Virtual scene generation method, system and device for vehicle stability development and medium

Abstract

The method is mainly applied to the technical field of vehicle engineering. The invention discloses a virtual scene generation method, system and device for vehicle stability development and a medium, and the method comprises the steps: building a systematic constraint condition of a multi-parameter coupling relation based on a preset multi-level function scene model, and determining a parameter coupling boundary of a key scene according to the systematic constraint condition; selecting a parameter combination in the parameter coupling boundary, and generating and covering all conventional scenes and dangerous scenes possibly causing instability according to the selected parameter combination; based on a preset safety standard or physical constraint, performing compliance screening on each conventional scene and each dangerous scene; and generating a comprehensive scene library for virtual calibration of the chassis electric control system according to the plurality of screened scenes. According to the invention, the efficiency and quality of virtual calibration of the chassis electric control system can be obviously improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle engineering technology, specifically to a method, system, device, and medium for generating virtual scenes for vehicle stability development. Background Technology

[0002] With the accelerated development of automotive intelligence, the functional complexity and coupling of chassis electronic control systems are constantly increasing, making safety verification and calibration a key bottleneck restricting the development cycle. Traditional calibration methods relying on real-vehicle road testing face problems such as high cost, long cycle time, and difficulty in reproducing risk scenarios. As a result, virtual calibration technology has become the mainstream solution in the industry. The effectiveness of virtual calibration is highly dependent on the coverage and realism of the test scenarios, and there is an urgent need to build a large-scale, highly generalized scenario library that conforms to physical constraints.

[0003] The fundamental flaw in existing scene generation methods lies in the lack of systematic modeling of vehicle dynamics constraints and multi-parameter coupling relationships. Chassis electronic control scenarios involve multi-dimensional parameters with strong nonlinear coupling and strict physical boundaries. Existing technologies either simplify these constraints or post-process dynamics verification, leading to a sharp contradiction between "statistical coverage" and "physical validity": pursuing coverage results in a surge in invalid scenarios; while strictly ensuring validity artificially compresses the exploration space, making it difficult to reach the system's safety boundaries. Therefore, there is an urgent need for a scene generation method that can endogenously integrate dynamic mechanisms, automatically identify physical limits, and balance coverage and validity. Summary of the Invention

[0004] This invention provides a method, system, device, and medium for generating virtual scenarios for vehicle stability development, which can significantly improve the efficiency and quality of virtual calibration of chassis electronic control systems.

[0005] This invention provides a method for generating virtual scenes for vehicle stability development, the method comprising: Based on a pre-defined multi-level functional scenario model, a systematic constraint condition for multi-parameter coupling relationship is constructed, and the parameter coupling boundary of key scenarios is determined according to the systematic constraint condition. Within the parameter coupling boundary, select parameter combinations and generate all normal and dangerous scenarios that may lead to instability based on the selected parameter combinations; Based on preset safety standards or physical constraints, compliance screening is performed on each of the conventional scenarios and each of the hazardous scenarios; A comprehensive scenario library for virtual calibration of the chassis electronic control system is generated based on multiple selected scenarios.

[0006] Optionally, methods for determining the parameter coupling boundaries of key scenarios include: The multi-level functional scenario model is deconstructed into a first-level scenario and a second-level scenario, wherein the first-level scenario is a scenario of macro driving task category, and the second-level scenario is a specific driving road condition scenario in the first-level scenario; For each of the secondary scenarios, a corresponding set of key parameters is generated, wherein the set of key parameters includes at least one of the following parameters: steering wheel angle, steering wheel angular velocity, vehicle speed, and road surface adhesion coefficient. Determine the value range for each parameter in the set of key parameters.

[0007] Optionally, methods for generating a regular scene based on the selected parameter combination include: For each of the aforementioned key scenarios, the vehicle speed, road surface adhesion coefficient, lateral acceleration, and longitudinal acceleration in the key scenario are determined as key parameters; The first and second values ​​are obtained by taking values ​​from the parameter ranges of the vehicle speed and the road surface adhesion coefficient using a joint bias distribution method. The third and fourth values ​​are obtained by taking values ​​from the parameter range of the lateral acceleration and the longitudinal acceleration using Latin hypercube sampling. Based on the scenario value assessment function, the first value, the second value, the third value, and the fourth value are filtered, and parameter combinations are generated based on the filtered values. Generate the corresponding conventional scene based on the parameter combination; Return to the step of taking values ​​from the parameter ranges of the vehicle speed and the road surface adhesion coefficient using the joint bias distribution method to obtain the first value and the second value. When the number of generated regular scenarios reaches the preset upper limit, each regular scenario is classified into the regular scenario set.

[0008] Optionally, the method of taking values ​​within the parameter range also includes: Select the target sampling strategy from multiple sampling strategies; After selecting one or more values ​​from the parameter range according to the target sampling strategy, the process returns to the step of selecting the target sampling strategy from multiple sampling strategies until the number of selections reaches a preset limit.

[0009] Optionally, the methods for generating hazardous scenarios based on the selected parameter combinations include: For each of the key scenarios, determine multiple key parameters within that key scenario; For each of the key parameters, the parameter range of the key parameter is determined, and the limit value selected from the parameter range is used as the physical boundary value of the key parameter; Generate multiple parameter sets, each parameter set including at least one of the key parameters; Based on the vehicle dynamics model, a region map showing the stability of the center of mass sideslip angle and yaw rate is generated using the phase plane analysis method. On the regional map, critical operating condition boundaries, including the unstable tire force saturation value and the unstable inertia parameter, are identified; The multi-objective optimization function is used to iteratively solve the problem, so as to select the dangerous parameter combination that contains the physical boundary value and makes the vehicle dynamic state approach the critical working condition boundary from the multiple parameter sets; Based on the combination of the hazard parameters, hazard scenarios are generated, and each hazard scenario is classified into a hazard scenario set.

[0010] Optionally, the method for determining the limit value includes: Determine the vehicle's dynamic response index value under the target parameter combination within the specified parameter range; When the value of the dynamic response index is equal to or greater than the preset dynamic stability threshold, the value of the target parameter combination is determined to be the limit value.

[0011] Optionally, the compliance screening for each of the conventional scenarios and each of the hazardous scenarios based on preset safety standards or physical constraints includes: Preset physical rules and conditions are applied one by one to each target scenario in the set of normal scenarios or the set of dangerous scenarios to determine whether the parameter combination of each target scenario meets the requirements, and to filter out scenarios with parameter combinations that meet the requirements. The physical rules and conditions include at least one of the following: The hydraulic system response time corresponding to the combination of braking pressure and vehicle speed is not greater than the preset maximum response time threshold. The rate of change of steering wheel angle is not greater than the maximum rate of change threshold that the sensor can measure. The tire force requirement shall not exceed the maximum available tire force threshold calculated based on the current road surface adhesion coefficient and vertical load. The combination of yaw rate and sideslip angle in the instability scenario is within the recoverable stability boundary parameters of the vehicle stability control system.

[0012] The present invention also provides a virtual scene generation system for vehicle stability development, the generation system comprising: The parameterization parsing module is used to construct systematic constraints on multi-parameter coupling relationships based on a preset multi-level functional scenario model, and to determine the parameter coupling boundaries of key scenarios according to the systematic constraints. The scene generation module is used to select parameter combinations within the parameter coupling boundary and generate all normal and dangerous scenes that may lead to instability based on the selected parameter combinations. The compliance check module is used to perform compliance screening for each of the conventional scenarios and each of the hazardous scenarios based on preset safety standards or physical constraints; The scenario library management output module is used to generate a comprehensive scenario library for virtual calibration of the chassis electronic control system based on multiple filtered scenarios.

[0013] The present invention also provides an electronic device, the electronic device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the virtual scene generation method for vehicle stability development as described in any of the preceding claims.

[0014] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the virtual scene generation method for vehicle stability development as described in any of the preceding claims.

[0015] The present invention has at least the following beneficial effects: This technical solution accurately determines the parameter coupling boundaries of key scenarios by constructing a multi-level functional scenario model and systematic constraints on multi-parameter coupling relationships. Within these boundaries, parameter combinations are selected to generate comprehensive coverage of both conventional and hazardous scenarios that may lead to instability. This systematic and comprehensive scenario generation method avoids the randomness and one-sidedness of scenario selection in traditional methods, ensuring effective calibration of the chassis electronic control system under various complex operating conditions. Simultaneously, compliance screening of scenarios based on preset safety standards or physical constraints further improves the relevance and effectiveness of the scenarios, reducing invalid or redundant scenarios and making the calibration process more efficient. The resulting comprehensive scenario library provides rich and high-quality test scenarios for the virtual calibration of the chassis electronic control system, significantly improving calibration efficiency and quality, helping to shorten the development cycle, reduce development costs, and improve the stability and reliability of the chassis electronic control system. Attached Figure Description

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

[0017] Figure 1 This is a flowchart illustrating the steps involved in a virtual scene generation method for vehicle stability development. Figure 2 This is a flowchart illustrating the steps involved in determining the parameter coupling boundary of a key scenario in a virtual scenario generation method for vehicle stability development. Figure 3 This is a flowchart illustrating the steps involved in generating a regular scene within a virtual scene generation method for vehicle stability development. Figure 4 This is a flowchart illustrating the steps involved in generating a virtual scene for vehicle stability development, specifically within a parameter range. Figure 5 This is a flowchart illustrating the steps involved in generating hazardous scenarios within a virtual scenario generation method for vehicle stability development. Figure 6 This is a flowchart of another step in a virtual scene generation method for vehicle stability development; Figure 7 This is a schematic diagram of a virtual scene generation system for vehicle stability development. Figure 8 This is a schematic diagram of the structure of an electronic device. Detailed Implementation

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

[0019] The researchers in this application found that for electronically controlled systems such as ESC and ABS, which are crucial for stability, virtual testing heavily relies on extreme operating conditions (such as split-road braking, fishhook tests, and moose tests) explicitly specified in regulations or standards. These scenarios serve as the "gold standard" for verification, but their types and parameters are relatively fixed. In a virtual environment, engineers primarily calibrate the system's threshold values ​​and control parameters by reproducing and fine-tuning these standard scenarios.

[0020] Despite advancements in existing technology, the following problems still exist: 1. The current scenario generation method has low coverage: it relies too much on a limited number of standard dangerous working conditions, which makes it impossible to systematically discover and generate all parameter-coupled extreme scenarios that may lead to instability (such as steering at low adhesion coefficient and low vehicle speed, or composite steering and braking excitation at medium and high adhesion), which makes the ability of the calibrated system to cope with unknown and complex risks vulnerable.

[0021] 2. The developed scenarios may not conform to dynamic requirements and objective physical laws: When attempting to combine new scenarios, it is easy to generate invalid scenarios that exceed the vehicle's dynamic stability boundaries. For example, a combination of "extremely high vehicle speed and extremely low adhesion coefficient" has a theoretical minimum turning radius that far exceeds the road boundary in the scenario, and the vehicle would have already run off the road before losing control. Such scenarios cannot effectively stimulate the system's stability control function; instead, due to their physical impossibility, they cause the calibration work to deviate from the correct direction.

[0022] To address the issue of insufficient coverage, the technical solution proposed in this application can transcend limited regulatory conditions and automatically and systematically explore the multi-dimensional parameter space leading to instability. By combining the extreme values ​​of parameters such as adhesion coefficient, vehicle speed, steering input, and braking input, it can discover complex coupled instability scenarios that are difficult to conceive of based on experience, providing more comprehensive test coverage for the safety boundary verification of systems such as ESC and ABS.

[0023] To address the issue of scenarios not meeting dynamic requirements, this application's technical solution integrates a vehicle dynamics stability model to ensure that the generated hazardous scenarios are all in a critical state of instability, rather than physically impossible or overly conservative invalid combinations. This provides the stability control system with "just the right" extreme stress test, ensuring that the calibrated system can be accurately and promptly triggered in real dangerous situations.

[0024] By generating massive amounts of high-quality extreme scenarios through automated processes, the technical solution of this application greatly enhances the objectivity and rigor of virtual testing. It allows the development of stable systems to proactively expose potential defects through systematic "stress testing," rather than relying on accidental discoveries, thus providing solid data support and confidence assurance for the safety and reliability of the final product. The following are various embodiments of the technical solution of this application.

[0025] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating the steps involved in generating a virtual scene for vehicle stability development.

[0026] This embodiment provides a virtual scene generation method for vehicle stability development, including: S101. Based on the preset multi-level functional scenario model, construct systematic constraints for multi-parameter coupling relationships, and determine the parameter coupling boundaries of key scenarios according to the systematic constraints.

[0027] S102. Select parameter combinations within the parameter coupling boundary, and generate all normal and dangerous scenarios that may lead to instability based on the selected parameter combinations.

[0028] S103. Based on preset safety standards or physical constraints, conduct compliance screening for each routine scenario and each hazardous scenario.

[0029] S104. Generate a comprehensive scenario library for virtual calibration of the chassis electronic control system based on multiple selected scenarios.

[0030] Understandably, this technical solution accurately determines the parameter coupling boundaries of key scenarios by constructing a multi-layered functional scenario model and systematic constraints on multi-parameter coupling relationships. Within these boundaries, parameter combinations are selected to generate comprehensive coverage of both conventional and hazardous scenarios that may lead to instability. This systematic and comprehensive scenario generation method avoids the randomness and one-sidedness of scenario selection in traditional methods, ensuring that the chassis electronic control system can be effectively calibrated under various complex operating conditions. Simultaneously, compliance screening of scenarios based on preset safety standards or physical constraints further improves the relevance and effectiveness of the scenarios, reducing invalid or redundant scenarios and making the calibration process more efficient. The resulting comprehensive scenario library provides rich and high-quality test scenarios for the virtual calibration of the chassis electronic control system, significantly improving calibration efficiency and quality, helping to shorten the development cycle, reduce development costs, and improve the stability and reliability of the chassis electronic control system.

[0031] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the steps involved in determining the parameter coupling boundaries of key scenarios in a virtual scenario generation method for vehicle stability development.

[0032] In some embodiments, the method for determining the parameter coupling boundary of a key scenario includes: S201. The multi-level functional scenario model is deconstructed into a first-level scenario and a second-level scenario. The first-level scenario is a scenario of macro driving task category, and the second-level scenario is a specific driving road condition scenario in the first-level scenario.

[0033] S202. For each secondary scenario, generate a corresponding set of key parameters, wherein the set of key parameters includes at least one of the following parameters: steering wheel angle, steering wheel angular velocity, vehicle speed, and road surface adhesion coefficient.

[0034] S203. Determine the value range for each parameter in the set of key parameters.

[0035] In some embodiments, primary scenarios refer to "low-speed parking scenarios," "urban road scenarios," and "complex curve scenarios," etc.; secondary scenarios refer to entering parking spaces, turning at intersections, and following other vehicles on high-speed curves, etc. Different functional scenarios focus on different sets of key parameters. A unique set of key parameters, P_scenario, is defined for each secondary functional scenario, and the physical range of each parameter (including steering wheel angle, steering wheel angular velocity, vehicle speed, road surface adhesion coefficient, etc.) is clearly defined.

[0036] Understandably, this embodiment further refines the scenario classification by deconstructing the multi-level functional scenario model into primary and secondary scenarios, making scenario construction more precise and specific. A set of key parameters is generated for each secondary scenario, and the value range of each parameter is clearly defined, ensuring the relevance and comprehensiveness of scenario generation. This refinement and clarification makes the generated virtual scenarios closer to real driving conditions, further improving the accuracy and reliability of the virtual calibration of the chassis electronic control system. Simultaneously, the precise parameter range setting reduces the generation of invalid scenarios, optimizes the calibration process, significantly improves calibration efficiency and quality, and provides a more efficient and high-quality virtual testing environment for the development of the chassis electronic control system.

[0037] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the steps involved in generating a standard scene within a virtual scene generation method for vehicle stability development.

[0038] In some embodiments, the method of generating a conventional scene based on the selected parameter combination includes: S301. For each key scenario, determine the vehicle speed, road surface adhesion coefficient, lateral acceleration, and longitudinal acceleration as key parameters.

[0039] S302. The first and second values ​​are obtained by taking values ​​from the parameter ranges of vehicle speed and road surface adhesion coefficient using a joint bias distribution method.

[0040] S303. The third and fourth values ​​are obtained by taking values ​​from the parameter range of lateral acceleration and longitudinal acceleration using Latin hypercube sampling.

[0041] S304. Based on the scenario value assessment function, filter the first, second, third, and fourth values ​​and generate parameter combinations based on the filtered values.

[0042] S305. Generate the corresponding conventional scene based on the parameter combination.

[0043] S306. Return to step S302. When the number of generated regular scenes reaches the preset upper limit, classify each regular scene into the regular scene set.

[0044] In one specific embodiment, during the generation of a virtual scene for vehicle stability development, values ​​need to be selected from the parameter ranges of vehicle speed and road adhesion coefficient. Assume the parameter range for vehicle speed is [20 km / h, 120 km / h], and the parameter range for road adhesion coefficient is [0.3, 0.9].

[0045] Assuming that the distribution of vehicle speed is more inclined towards medium-to-high speed scenarios, an offset distribution function f_vehicle_speed(v) is adopted to give it a higher probability density above 80km / h; the distribution of road surface adhesion coefficient is more inclined towards low adhesion coefficient scenarios, and an offset distribution function f_adhesion_coefficient(μ) is adopted to give it a higher probability density between 0.3 and 0.5.

[0046] For vehicle speed, a random number rv is generated and mapped to a bias distribution using an inverse transformation method to obtain the first value of vehicle speed v1.

[0047] For the road surface adhesion coefficient, a random number rμ is generated and mapped to the bias distribution using the inverse transformation method to obtain the second value μ1 of the adhesion coefficient.

[0048] Assuming the generated random numbers are rv=0.7 and rμ=0.4, after calculation using the bias distribution function, the vehicle speed is obtained as v1=95km / h and the adhesion coefficient is as μ1=0.42.

[0049] This embodiment, through a joint bias distribution, can flexibly adjust the probability distribution of parameter values ​​according to actual needs (such as focusing on medium-high speed or low adhesion coefficient scenarios), making the generated scenarios more targeted.

[0050] In one specific embodiment, during the generation of a virtual scene for vehicle stability development, values ​​need to be selected from the parameter ranges of lateral acceleration and longitudinal acceleration. Assume the parameter range for lateral acceleration is [0.1g, 0.5g], and the parameter range for longitudinal acceleration is [-0.3g, 0.3g].

[0051] The parameter ranges for lateral and longitudinal acceleration are divided into equally probable sub-intervals. Assume there are 10 sub-intervals, each with widths of Δa_lateral = 0.04g and Δa_longitudinal = 0.06g.

[0052] For lateral acceleration, a value is randomly selected from each sub-interval to obtain 10 sample points.

[0053] For longitudinal acceleration, a value is randomly selected from each sub-interval to obtain 10 sample points.

[0054] The sample points of lateral acceleration and longitudinal acceleration were randomly combined to form 10 sets of sample points, each set containing one lateral acceleration value and one longitudinal acceleration value.

[0055] Assume that one of the combined sample points is a lateral = 0.32g, a longitudinal = 0.15g, which is the third and fourth value.

[0056] This embodiment uses Latin hypercube sampling to ensure that sample points are evenly distributed in the parameter space, avoiding the clustering or omission problems that may be caused by random sampling, improving the representativeness and comprehensiveness of parameter values, and thus improving the quality and reliability of the generated scene.

[0057] Understandably, this embodiment further enhances the scientific rigor and effectiveness of conventional scene generation through refined parameter selection methods and scene generation processes. The combination of joint bias distribution and Latin hypercube sampling ensures the diversity and representativeness of parameter values, avoiding the bias caused by random selection. Simultaneously, the parameter combinations are screened based on a scene value evaluation function, further optimizing scene quality and ensuring that the generated conventional scenes have greater practical application value. By iteratively generating and categorizing scenes into sets, efficient and systematic scene construction is achieved. This improvement significantly enhances the generation efficiency and quality of conventional scenes, providing a more accurate and comprehensive testing foundation for the virtual calibration of chassis electronic control systems, further optimizing the calibration process, and improving the accuracy and reliability of calibration.

[0058] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating the steps involved in generating a virtual scene for vehicle stability development, specifically within a parameter range.

[0059] In some embodiments, the method of taking values ​​within the parameter range also includes: S401. Select the target sampling strategy from multiple sampling strategies.

[0060] S402. After selecting one or more values ​​from the parameter range according to the target sampling strategy, return to step S401 until the number of selections reaches the preset limit.

[0061] Understandably, this embodiment further enhances the flexibility and diversity of parameter values ​​by introducing multiple sampling strategies and dynamically selecting the target sampling strategy. By repeatedly selecting values ​​within the parameter range until a preset limit is reached, the comprehensiveness and coverage of parameter combinations are ensured. This dynamic adjustment and multiple sampling method can more accurately capture key parameter combinations that may lead to vehicle instability, generating more representative and challenging test scenarios. This not only improves the generation quality of both conventional and hazardous scenarios but also further optimizes the virtual calibration test environment, significantly improving the efficiency and quality of chassis electronic control system calibration and enhancing system stability and reliability.

[0062] In some embodiments, the user specifies the number of generalized scenarios N_regular to be generated for a specific functional scenario. The scenario generation engine can flexibly select or combine several sampling strategies based on the testing and calibration objectives, from each parameter p... iPhysical range [min i , max i The parameter values ​​are generated in the [database name] to ensure that the generated generalized scenario library can efficiently and unbiasedly cover a wider range of user driving conditions.

[0063] A risk-oriented sampling strategy is adopted to focus on covering parameter space areas that are prone to instability; a joint bias distribution is used for vehicle speed and road adhesion coefficient, and the sampling density is increased in the low adhesion and high vehicle speed area; Latin hypercube sampling is used for lateral acceleration and longitudinal acceleration to ensure uniform coverage of various acceleration combinations; a scenario value evaluation function is established to prioritize the generation of scenarios that can provide new stability information.

[0064] Ultimately, regardless of the sampling strategy or combination of sampling strategies used, the system will combine the generated random parameter values ​​to form N_regular specific scenario descriptions determined by the parameters, which constitute the set of regular generalized scenarios S_regular used for virtual calibration.

[0065] Please refer to Figure 5 , Figure 5 This is a flowchart illustrating the steps involved in generating hazardous scenarios within a virtual scenario generation method for vehicle stability development.

[0066] In some embodiments, the method of generating a hazardous scenario based on the selected combination of parameters includes: S501. For each key scenario, determine multiple key parameters in the key scenario.

[0067] S502. For each key parameter, determine the parameter range of the key parameter, and take the limit value selected from the parameter range as the physical boundary value of the key parameter.

[0068] S503. Generate multiple parameter sets, each parameter set including at least one key parameter.

[0069] S504. Based on the vehicle dynamics model, a region map with stable centroid sideslip angle and yaw rate is generated using the phase plane analysis method.

[0070] S505. On the regional map, identify the critical working condition boundary, including the unstable tire force saturation value and the unstable inertia parameter.

[0071] S506. Use a multi-objective optimization function to iteratively solve the problem, so as to select the dangerous parameter combination that contains physical boundary values ​​and makes the vehicle dynamic state approach the critical working condition boundary from multiple parameter sets.

[0072] S507. Based on the combination of hazard parameters, generate hazard scenarios and classify each hazard scenario into a hazard scenario set.

[0073] In some embodiments, the method for determining the limit value includes: Determine the vehicle's dynamic response index value under the target parameter combination within the parameter range; when the dynamic response index value is equal to or greater than the preset dynamic stability threshold, the value of the target parameter combination is determined to be the limit value.

[0074] In one specific embodiment, vehicle stability development requires analyzing vehicle stability under different operating conditions using vehicle dynamics models, particularly identifying critical states where the vehicle is about to become unstable. Let's assume we are studying the stability of a vehicle during high-speed cornering.

[0075] Vehicle dynamics models are used to simulate the behavior of a vehicle during high-speed cornering. These models take into account factors such as the vehicle's weight, tire-to-ground friction, and the vehicle's center of gravity.

[0076] By simulating the vehicle's driving behavior at different speeds and turning radii, the sideslip angle (the angle at which the vehicle's center of gravity deviates from the direction of travel) and yaw rate (the speed at which the vehicle rotates around its vertical axis) are recorded. When a vehicle turns, the body leans to one side; this lean angle is the sideslip angle. The vehicle also rotates around its vertical axis; this rotational speed is the yaw rate. Different combinations of sideslip angle and yaw rate are plotted on a graph, forming a regional map. Different regions on the map represent the vehicle's stability state under different operating conditions. Some regions on this map indicate a stable driving state, while others indicate a state where the vehicle is about to become unstable. In this way, the changes in vehicle stability under different operating conditions can be visually observed.

[0077] On the generated region map, carefully observe the areas where the vehicle transitions from a stable to an unstable state. These transition regions are the critical operating condition boundaries. When the vehicle turns at excessive speed, the friction between the tires and the ground reaches its limit, and the tires can no longer provide sufficient grip, causing the vehicle to begin to slip. This state where the tire force reaches its limit is the unstable tire force saturation value. When the vehicle is turning at high speed, the vehicle's inertia will cause it to lean outwards. When the inertia is too large, the vehicle's center of gravity will be too high, leading to a rollover. This state where the inertial parameter reaches a critical value is the critical operating condition boundary of the unstable inertial parameter.

[0078] On the regional map, it was found that when the sideslip angle reaches 5 degrees and the yaw rate reaches 0.5 degrees / second, the vehicle begins to show signs of instability. This point is the critical operating condition boundary. By identifying these boundaries, we can better understand under which operating conditions the vehicle is prone to instability, thus providing a basis for generating subsequent hazardous scenarios.

[0079] In some embodiments, the system automatically identifies each parameter p iThe physical boundary values ​​(such as min values ​​defined in the existing functional scenario library) i and max i , or calculate the physical limit based on the integrated formula.

[0080] Identify critical operating conditions that may lead to vehicle instability, including mechanisms such as tire force saturation instability and inertial parameter instability. Integrate a nonlinear vehicle dynamics model to calculate the stability boundary, use phase plane analysis to evaluate the stable region of the center of gravity sideslip angle and yaw rate, and use optimization algorithms to find the most dangerous parameter combination to generate systemic instability scenarios.

[0081] The system employs experimental design methods (such as worst-case combinations) or optimization search algorithms to find parameter combinations that include both parameter boundary values ​​and bring the vehicle's dynamic state to a critical point, generating a set of hazardous scenarios, S_extreme. For example, a combination of "low adhesion coefficient + high speed + sharp curve" is generated, which is determined by the dynamic model to be on the verge of instability.

[0082] Understandably, this embodiment significantly improves the accuracy and representativeness of hazardous scenarios by systematically generating them. By determining the physical boundary values ​​of key parameters and combining them with vehicle dynamics models and phase plane analysis, critical operating condition boundaries are accurately identified. Iterative solutions using multi-objective optimization functions are employed to select hazardous parameter combinations that approximate critical operating conditions, resulting in more challenging and practically meaningful hazardous scenarios. This refined hazardous scenario generation method ensures the calibration effect of the chassis electronic control system under extreme conditions, further optimizes the virtual calibration test environment, improves the comprehensiveness and reliability of calibration, and significantly enhances the stability and safety of the chassis electronic control system.

[0083] In some embodiments, after generating the regular scenario S_regular and the hazardous scenario S_extreme, an automated compliance check module is introduced.

[0084] This module incorporates a series of physical rules and preset conditions (such as legal and regulatory requirements, engineering common sense, and physical possibilities) to check the parameter combinations of each generated scene one by one. Any scene that does not conform to these preset rules will be automatically identified and eliminated, ensuring the validity and realism of all scenes in the final scene library.

[0085] In some embodiments, step S104 includes: Pre-defined physical rules and conditions are applied one by one to each target scenario in the set of normal scenarios or dangerous scenarios to determine whether the parameter combination of each target scenario meets the requirements, and to filter out scenarios with parameter combinations that meet the requirements. The physical rules and conditions include at least one of the following: The hydraulic system response time corresponding to the combination of braking pressure and vehicle speed is not greater than the preset maximum response time threshold. The rate of change of steering wheel angle is not greater than the maximum rate of change threshold that the sensor can measure. The tire force requirement shall not exceed the maximum available tire force threshold calculated based on the current road surface adhesion coefficient and vertical load. The combination of yaw rate and sideslip angle in the instability scenario is within the recoverable stability boundary parameters of the vehicle stability control system.

[0086] Furthermore, the regular scenario set S_regular and the hazardous scenario set S_extreme, which pass the compliance check, are merged to form the final comprehensive generalized scenario library S_total, which is used for virtual calibration of the chassis electronic control system.

[0087] S_total = [S_regular ∪ S_extreme] | passed_compliance_check This scenario library outputs data in machine-readable standard formats (such as XML and JSON), clearly recording the primary and secondary functional scenario types and all parameter values ​​for each scenario. This scenario library can be used to drive high-fidelity vehicle dynamics simulations, enabling efficient, comprehensive, and reliable virtual testing and calibration of chassis electronic control systems.

[0088] Please refer to Figure 6 , Figure 6 This is another step in a virtual scene generation method for vehicle stability development.

[0089] This embodiment provides a specific implementation case for the automatic generation of a virtual calibration scenario for the stability of a VDC system.

[0090] The multi-level functional scenarios related to VDC system development were selected and deconstructed parametrically to obtain first-level scenarios such as "straight driving scenario", "curved driving scenario", and "composite working condition scenario"; and second-level scenarios such as "split road braking", "steering braking", "emergency lane change" and "fishhook test".

[0091] Taking the "split-road braking" scenario as an example, the key parameter set is defined as follows: Difference in adhesion coefficient between the left and right sides of the road surface: 0.2-0.6; Initial speed: 50-120 km / h; Braking pressure: 2-15MPa; Steering wheel angle: 0-90°; Vehicle load distribution: unloaded - fully loaded.

[0092] To generate a standard test scenario for "split-road braking," a joint bias distribution is used for the difference between vehicle speed and road adhesion coefficient, increasing the sampling density by 3 times in the low-adhesion, high-speed region. Latin hypercube sampling is used for braking pressure and steering wheel angle to ensure uniform coverage of various braking and steering combinations. Uniformly distributed sampling is used for vehicle load to cover different loading conditions. A risk-oriented sampling strategy is employed to focus on generating parameter combinations that are prone to vehicle instability, improving testing efficiency.

[0093] Hazardous scenarios are identified based on physical limits and dynamic boundaries. Physical boundaries are identified by considering the maximum tire adhesion, the maximum braking system pressure, and the steering system's limit positions.

[0094] An integrated nonlinear vehicle dynamics model is used, and the phase plane analysis method is employed to calculate the stability boundary of the center of gravity sideslip angle and yaw rate, evaluate the vehicle stability margin and instability tendency, and identify the tire force saturation critical point.

[0095] Using a multi-objective optimization algorithm, systemic instability scenarios such as "sinusoidal stop steering on low-adhesion road surface" and "braking lane change on high-adhesion road surface" are generated to specifically test the intervention capability of the VDC system.

[0096] Establish VDC-specific compliance check rules: Instability scenarios must be kept within recoverable limits; The combination of braking pressure and vehicle speed is compatible with the response capability of the hydraulic system. The rate of change of steering wheel angle is within the sensor's measurement range; After excluding physically impossible tire force requirements, a comprehensive scenario library of virtual calibration scenarios will be formed by merging routine and hazardous inspection scenarios.

[0097] Please refer to Figure 7 , Figure 7 This is a schematic diagram of the structure of a virtual scene generation system for vehicle stability development.

[0098] This embodiment also provides a virtual scene generation system for vehicle stability development, including: The parameterization parsing module 601 is used to construct systematic constraints on multi-parameter coupling relationships based on a preset multi-level functional scenario model, and to determine the parameter coupling boundaries of key scenarios based on the systematic constraints.

[0099] The scene generation module 602 is used to select parameter combinations within the parameter coupling boundary and generate all normal and dangerous scenes that may lead to instability based on the selected parameter combinations.

[0100] The compliance check module 603 is used to perform compliance screening for each routine scenario and each hazardous scenario based on preset safety standards or physical constraints.

[0101] The scenario library management output module 604 is used to generate a comprehensive scenario library for virtual calibration of the chassis electronic control system based on multiple filtered scenarios.

[0102] It will be understood by those skilled in the art that all or some of the steps and apparatuses in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. As is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0103] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0104] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the virtual scene generation method for vehicle stability development as described above.

[0105] refer to Figure 8 , Figure 8 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 702 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store operating devices and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702, and the processor 701 calls and executes the virtual scene generation method for vehicle stability development according to the embodiments of this application. The input / output interface 703 is used to implement information input and output; The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704); The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0106] It is understood that the content of the above method embodiments is applicable to the embodiments of this electronic device. The specific functions implemented by the embodiments of this electronic device are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0107] This application also provides a computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to implement the virtual scene generation method for vehicle stability development as described in any of the above specific embodiments.

[0108] This application also discloses a computer program product, including a computer program or computer instructions, which are stored in a computer-readable storage medium. The processor of the computer device reads the computer program or computer instructions from the computer-readable storage medium and executes the computer program or computer instructions, causing the computer device to perform the virtual scene generation method for vehicle stability development as described in any of the preceding embodiments.

[0109] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0110] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatuses. It should be understood that in this application, “at least one” means one or more, and “more than one” means two or more.

[0111] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0112] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0113] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0114] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0115] Although the description of this application has been quite detailed and particularly focused on several of the described embodiments, it is not intended to limit itself to any of these details or embodiments or any particular embodiment. Rather, it should be considered as effectively covering the intended scope of this application by referring to the appended claims and taking into account the prior art, which provides for a broad possible interpretation of these claims. Furthermore, the foregoing description of this application with respect to embodiments foreseeable by the inventors is intended to provide a useful description, and non-substantial modifications to this application that have not yet been foreseen may still represent equivalent modifications.

Claims

1. A method for generating a virtual scenario for vehicle stability development, characterized in that The method comprises: Based on the preset multi-level function scene model, the system constraint condition of the multi-parameter coupling relationship is constructed, and the parameter coupling boundary of the key scene is determined according to the system constraint condition; Selecting a parameter combination within the parameter coupling boundary, and generating a regular scene and a dangerous scene that covers all possible instability scenes according to the selected parameter combination; According to the preset safety standard or physical constraint, the compliance screening is performed on each regular scene and each dangerous scene; According to a plurality of scenes screened, a comprehensive scene library for virtual calibration of the chassis electronic control system is generated.

2. The method of claim 1, wherein, The way of determining the parameter coupling boundary of the key scene comprises: The multi-level function scene model is decomposed into a primary scene and a secondary scene, wherein the primary scene is a macro driving task category scene, and the secondary scene is a specific driving road condition scene in the primary scene; For each secondary scene, a corresponding key parameter set is generated, wherein the key parameter set includes at least one of the following parameters: steering wheel angle, steering wheel angle speed, vehicle speed, road adhesion coefficient; The value range of each parameter in the key parameter set is determined.

3. The method of claim 1, wherein, The way of generating a regular scene according to the selected parameter combination comprises: For each key scene, the vehicle speed, the road adhesion coefficient, the lateral acceleration and the longitudinal acceleration in the key scene are determined as key parameters; The joint bias distribution is used to take values from the parameter range of the vehicle speed and the road adhesion coefficient respectively and obtain first and second values; The Latin hypercube sampling method is used to take values from the parameter range of the lateral acceleration and the longitudinal acceleration and obtain third and fourth values; Based on the scene value evaluation function, the first, second, third and fourth values are screened, and a parameter combination is generated according to the screened values; According to the parameter combination, a corresponding regular scene is generated; Return to execute the step of taking values from the parameter range of the vehicle speed and the road adhesion coefficient respectively and obtaining first and second values by using the joint bias distribution, and when the number of generated regular scenes reaches a preset upper limit value, each regular scene is classified into a regular scene set.

4. The method of claim 3, wherein, The way of taking values in the parameter range further comprises: Selecting a target sampling strategy from a plurality of sampling strategies; After selecting one or more values from the parameter range according to the target sampling strategy, return to execute the step of selecting a target sampling strategy from a plurality of sampling strategies until the selection times reach a preset limited number.

5. The method of claim 1, wherein, The way of generating a dangerous scene according to the selected parameter combination comprises: For each key scene, a plurality of key parameters in the key scene are determined; For each key parameter, the parameter range of the key parameter is determined, and the extreme value selected from the parameter range is taken as the physical boundary value of the key parameter; A plurality of parameter sets are generated, each of which includes at least one key parameter; Based on the vehicle dynamics model, the phase plane analysis method is used to generate a region map of the center of mass side slip angle and yaw rate stability; On the region map, a critical working condition boundary including an unstable tire force saturation value and an unstable inertia parameter is identified; A multi-objective optimization function is used for iterative solving to screen a dangerous parameter combination containing the physical boundary value and approximating the critical working condition boundary from the plurality of parameter sets; Based on the dangerous parameter combination, a dangerous scenario is generated, and each dangerous scenario is classified into a dangerous scenario set.

6. The method of claim 5, wherein, The manner of determining the limit value comprises: determining a dynamic response index value of the vehicle under a target parameter combination in the parameter range; when the dynamic response index value is equal to or greater than a preset dynamic stability threshold, determining that the value of the target parameter combination is the limit value.

7. The method of claim 1, wherein, The compliance screening of each of the normal scenarios and each of the dangerous scenarios based on the preset safety standards or physical constraints comprises: applying preset physical rules and conditions to each target scenario in the normal scenario set or the dangerous scenario set one by one to determine whether the parameter combination of each target scenario conforms to the regulations, and screening out scenarios with a parameter combination conforming to the regulations, wherein the physical rules and conditions comprise at least one of the following: a hydraulic system response time corresponding to a combination of brake pressure and vehicle speed is not greater than a preset maximum response time threshold; a steering wheel angle change rate is not greater than a maximum change rate threshold measurable by a sensor; a tire force demand is not greater than a maximum available tire force threshold calculated based on a current road adhesion coefficient and a vertical load; a parameter combination of a yaw rate and a center of mass side slip angle in an unstable scenario is within a stable boundary parameter range that can be recovered by a vehicle stability control system.

8. A virtual scenario generation system for vehicle stability development, characterized in that The generation system comprises: a parameterized analysis module configured to construct systematic constraint conditions of multi-parameter coupling relationships based on a preset multi-level functional scenario model, and determine parameter coupling boundaries of key scenarios according to the systematic constraint conditions; a scenario generation module configured to select parameter combinations within the parameter coupling boundaries, and generate normal scenarios and dangerous scenarios that can all cause instability according to the selected parameter combinations; a compliance checking module configured to perform compliance screening of each of the normal scenarios and each of the dangerous scenarios based on preset safety standards or physical constraints; a scenario library management output module configured to generate an integrated scenario library for virtual calibration of a chassis electronic control system according to a plurality of screened scenarios.

9. An electronic device, comprising: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the virtual scenario generation method for vehicle stability development of any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the virtual scenario generation method for vehicle stability development of any one of claims 1 to 7.

Images