing a trend of intelligentization, intra-chassis collaboration, and cross-domain integration (integration with the powertrain domain and intelligent driving domain). In order to support the implementation of intelligent driving control, the chassis electronic steering system needs to be calibrated to achieve accurate and timely response to typical intelligent driving commands. In addition, the steering comfort and stability in intelligent scenarios will also be matched and calibrated.

[0003] Calibrating the chassis electronic steering system based on typical intelligent driving commands is called open-loop calibration; calibrating the intelligent driving system based on intelligent driving scenarios is called closed-loop calibration. Currently, both of these calibration processes are based on real vehicles and mainly rely on the experience of calibration personnel and repeated experiments. This results in problems such as long calibration cycles, multiple and heavy calibration conditions, and high risks associated with high-speed conditions. Summary of the Invention

[0004] One objective of this invention is to provide a hardware-in-the-loop calibration method to solve the problems of long calibration cycles, multiple and heavy calibration conditions, and high risk at high speeds in the existing hardware-in-the-loop calibration process; a second objective is to provide a hardware-in-the-loop calibration device; a third objective is to provide an electronic device; a fourth objective is to provide a computer-readable storage medium; and a fifth objective is to provide a vehicle.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A hardware-in-the-loop calibration method, the method comprising:

[0007] Create vehicle dynamics models and intelligent driving control system models;

[0008] Construct multiple typical operating conditions and multiple intelligent driving scenarios for vehicle operation;

[0009] The HiL bench test environment is constructed based on the vehicle dynamics model and the intelligent driving control system model. The HiL bench test environment is used to perform hardware-in-the-loop calibration of the intelligent driving system and chassis electronic steering system under multiple typical working conditions and multiple intelligent driving scenarios.

[0010] The HiL bench test environment is used to perform open-loop calibration of the chassis electronic steering system and / or closed-loop calibration of the intelligent driving system.

[0011] Optionally, the construction of the HiL bench test environment based on the vehicle dynamics model and the intelligent driving control system model includes:

[0012] Load the real-time simulator and add the hardware devices corresponding to the HiL bench test environment to the real-time simulator;

[0013] The vehicle dynamics model, the intelligent driving control system model, the multiple typical working conditions, and the multiple intelligent driving scenarios are added to the real-time simulator.

[0014] Connect the real-time simulator to the HiL cabinet and the HiL hardware system, and configure the HiL bench test environment.

[0015] Optionally, the step of using the HiL bench test environment to perform open-loop calibration of the chassis electronic steering system and / or closed-loop calibration of the intelligent driving system includes:

[0016] Determine the first target item for the open-loop calibration of the chassis electronic steering system;

[0017] Based on the first target item, the first parameter to be calibrated for the chassis electronic steering system is selected;

[0018] Determine the first test plan corresponding to the first parameter to be calibrated;

[0019] According to the first test plan, the HiL bench test environment is called to perform the test, and the first recalibration parameters and the first parameter range are obtained.

[0020] The first calibration parameters and the first parameter range are optimized to obtain the first calibration parameters.

[0021] Optionally, determining the first test plan corresponding to the first parameter to be calibrated includes:

[0022] Determine the upper and lower limits of the first parameter to be calibrated;

[0023] The first test matrix of the first parameter to be calibrated is generated based on the upper and lower limits.

[0024] Optionally, the step of calling the HiL bench test environment according to the test plan to obtain the first recalibration parameters and the first parameter range includes:

[0025] Based on the chassis electronic steering system, determine the open-loop calibration conditions corresponding to the parameters to be calibrated;

[0026] The first test matrix is ​​converted into a test sequence according to the open-loop calibration conditions described above;

[0027] The test sequence is run in the HiL bench test environment to obtain the test results;

[0028] The first recalibration parameters and the range of the first parameters were determined based on the test results.

[0029] Optionally, optimizing the first key calibration parameter and the first parameter range to obtain the first calibration parameter includes:

[0030] A response surface model between the calibration parameters and the calibration target is established based on the first key calibration parameters and the first parameter range;

[0031] A multi-objective optimization method is used to perform global optimization on the response surface model to determine the first calibration parameter under typical operating conditions.

[0032] Optionally, the step of using the HiL bench test environment to perform open-loop calibration of the chassis electronic steering system and / or closed-loop calibration of the intelligent driving system includes:

[0033] Determine the second target item for the closed-loop calibration of the intelligent driving system;

[0034] A deep neural network model for intelligent driving is established; the deep neural network model is a model that represents the correlation between subjective evaluation scoring data and objective test data.

[0035] Based on the target item, the HiL bench test environment is invoked to perform the test and obtain objective test data of the target.

[0036] The objective test data of the target is input into the neural network model, and the subjective evaluation score data corresponding to the objective test data of the target is output.

[0037] Sensitivity analysis was performed based on the subjective evaluation scoring data to obtain the second recalibration parameter and the range of the second parameter.

[0038] The second calibration parameters and the range of the second parameter are optimized to obtain the second calibration parameters.

[0039] Optionally, optimizing the second critical calibration parameter and the second parameter range to obtain the second calibration parameter includes:

[0040] Using the expected score in the subjective evaluation scoring data as the calibration target, a response surface model between the calibration parameters and the calibration target is established with the second critical calibration parameter and the range of the second parameter.

[0041] A multi-objective optimization method is used to perform global optimization on the response surface model to determine the second calibration parameter under typical operating conditions.

[0042] Optionally, the hardware device includes any one or more of the following:

[0043] CAN bus communication board, IO board.

[0044] A hardware-in-the-loop calibration device, the device comprising:

[0045] The model creation module is used to create vehicle dynamics models and intelligent driving control system models.

[0046] The working condition and scenario creation module is used to construct multiple typical working conditions and multiple intelligent driving scenarios for vehicle operation;

[0047] The test environment construction module is used to construct the HiL bench test environment based on the vehicle dynamics model and the intelligent driving control system model. The HiL bench test environment is used to perform hardware-in-the-loop calibration of the intelligent driving system and chassis electronic steering system under multiple typical working conditions and multiple intelligent driving scenarios.

[0048] The calibration module is used to perform open-loop calibration of the chassis electronic steering system and / or closed-loop calibration of the intelligent driving system using the HiL bench test environment.

[0049] An electronic device includes: a processor; and a memory for storing processor-executable instructions.

[0050] The processor is configured to execute the instructions to implement the hardware-in-the-loop calibration method described above.

[0051] A computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a mobile terminal, enables the mobile terminal to perform the hardware-in-the-loop calibration method described above.

[0052] A vehicle comprising the aforementioned electronic equipment.

[0053] The beneficial effects of this invention are:

[0054] In this embodiment of the invention, by constructing a HiL bench test environment, the calibration of the intelligent driving system and the chassis electronic steering system under different typical working conditions and intelligent driving scenarios is achieved. Calibration within the HiL bench test environment reduces reliance on real-vehicle testing, shortens the calibration cycle, and the automated testing process reduces manual intervention, significantly improving calibration efficiency. The calibration scheme in this embodiment eliminates the need for frequent real-vehicle testing, saving on test vehicle usage costs, maintenance costs, and site rental fees. It also reduces the need for real-vehicle testing under high-speed or other hazardous conditions, lowering safety risks during testing. Furthermore, it reduces reliance on the experience of calibration personnel, lowering the possibility of human error and improving the consistency and reliability of calibration results. The simulation environment allows testing in various virtual scenarios, including different speeds, road conditions, and intelligent driving scenarios, ensuring the system's adaptability in changing environments. Attached Figure Description

[0055] Figure 1a This is a flowchart illustrating the steps of a hardware-in-the-loop calibration method provided in an embodiment of the present invention;

[0056] Figure 1b This is a schematic diagram of a test environment for a HiL chassis electronic steering system for intelligent driving, as provided in an embodiment of the present invention.

[0057] Figure 2a This is a flowchart illustrating the steps of a hardware-in-the-loop calibration method provided in an embodiment of the present invention;

[0058] Figure 2b This is a schematic diagram of an open-loop calibration process provided in an embodiment of the present invention;

[0059] Figure 3a This is a flowchart illustrating the steps of a hardware-in-the-loop calibration method provided in an embodiment of the present invention;

[0060] Figure 3b This is a schematic diagram of a closed-loop calibration step provided in an embodiment of the present invention;

[0061] Figure 4 This is a schematic diagram of the structure of a hardware-in-the-loop calibration device provided in an embodiment of the present invention;

[0062] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0063] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0064] It should be noted that the embodiments of the present invention may involve the use of user data. In practical applications, user-specific personal data may be used in the scheme described herein within the scope permitted by applicable laws and regulations, provided that it complies with the applicable laws and regulations of the country (e.g., with the user's explicit consent, with the user being properly notified, etc.).

[0065] Reference Figure 1a The diagram illustrates a hardware-in-the-loop calibration method provided in an embodiment of the present invention, which specifically includes the following steps:

[0066] Step 101: Create the vehicle dynamics model and intelligent driving control system model;

[0067] This invention relates to a hardware-in-the-loop (HiL) calibration method for the integration of intelligent driving and chassis electronic steering systems, specifically enabling open-loop calibration of the vehicle chassis electronic steering system and closed-loop calibration of the vehicle intelligent driving system.

[0068] In practical applications, vehicle dynamics models can be established, which can specifically include models of the vehicle body, tires, suspension system, drive and braking systems, etc.

[0069] In practical applications, to ensure the accuracy of the created model, the completed vehicle model can be verified. The specific verification process may include collecting response data such as steering wheel angle and torque, vehicle speed, acceleration and deceleration, lateral acceleration and yaw rate of the actual vehicle under different working conditions; comparing and analyzing the consistency between the output of the simulation model and the test data to ensure the accuracy of the vehicle model.

[0070] To construct the calibration environment, intelligent driving control system models can also be created, which may include sensor models such as millimeter-wave radar models, vision sensor models, lidar sensor models, environmental recognition models, decision planning models, control command models, and other models.

[0071] In this embodiment of the invention, both the vehicle dynamics model and the intelligent driving control system model are models used to simulate vehicle control logic.

[0072] Step 102: Construct multiple typical operating conditions and multiple intelligent driving scenarios for vehicle operation;

[0073] Typical operating conditions, as shown in Table 1, include various typical operating conditions where the vehicle requests amplitude and frequency at different speeds, different turning directions, and different turning angles. Different vehicle speeds: 0 kph—200 kph, with a speed interval of 40 kph; different turning angle input methods: turning angle ramp signal, turning angle sine signal, etc.; different turning angle amplitudes: 0°—maximum turning angle, with a turning angle interval of 50°; different turning angular velocities: 0° / s—500° / s, with a turning velocity interval of 50° / s.

[0074] Table 1 Typical Open-Loop Operating Conditions

[0075]

[0076] Intelligent driving scenarios, as shown in Table 2, include, but are not limited to, the application scenarios of intelligent driving assistance systems such as Lane Keeping Assist (LKA), Lane Centering Control (LCC), Lane Departure Prevention (LDP), Lane Departure Warning (LDW), Automatic Parking (APA), Automatic Emergency Steering (AES), and Emergency Steering Assist (ESA).

[0077] Table 2 Intelligent Driving Scenarios

[0078]

[0079] The construction of intelligent driving scenarios includes the following steps:

[0080] (1) Construct diverse roads (straight lines, ramps, curves with various radii of curvature, intersections, etc.), road edges, dashed lines and solid lines (clear, worn);

[0081] (2) Construct various parking space scenarios (straight, side, and angled parking spaces), and parking lines (clear, worn, and without parking lines);

[0082] (3) Build a driver model: Set driving behaviors at different vehicle speeds;

[0083] (4) Environmental simulation: such as lighting conditions, rainy days, fog and haze, high-density parking lots and other complex scenarios;

[0084] (5) Create traffic scenes: Add different dynamic vehicles (stationary, low speed, emergency lane change), pedestrians, bicycles, animals, traffic signs, buildings, etc.;

[0085] (6) Sensor configuration: Configure a front camera for detecting lane lines, vehicles ahead and obstacles; equip with a lidar for measuring the distance and relative speed of vehicles ahead.

[0086] Step 103: Construct the HiL bench test environment based on the vehicle dynamics model and the intelligent driving control system model. The HiL bench test environment is used to perform hardware-in-the-loop calibration of the intelligent driving system and chassis electronic steering system under multiple typical working conditions and multiple intelligent driving scenarios.

[0087] In this embodiment of the invention, a HiL bench test environment can be constructed based on a vehicle dynamics model and an intelligent driving control system model. The HiL bench test environment can simulate vehicle control based on the vehicle dynamics model and the intelligent driving control system model, thereby achieving calibration.

[0088] The HiL bench test environment can perform hardware-in-the-loop calibration of intelligent driving systems and chassis electronic steering systems under multiple typical operating conditions and multiple intelligent driving scenarios. The HiL bench test environment has universal applicability and can calibrate vehicle parameters under different typical operating conditions and different intelligent driving scenarios. Parameter calibration can also be performed through the HiL bench test environment without the need for actual vehicle testing.

[0089] In one embodiment of the present invention, the HiL bench test environment is constructed based on a vehicle dynamics model and an intelligent driving control system model, including the following sub-steps:

[0090] Sub-step 11: Load the real-time simulator and add the hardware devices corresponding to the HiL bench test environment to the real-time simulator;

[0091] The real-time simulator is the core hardware of the HIL system. It possesses deterministic real-time performance, capable of running simulation models and completing calculations within a defined timeframe. By loading the real-time simulator, high-fidelity vehicle models can be run, ensuring strict synchronization between model computations and real-world time. Specifically, this is achieved by starting a real-time operating system (such as NI VeriStand, dSPACE SCALEXIO, etc.) on the real-time simulator, thus preparing the environment for running the model.

[0092] Furthermore, the hardware devices corresponding to the HiL bench test environment were added to the real-time simulator, thus establishing a bridge between the virtual world and real hardware.

[0093] In one example, the hardware device includes one or more of the following:

[0094] CAN bus communication board, IO board.

[0095] The CAN bus board can be used to communicate with the steering ECU. The real-time simulator can send virtual vehicle status information (such as vehicle speed, engine speed, steering wheel angle sensor signal, etc.) to the ECU via the CAN card, and receive control commands (such as target auxiliary torque) from the ECU.

[0096] I / O boards (including D / A, A / D, DIO, PWM, etc.) can be used to connect and process analog and digital signals. For example: receiving motor control signals (PWM) from the steering ECU; sending analog torque sensor signals (analog voltage) to the steering ECU; and connecting to a fault injection unit to simulate short circuits / open circuits (digital I / O).

[0097] Sub-step 12: Add the vehicle dynamics model, intelligent driving control system model, multiple typical working conditions, and multiple intelligent driving scenarios to the real-time simulator.

[0098] In practical applications, vehicle dynamics models, intelligent driving control system models, multiple typical working conditions, and multiple intelligent driving scenarios can be added to the real-time simulator to simulate the operating environment and controlled object of the steering system.

[0099] Sub-step 13: Connect the real-time simulator to the HiL cabinet and the HiL hardware system, and configure the HiL bench test environment.

[0100] By connecting the real-time simulator to the HiL steering cabinet and steering hardware system, it is possible to connect the real steering ECU and its actuators (such as EPS motors) and sensors to the test system, forming a complete "hardware-in-the-loop" test environment.

[0101] In practical applications, the HiL bench test environment can be configured to keep the state of the entire test bench consistent with that of a real vehicle or a specific test scenario. Specifically, configuration operations such as CAN communication configuration, power management configuration, and test scenario initialization configuration can be performed.

[0102] Step 104: Use the HiL bench test environment to perform open-loop calibration of the chassis electronic steering system and / or closed-loop calibration of the intelligent driving system.

[0103] After constructing the HiL bench test environment, it is possible to perform open-loop calibration of the chassis electronic steering system and closed-loop calibration of the intelligent driving system.

[0104] like Figure 1bThe diagram shown illustrates a test environment for a HiL (High-Level Intelligent Steering) chassis-based electronic steering system, as described in an embodiment of the present invention. The HiL bench may include a host computer, a switch, and a real-time simulator. The real-time simulator may include a central processing unit, I / O boards, and a CAN card. The constructed vehicle dynamics model, intelligent driving control model, and intelligent scenarios can be applied to the HiL bench to calibrate vehicle parameters.

[0105] In this embodiment of the invention, by constructing a HiL bench test environment, the calibration of the intelligent driving system and the chassis electronic steering system under different typical working conditions and intelligent driving scenarios is achieved. Calibration within the HiL bench test environment reduces reliance on real-vehicle testing, shortens the calibration cycle, and the automated testing process reduces manual intervention, significantly improving calibration efficiency. The calibration scheme in this embodiment eliminates the need for frequent real-vehicle testing, saving on test vehicle usage costs, maintenance costs, and site rental fees. It also reduces the need for real-vehicle testing under high-speed or other hazardous conditions, lowering safety risks during testing. Furthermore, it reduces reliance on the experience of calibration personnel, lowering the possibility of human error and improving the consistency and reliability of calibration results. The simulation environment allows testing in various virtual scenarios, including different speeds, road conditions, and intelligent driving scenarios, ensuring the system's adaptability in changing environments.

[0106] Reference Figure 2a The flowchart illustrates another hardware-in-the-loop calibration method provided in an embodiment of the present invention, which specifically includes the following steps:

[0107] Step 201: Create the vehicle dynamics model and the intelligent driving control system model;

[0108] Step 202: Construct multiple typical operating conditions and multiple intelligent driving scenarios for vehicle operation;

[0109] Step 203: Construct the HiL bench test environment based on the vehicle dynamics model and the intelligent driving control system model. The HiL bench test environment is used to perform hardware-in-the-loop calibration of the intelligent driving system and chassis electronic steering system under multiple typical working conditions and multiple intelligent driving scenarios.

[0110] Step 204: Determine the first target item for the open-loop calibration of the chassis electronic steering system;

[0111] In practical applications, an objective performance evaluation index system for the chassis electronic steering system under various typical operating conditions can be established. This objective performance evaluation index system may include, but is not limited to, objective evaluation indicators such as angle control reaction time, time difference to reach the target angle, EPS execution angle error, EPS execution angle overshoot, maximum limit of the response steering angle, and reverse request response time, which serve as target items for the chassis electronic steering system calibration. These target items are objective performance evaluation indicators under various typical operating conditions.

[0112] Step 205: Select the first parameter to be calibrated for the chassis electronic steering system based on the first target item;

[0113] The first parameter to be calibrated refers to the parameters that need to be calibrated during software development, including but not limited to calibrable parameters such as the proportional, integral, and derivative coefficients and damping coefficients of the chassis electronic steering system. The first parameter to be calibrated is the variable that affects the first target item; by calibrating different parameters, the target item is achieved.

[0114] Step 206: Determine the first test plan corresponding to the first parameter to be calibrated;

[0115] After determining the first parameter to be calibrated, a first test plan can be set for the first parameter to be calibrated. The first test plan is the design idea for accurately calibrating the first parameter to be calibrated.

[0116] Step 207: According to the first test plan, call the HiL bench test environment to conduct the test and obtain the first recalibration parameters and the first parameter range;

[0117] After constructing the first test plan, the HiL bench test environment can be called to conduct the test. Based on the test structure, the first recalibration parameters and the first parameter range can be determined.

[0118] Step 208: Optimize the first recalibration parameters and the first parameter range to obtain the first calibration parameters.

[0119] Once the first recalibration parameters and the first parameter range are obtained, a preset optimization scheme can be used for optimization to obtain the first calibration parameters. The first calibration parameters can be used as standard parameters for vehicle operation.

[0120] In one embodiment of the present invention, determining the first test plan corresponding to the first parameter to be calibrated includes: determining the upper limit and lower limit of the first parameter to be calibrated; and generating a first test matrix of the first parameter to be calibrated based on the upper limit and lower limit.

[0121] In practical applications, setting upper and lower limits serves to define a reasonable range for the variation of the parameter to be calibrated. Within this reasonable range, sampling is performed, an experimental matrix is ​​designed, and the critical calibration parameters can be output based on the experimental results. The upper and lower limits of the critical calibration parameters must not exceed the upper and lower limits of the parameter to be calibrated. These upper and lower limits are variables (the parameter to be calibrated) and are not used as scoring criteria.

[0122] In one example, methods for setting the upper and lower limits of the parameter to be calibrated include, but are not limited to, the actual physical meaning of the parameter, the value range set during the software development phase, and scaling a single initial value by ±50%. The single initial value setting is based on a set of parameters given by engineering experience, physical meaning, and parameter identification techniques. ±50% is a commonly used method in engineering for setting the upper and lower limits of the parameter to be calibrated, and can be used to generate subsequent experimental matrices.

[0123] In practical applications, the first experimental matrix of the first parameter to be calibrated can be generated by methods including but not limited to the optimal Latin hypercube design method, the Latin hypercube design method, the orthogonal experimental method, and the parametric experiment.

[0124] In one embodiment of the present invention, the HiL bench test environment is called according to the test plan to conduct the test and obtain the first key calibration parameters and the first parameter range, including: determining the open-loop calibration conditions corresponding to the parameters to be calibrated based on the chassis electronic steering system; converting the first test matrix into a test sequence according to the open-loop calibration conditions; running the test sequence in the HiL bench test environment to obtain the test results;

[0125] The first-stage recalibration parameters and their ranges were determined based on the experimental results. Methods used to determine these parameters included, but were not limited to, plotting Pareto charts, correlation plots, main effects plots, and delivery effect plots.

[0126] In one embodiment of the present invention, the first recalibration parameter and the first parameter range are optimized to obtain the first calibration parameter, including: establishing a response surface model between the calibration parameter and the calibration target based on the first recalibration parameter and the first parameter range; and using a multi-objective optimization method to perform global optimization on the response surface model to determine the first calibration parameter under typical working conditions.

[0127] In practical applications, a response surface model between the calibration parameters and the calibration target can be established using polynomial fitting. Based on this model, an intelligent multi-objective optimization method can be employed to perform global optimization and determine calibration data under typical operating conditions. This intelligent optimization method includes, but is not limited to, the second-generation non-neighborhood genetic algorithm.

[0128] Reference Figure 2bThis is a schematic diagram of an open-loop calibration process in an embodiment of the present invention. It may include processes such as determining the target items for the open-loop calibration of the chassis electronic steering system, selecting the parameters to be calibrated for the chassis electronic steering system, designing an experimental plan, conducting experiments and collecting data, outputting key calibration parameters, establishing a response surface model, and optimizing the calibration parameters.

[0129] In this embodiment of the invention, by constructing a HiL bench test environment, the chassis electronic steering system is calibrated under different typical working conditions and different intelligent driving scenarios. Calibration within the HiL bench test environment reduces reliance on real-vehicle testing, shortens the calibration cycle, and the automated testing process reduces manual intervention, significantly improving calibration efficiency. The calibration scheme in this embodiment eliminates the need for frequent real-vehicle testing, saving on test vehicle usage costs, maintenance costs, and site rental fees. It also reduces the need for real-vehicle testing under high-speed or other hazardous conditions, lowering safety risks during testing. Furthermore, it reduces reliance on the experience of calibration personnel, lowering the possibility of human error and improving the consistency and reliability of calibration results. The simulation environment allows testing in various virtual scenarios, including different speeds, road conditions, and intelligent driving scenarios, ensuring the system's adaptability in changing environments.

[0130] Reference Figure 3a The flowchart illustrates another hardware-in-the-loop calibration method provided in an embodiment of the present invention, which specifically includes the following steps:

[0131] Step 301: Create the vehicle dynamics model and the intelligent driving control system model;

[0132] Step 302: Construct multiple typical operating conditions and multiple intelligent driving scenarios for vehicle operation;

[0133] Step 303: Construct the HiL bench test environment based on the vehicle dynamics model and the intelligent driving control system model. The HiL bench test environment is used to perform hardware-in-the-loop calibration of the intelligent driving system and chassis electronic steering system under multiple typical working conditions and multiple intelligent driving scenarios.

[0134] Step 304: Determine the second target item for the closed-loop calibration of the intelligent driving system;

[0135] In practical applications, the goals of closed-loop calibration of intelligent driving systems can be determined, and a subjective evaluation system for the performance of chassis electronic steering systems in various intelligent driving scenarios can be established. This includes, but is not limited to, system stability and response speed in LKA function, and comprehensive evaluation of the function's handling stability and ride comfort during operation; human-computer interaction evaluation such as alarm sensitivity, alarm sound, and vibration intensity in LDW function; and subjective evaluation indicators such as parking process smoothness, confidence, parking completion effect, and recognition of special obstacles in APA function, which serve as the goals for chassis electronic steering system calibration.

[0136] Step 305: Establish a deep neural network model for intelligent driving; the deep neural network model is a model that represents the correlation between subjective evaluation scoring data and objective test data.

[0137] Establishing a consistency model for objective and subjective evaluation of intelligent driving is a model that correlates objective test indicators of intelligent driving vehicles with subjective evaluations based on intelligent driving scenarios. This may include the following steps:

[0138] (1) Data collection: Record the subjective evaluation scores of actual vehicles in intelligent driving scenarios (such as LKA, APA, LDW, ACC, etc.), and collect the objective test indicators of actual vehicles (such as yaw rate gain, lateral acceleration, longitudinal acceleration, roll angle gradient, vehicle pitch angle gradient, etc.). Divide the subjective and objective data into two parts: one part is used for training modeling (the data volume accounts for 70% of the total data volume), and the other part is used for model testing (the remaining data except for the data used for training modeling).

[0139] (2) Using deep neural network methods, a deep neural network model was established for subjective evaluation scoring data and objective test data;

[0140] (3) Based on the remaining subjective and objective data from step (1), verify the accuracy of the deep neural network model from step (2).

[0141] Step 306: Based on the target item, call the HiL bench test environment to perform the test and obtain objective test data of the target;

[0142] Step 307: Input the objective test data of the target into the neural network model and output the subjective evaluation score data corresponding to the objective test data of the target.

[0143] Step 308: Perform sensitivity analysis based on subjective evaluation scoring data to obtain the second recalibration parameters and the range of the second parameter;

[0144] In practical applications, sensitivity analysis can be performed during the calibration of intelligent driving systems. Sensitivity analysis can include selecting calibration parameters, setting upper and lower limits for these parameters, designing test matrices, and collecting test results. Calibration parameters include, but are not limited to, speed limit thresholds, following distance, offset distance parameters, offset frequency, lane change mode, trajectory smoothing parameters, vibration level amplitude, vibration duration, and vibration interval duration.

[0145] Step 309: Optimize the second calibration parameters and the range of the second parameter to obtain the second calibration parameters.

[0146] In one embodiment of the present invention, the second calibration parameter is optimized to obtain the second calibration parameter by: using the expected score in the subjective evaluation scoring data as the calibration target, and establishing a response surface model between the calibration parameter and the calibration target with the second calibration parameter and the second parameter range; and using a multi-objective optimization method to perform global optimization on the response surface model to determine the second calibration parameter under typical working conditions.

[0147] like Figure 3b The diagram shown illustrates a closed-loop calibration step in an embodiment of the present invention. It may include the following process: determining the target items for closed-loop calibration of the intelligent driving system; establishing a consistency model of subjective and objective evaluation for intelligent driving (based on collected subjective scores and objective test data from actual vehicles); running the chassis electronic control HiL test bench; collecting objective test data from the test bench; outputting the consistency model of subjective and objective evaluation; outputting the vehicle's subjective score in intelligent scenarios; sensitivity analysis; outputting key calibration parameters and their ranges; designing the test matrix; calibrating key parameters; determining whether the expected score is met; and outputting calibration data if the expected score is met, otherwise returning to the test matrix design and recalibrating.

[0148] In this embodiment of the invention, by constructing a HiL bench test environment, the calibration of the intelligent driving system under different typical operating conditions and intelligent driving scenarios is achieved. Calibration within the HiL bench test environment reduces reliance on real-vehicle testing, shortens the calibration cycle, and the automated testing process reduces manual intervention, significantly improving calibration efficiency. The calibration scheme in this embodiment eliminates the need for frequent real-vehicle testing, saving on the cost of test vehicle use, maintenance, and site rental. It also reduces the need for real-vehicle testing under high-speed or other hazardous conditions, lowering safety risks during testing. Furthermore, it reduces reliance on the experience of calibration personnel, reducing the possibility of human error and improving the consistency and reliability of calibration results. The simulation environment allows testing in various virtual scenarios, including different speeds, road conditions, and intelligent driving scenarios, ensuring the system's adaptability in changing environments.

[0149] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0150] Reference Figure 4 The diagram illustrates a hardware-in-the-loop calibration device provided in an embodiment of the present invention, which specifically includes the following modules:

[0151] Model creation module 401 is used to create vehicle dynamics models and intelligent driving control system models.

[0152] The working condition and scenario creation module 402 is used to construct multiple typical working conditions and multiple intelligent driving scenarios for vehicle operation;

[0153] The test environment construction module 403 is used to construct the HiL bench test environment based on the vehicle dynamics model and the intelligent driving control system model. The HiL bench test environment is used to perform hardware-in-the-loop calibration of the intelligent driving system and chassis electronic steering system under multiple typical working conditions and multiple intelligent driving scenarios.

[0154] The calibration module 404 is used to perform open-loop calibration of the chassis electronic steering system and / or closed-loop calibration of the intelligent driving system using the HiL bench test environment.

[0155] In one embodiment of the present invention, the test environment construction module 403 may include:

[0156] The simulator loading submodule is used to load the real-time simulator and add the hardware devices corresponding to the HiL bench test environment to the real-time simulator;

[0157] The data addition submodule is used to add the vehicle dynamics model, the intelligent driving control system model, the multiple typical working conditions, and the multiple intelligent driving scenarios to the real-time simulator.

[0158] The configuration submodule is used to connect the real-time simulator to the HiL cabinet and the HiL hardware system, and to configure the HiL bench test environment.

[0159] In one embodiment of the present invention, the calibration module 404 may include:

[0160] The first target item determination submodule is used to determine the first target item of the open-loop calibration of the chassis electronic steering system.

[0161] The first parameter to be calibrated determination submodule is used to select the first parameter to be calibrated of the chassis electronic steering system based on the first target item.

[0162] The first test scheme determination submodule is used to determine the first test scheme corresponding to the first parameter to be calibrated.

[0163] The first recalibration parameter determination submodule is used to call the HiL bench test environment to perform tests according to the first test plan, and obtain the first recalibration parameters and the first parameter range.

[0164] The first optimization submodule is used to optimize the first critical calibration parameters and the first parameter range to obtain the first calibration parameters.

[0165] In one embodiment of the present invention, the first test scheme determination submodule may include:

[0166] The first limit determination unit is used to determine the upper limit and lower limit values ​​of the first parameter to be calibrated;

[0167] The first test matrix determination unit is used to generate a first test matrix for the first parameter to be calibrated based on the upper limit value and the lower limit value.

[0168] In one embodiment of the present invention, the first criticality calibration parameter determination submodule may include:

[0169] An open-loop calibration condition determination unit is used to determine the open-loop calibration condition corresponding to the parameter to be calibrated based on the chassis electronic steering system.

[0170] The test sequence determination unit is used to convert the first test matrix into a test sequence according to the open-loop calibration conditions.

[0171] The test result determination unit is used to run the test sequence in the HiL bench test environment to obtain the test results.

[0172] The first recalibration parameter determination unit is used to determine the first recalibration parameters and the range of the first parameters based on the test results.

[0173] In one embodiment of the present invention, the first optimization submodule may include:

[0174] The first response surface parameter determination unit is used to establish a response surface model between the calibration parameters and the calibration target based on the first critical calibration parameters and the first parameter range;

[0175] The first calibration parameter determination unit is used to perform global optimization using a multi-objective optimization method on the response surface model to determine the first calibration parameters under typical working conditions.

[0176] In one embodiment of the present invention, the calibration module 404 may include:

[0177] The second target item determination submodule is used to determine the second target item for the closed-loop calibration of the intelligent driving system.

[0178] The second parameter to be calibrated determination submodule is used to select the second parameter to be calibrated of the intelligent driving system based on the second target item;

[0179] The second test scheme determination submodule is used to determine the second test scheme corresponding to the second parameter to be calibrated.

[0180] The second recalibration parameter determination submodule is used to call the HiL bench test environment to perform tests according to the second test plan, and obtain the second recalibration parameters and the second parameter range.

[0181] The second optimization submodule is used to optimize the second critical calibration parameters and the second parameter range to obtain the second calibration parameters.

[0182] In one embodiment of the present invention, the second optimization submodule may include:

[0183] A deep neural network model building unit is used to build a deep neural network model for intelligent driving; the deep neural network model is a model that represents the correlation between subjective evaluation scoring data and objective test data.

[0184] The objective test data determination unit is used to call the HiL bench test environment to perform tests based on the target item and obtain objective test data of the target.

[0185] The subjective evaluation scoring data determination unit is used to input the target objective test data into the neural network model and output the subjective evaluation scoring data corresponding to the target objective test data.

[0186] The response surface model determination unit is used to establish a response surface model between the calibration parameters and the calibration target by using the expected score in the subjective evaluation scoring data as the calibration target, and the second key calibration parameters and the second parameter range.

[0187] The second calibration parameter determination unit is used to perform global optimization using a multi-objective optimization method on the response surface model to determine the second calibration parameters under typical working conditions.

[0188] In one embodiment of the present invention, the hardware device includes any one or more of the following:

[0189] CAN bus communication board, IO board.

[0190] In this embodiment of the invention, by constructing a HiL bench test environment, the calibration of the intelligent driving system and the chassis electronic steering system under different typical working conditions and intelligent driving scenarios is achieved. Calibration within the HiL bench test environment reduces reliance on real-vehicle testing, shortens the calibration cycle, and the automated testing process reduces manual intervention, significantly improving calibration efficiency. The calibration scheme in this embodiment eliminates the need for frequent real-vehicle testing, saving on test vehicle usage costs, maintenance costs, and site rental fees. It also reduces the need for real-vehicle testing under high-speed or other hazardous conditions, lowering safety risks during testing. Furthermore, it reduces reliance on the experience of calibration personnel, lowering the possibility of human error and improving the consistency and reliability of calibration results. The simulation environment allows testing in various virtual scenarios, including different speeds, road conditions, and intelligent driving scenarios, ensuring the system's adaptability in changing environments.

[0191] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0192] This invention also provides an electronic device, such as... Figure 5 As shown, it includes a processor 501, a device interface 502, a memory 503, and a bus 504;

[0193] Memory 503 is used to store computer programs;

[0194] The processor 501 performs the above steps when executing the program stored in the memory 503.

[0195] The bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0196] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0197] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0198] The present invention also provides a storage medium that, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the hardware-in-the-loop calibration method of the foregoing embodiments.

[0199] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0200] The algorithms and displays provided herein are not inherently related to any particular computer, virtual device, or other equipment. The structure required to construct such a device is readily apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0201] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0202] Similarly, it should be understood that, in order to simplify the invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed invention requires more features than expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0203] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0204] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the sorting device according to the present invention. The present invention can also be implemented as a device or apparatus program for performing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0205] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0206] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0207] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0208] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0209] It should be noted that the various data-related processes in the embodiments of this application are carried out in compliance with the relevant data protection laws and policies of the country where the location is located, and with the authorization granted by the owner of the corresponding device.

Claims

1. A hardware-in-the-loop calibration method, characterized in that, The method includes: Create vehicle dynamics models and intelligent driving control system models; Construct multiple typical operating conditions and multiple intelligent driving scenarios for vehicle operation; The HiL bench test environment is constructed based on the vehicle dynamics model and the intelligent driving control system model. The HiL bench test environment is used to perform hardware-in-the-loop calibration of the intelligent driving system and chassis electronic steering system under multiple typical working conditions and multiple intelligent driving scenarios. The HiL bench test environment was used to perform open-loop calibration of the chassis electronic steering system and closed-loop calibration of the intelligent driving system. The construction of the HiL bench test environment based on the vehicle dynamics model and the intelligent driving control system model includes: Load the real-time simulator and add the hardware devices corresponding to the HiL bench test environment to the real-time simulator; The vehicle dynamics model, the intelligent driving control system model, the multiple typical working conditions, and the multiple intelligent driving scenarios are added to the real-time simulator. Connect the real-time simulator to the HiL cabinet and the HiL hardware system, and configure the HiL bench test environment. The open-loop calibration of the chassis electronic steering system and the closed-loop calibration of the intelligent driving system using the HiL bench test environment include: Determine the second target item for the closed-loop calibration of the intelligent driving system; A deep neural network model for intelligent driving is established; the deep neural network model is a model that represents the correlation between subjective evaluation scoring data and objective test data. Based on the second target item, the HiL bench test environment is invoked to perform the test and obtain objective test data of the target. The objective test data of the target is input into the deep neural network model, and the subjective evaluation score data corresponding to the objective test data of the target is output. The HiL bench test environment was used to perform open-loop calibration of the chassis electronic steering system, and the subjective evaluation was used to perform closed-loop calibration of the intelligent driving system.

2. The method according to claim 1, characterized in that, The open-loop calibration of the chassis electronic steering system and the closed-loop calibration of the intelligent driving system using the HiL bench test environment include: Determine the first target item for the open-loop calibration of the chassis electronic steering system; Based on the first target item, the first parameter to be calibrated for the chassis electronic steering system is selected; Determine the first test plan corresponding to the first parameter to be calibrated; According to the first test plan, the HiL bench test environment is called to perform the test, and the first recalibration parameters and the first parameter range are obtained. The first calibration parameters and the first parameter range are optimized to obtain the first calibration parameters.

3. The method according to claim 2, characterized in that, The step of determining the first test plan corresponding to the first parameter to be calibrated includes: Determine the upper and lower limits of the first parameter to be calibrated; The first test matrix of the first parameter to be calibrated is generated based on the upper and lower limits.

4. The method according to claim 3, characterized in that, The step of calling the HiL bench test environment according to the first test plan to perform the test, and obtaining the first recalibration parameters and the first parameter range, includes: Based on the chassis electronic steering system, determine the open-loop calibration condition corresponding to the first parameter to be calibrated; The first test matrix is ​​converted into a test sequence according to the open-loop calibration conditions described above; The test sequence is run in the HiL bench test environment to obtain the test results; The first recalibration parameters and the range of the first parameters were determined based on the test results.

5. The method according to claim 2, characterized in that, The optimization of the first key calibration parameter and the first parameter range to obtain the first calibration parameter includes: A response surface model between the calibration parameters and the calibration target is established based on the first key calibration parameters and the first parameter range; A multi-objective optimization method is used to perform global optimization on the response surface model to determine the first calibration parameter under typical operating conditions.

6. The method according to claim 1, characterized in that, The closed-loop calibration of the intelligent driving system based on the subjective evaluation includes: Sensitivity analysis was performed based on the subjective evaluation scoring data to obtain the second recalibration parameter and the range of the second parameter. The second calibration parameters and the range of the second parameter are optimized to obtain the second calibration parameters.

7. The method according to claim 6, characterized in that, The optimization of the second critical calibration parameters and the range of the second parameters to obtain the second calibration parameters includes: Using the expected score in the subjective evaluation scoring data as the calibration target, a response surface model between the calibration parameters and the calibration target is established with the second critical calibration parameter and the range of the second parameter. A multi-objective optimization method is used to perform global optimization on the response surface model to determine the second calibration parameter under typical operating conditions.

8. The method according to claim 1, characterized in that, The hardware device includes any one or more of the following: CAN bus communication board, IO board.

9. A hardware-in-the-loop calibration device, characterized in that, The device includes: The model creation module is used to create vehicle dynamics models and intelligent driving control system models. The working condition and scenario creation module is used to construct multiple typical working conditions and multiple intelligent driving scenarios for vehicle operation; The test environment construction module is used to construct the HiL bench test environment based on the vehicle dynamics model and the intelligent driving control system model. The HiL bench test environment is used to perform hardware-in-the-loop calibration of the intelligent driving system and chassis electronic steering system under multiple typical working conditions and multiple intelligent driving scenarios. The calibration module is used to perform open-loop calibration of the chassis electronic steering system and closed-loop calibration of the intelligent driving system using the HiL bench test environment. The test environment construction module includes: The simulator loading submodule is used to load the real-time simulator and add the hardware devices corresponding to the HiL bench test environment to the real-time simulator; The data addition submodule is used to add the vehicle dynamics model, the intelligent driving control system model, the multiple typical working conditions, and the multiple intelligent driving scenarios to the real-time simulator. The configuration submodule is used to connect the real-time simulator to the HiL cabinet and the HiL hardware system, and to configure the HiL bench test environment. The calibration module is used to determine the second target item for the closed-loop calibration of the intelligent driving system; establish a deep neural network model for intelligent driving; the deep neural network model is a model representing the correlation between subjective evaluation scoring data and objective test data; call the HiL bench test environment based on the second target item to perform testing and obtain target objective test data; input the target objective test data into the deep neural network model and output the subjective evaluation scoring data corresponding to the target objective test data; use the HiL bench test environment to perform open-loop calibration of the chassis electronic steering system, and perform closed-loop calibration of the intelligent driving system based on the subjective evaluation.

10. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to execute the instructions to implement the hardware-in-the-loop calibration method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the mobile terminal, the mobile terminal is able to perform the hardware-in-the-loop calibration method as described in any one of claims 1 to 8.

12. A vehicle, characterized in that, The vehicle includes the electronic equipment as described in claim 10.

Images