Driver's license testing methods and equipment

Abstract

This application discloses a driver's license testing method and equipment, relating to the field of autonomous driving driver's license testing technology. The method includes: acquiring behavioral data of a target vehicle in a preset scenario switching test level, the preset scenario switching test level including dynamic transition test scenarios of varying complexity from low to high; determining the scenario adaptation score of the target vehicle during the scenario switching process based on the behavioral data; and determining whether to terminate the scenario switching test of the target vehicle based on the scenario adaptation score. This application, by setting dynamic transition test scenarios, tests the vehicle's adaptability under complex scenario switching, achieving scientific control of driver's license test scenario switching and improving the accuracy and realism of driver's license testing.

Description

Technical Field

[0001] This application relates to the field of autonomous driving license testing technology, and in particular to a driver's license testing method and equipment. Background Technology

[0002] With the rapid development of autonomous driving technology, Robotaxi (driverless taxi) has become an important carrier for the application of autonomous driving technology, and its driving safety and adaptability to various scenarios have become the focus of industry attention.

[0003] Current driver's license tests primarily focus on the static performance of vehicles in fixed scenarios, making it difficult for vehicles to adapt to real-world, complex scenarios.

[0004] In view of the shortcomings of the existing technology, there is an urgent need for a driver's license testing scheme that can enable vehicles to adapt to real and complex scenarios. Summary of the Invention

[0005] The main purpose of this application is to provide a driver's license testing method and equipment, which aims to solve the technical problem in the prior art that driver's license testing causes vehicles to be unable to adapt to real and complex scenarios.

[0006] To achieve the above objectives, this application proposes a driver's license testing method, which includes:

[0007] Acquire behavioral data of the target vehicle in preset scenario switching test levels. The preset scenario switching test levels include dynamic transition test scenarios with different complexity from low to high.

[0008] Based on behavioral data, determine the scene adaptability score of the target vehicle during scene switching.

[0009] Based on the scene adaptability score, determine whether to terminate the scene switching level test for the target vehicle.

[0010] In one embodiment, the step of determining whether to terminate the scene switching level test of the target vehicle based on the scene adaptability score includes:

[0011] If the current scene level of the target vehicle is higher than the target scene level that the target vehicle is challenging, and the scene adaptation score is less than the scene adaptation qualification threshold, then the scene switching level test of the target vehicle will be terminated.

[0012] If the current scene level is not higher than the target scene level, and / or the scene adaptation score is greater than or equal to the scene adaptation qualification threshold, then continue the scene switching level test for the target vehicle.

[0013] In one embodiment, after the above-described step of continuing the scene switching level test for the target vehicle, the method further includes:

[0014] The final score for the current scene transition level is calculated based on the scene adaptability score and the baseline score of the current scene transition level.

[0015] In one embodiment, the threshold value for scene adaptability is in the range of 0.3 to 0.6.

[0016] In one embodiment, determining the scene adaptability score of the target vehicle during scene switching based on behavioral data includes:

[0017] Based on behavioral data, determine the actual behavior of the target vehicle;

[0018] Determine the deviation parameters of the actual behavior from the expected standard behavior during scene switching in each dimension;

[0019] The deviation parameters of each dimension are substituted into the weighted scoring model to calculate the scene adaptation score of the target vehicle during scene switching. The weighted scoring model is used to reflect the correlation between the scene adaptation score and the deviation parameters of each dimension and their corresponding weight coefficients.

[0020] In one embodiment, the driver's license testing method further includes a post-test debriefing step:

[0021] Compare the final score of the scene transition level with the preset passing score to determine if there is room for improvement in the target vehicle's scene transition capability. If so, output improvement suggestions; and / or,

[0022] Record behavioral data for the test period, including at least one of the following: scene switching time points, deviation parameters for each dimension, corresponding weight coefficients, scene adaptability score, real-time trajectory data of the target vehicle, and decision operation records.

[0023] In one embodiment, the dimensions of the aforementioned deviation parameter include reaction delay time deviation,

[0024] At least one of trajectory deviation, number of decision-making errors, and deviation of comfort index.

[0025] In one embodiment, the above-mentioned dynamic transition test scenario includes at least one of the following:

[0026] Switch from city roads to highway entrance ramps;

[0027] From sunny daytime weather to rainy or foggy nighttime weather;

[0028] Shifting from one-way, low-density traffic flow to multi-way, complex intersections;

[0029] Switch from driving straight through unobstructed areas to avoiding sudden obstacles.

[0030] In one embodiment, if it is determined that the scene switching level test of the target vehicle will be terminated, at least one of the following operations is performed:

[0031] The scene adaptation score for the current scene transition level is determined to be 0;

[0032] The safety officer takeover signal is automatically triggered, which prompts the safety officer to guide the target vehicle to a safe area.

[0033] Record the reason for test termination, the time of termination, and the behavioral data for the corresponding time period.

[0034] By recording the reasons for test termination and related data, subsequent analysis can be conducted to provide a basis for test optimization and vehicle improvement.

[0035] In one embodiment, scenarios of varying complexity from low to high include basic complexity scenarios, medium complexity scenarios, high complexity scenarios, and extremely high complexity scenarios. The complexity of each scenario level is determined by traffic flow density, environmental interference factors, and operational difficulty coefficients.

[0036] In addition, to achieve the above objectives, this application also proposes a driver's license testing device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the driver's license testing method as described above.

[0037] This application proposes a driver's license testing method and device. The method includes: acquiring behavioral data of a target vehicle in a preset scenario switching test level, wherein the preset scenario switching test level includes dynamic transition test scenarios with varying complexity from low to high; determining the scenario adaptability score of the target vehicle during the scenario switching process based on the behavioral data; and determining whether to terminate the scenario switching test of the target vehicle based on the scenario adaptability score. By setting dynamic transition test scenarios, the adaptability of the vehicle under complex scenario switching is tested, achieving an accurate assessment of the vehicle's scenario switching adaptability and significantly improving the scientific rigor, accuracy, and reliability of driver's license testing. Attached Figure Description

[0038] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart illustrating the first embodiment of the driver's license testing method in this application.

[0041] Figure 2 This is a flowchart illustrating Embodiment 2 of the driver's license testing method provided in this application;

[0042] Figure 3 This is a flowchart illustrating Embodiment 3 of the driver's license testing method provided in this application;

[0043] Figure 4 This is a flowchart illustrating Embodiment 4 of the driver's license testing method of this application;

[0044] Figure 5 This is a schematic diagram of the module structure of the driver's license testing system according to an embodiment of this application;

[0045] Figure 6 This is a schematic diagram of the hardware operating environment involved in the driver's license testing method in this application. Detailed Implementation

[0046] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of this application and are not intended to limit this application.

[0047] The inventors' research revealed that in real-world road environments, vehicles need to switch between scenarios of varying complexity, such as transitioning from urban main roads to highway ramps. Because current driver's license tests focus on the static performance of vehicles in fixed-level scenarios, they lack accurate assessment of the actual performance of vehicles during dynamic transitions. This leads to safety risks as some vehicles continue testing despite insufficient adaptation in high-complexity scenarios, or are mistakenly terminated due to minor errors in low-complexity scenarios, affecting testing efficiency and accuracy. Consequently, the testing objectives of "capability adaptation - dynamic assessment - risk control" cannot be achieved, resulting in vehicles being unable to adapt to real-world complex scenarios.

[0048] Based on the above, this application provides a driver's license testing scheme. By setting up dynamic transition test scenarios, the scheme tests the vehicle's adaptability under complex scenario switching, achieves accurate evaluation of the vehicle's scenario switching adaptability, thereby improving the vehicle's adaptability to real complex scenarios and achieving the testing goal of "capability adaptation - dynamic evaluation - risk controllability", enabling the vehicle to adapt to real complex scenarios.

[0049] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0050] The main solution of this application embodiment is: to acquire behavioral data of the target vehicle in a preset scene switching test level; to determine the scene adaptation score of the target vehicle during scene switching based on the behavioral data; and to determine whether to terminate the scene switching test of the target vehicle based on the scene adaptation score. It should be noted that the executing entity of this application embodiment can be a computing device with data processing, scene control, and program execution functions, such as an in-vehicle test terminal, a ground test control console, or a cloud-based test management platform. For ease of description, the following uses an in-vehicle test unit as an example to describe this embodiment and the following embodiments.

[0051] Based on this, the embodiments of this application provide a driver's license testing method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the driver's license testing method in this application.

[0052] In this embodiment of the application, the driver's license testing method includes steps S10 to S30.

[0053] Step S10: Obtain the behavior data of the target vehicle in the preset scene switching test level.

[0054] In this embodiment, the on-board testing unit collects multi-dimensional behavioral data generated by the target vehicle during its operation in preset scenario switching test stages through multiple channels, including the vehicle bus, on-board sensors, and testing terminals. This behavioral data is the core basis for subsequent calculation of scenario adaptability scores, and its collection frequency and accuracy must meet the evaluation requirements. Specifically, this includes, but is not limited to, the vehicle's reaction delay time during scenario switching, actual driving trajectory data, decision-making operation records (such as acceleration, braking, and steering commands), comfort-related parameters (such as the rate of change of longitudinal acceleration), and environmental interaction data (such as changes in distance to surrounding vehicles).

[0055] The preset scenario switching test level is a set of dynamic transition test scenarios built based on driver's license test requirements. It includes dynamic transition test scenarios with varying complexity from low to high, aiming to simulate various scenario switching conditions that may be encountered in real driving. Optionally, the dynamic transition test scenarios include, but are not limited to: switching from urban roads to highway entrance ramps (road type switching), switching from sunny daytime weather to rainy or foggy nighttime weather (environmental condition switching), switching from one-way low-density traffic flow to multi-way complex intersections (traffic flow complexity switching), and switching from unobstructed straight-through to sudden obstacle avoidance. The timing and duration of each scenario combination can be dynamically configured according to the test level.

[0056] Step S20: Based on behavioral data, determine the scene adaptability score of the target vehicle during scene switching.

[0057] The scenario adaptability score is used to quantify the degree of adaptability of the target vehicle's operation behavior and decision-making logic to the requirements of the current switching scenario during the scenario switching process. The higher the scenario adaptability score, the stronger the vehicle's ability to adapt to scenario switching, and vice versa.

[0058] The core logic of converting the target vehicle's behavior data in the preset scenario switching test level into a quantifiable scenario adaptability score is as follows: taking the expected standard behavior of scenario switching as the benchmark, calculating the degree of deviation between the vehicle's actual behavior and the standard behavior in each key dimension, and combining the degree of deviation in each dimension to calculate the adaptability score.

[0059] Optionally, the scene fit score can be calculated using a pre-defined weighted scoring model. Alternatively, a scene fit evaluation model can be pre-trained to evaluate the scene fit score of the target vehicle during scene switching based on behavioral data. Specifically, by inputting real-time acquired behavioral data into the scene fit evaluation model, the output of the model can be obtained as the scene fit score of the target vehicle during scene switching. Alternatively, the behavioral data can be pre-processed, such as through data cleaning, to obtain the model input for the scene fit evaluation model. The scene fit evaluation model then evaluates the scene fit of this model input to obtain the scene fit score of the target vehicle during scene switching.

[0060] It should be noted that the weighted deduction model is a quantitative model based on multi-dimensional deviation assessment, used to implement the core logic mentioned above.

[0061] Furthermore, the weighted deduction model is used to reflect the correlation between the scene fit score and the deviation parameters of each dimension and their corresponding weight coefficients. In other words, the weighted deduction model calculates a weighted deduction based on the degree of deviation between the vehicle's actual behavior and the standard behavior in each key dimension, combined with the weight coefficients of each dimension, and finally obtains a normalized scene fit score.

[0062] Understandably, traditional driver's license tests often rely on qualitative assessments or single-dimensional indicators to judge scenario adaptability, which can lead to biased evaluations. However, this application's embodiment constructs a weighted scoring model to achieve a multi-dimensional quantitative assessment of vehicle scenario adaptability, effectively improving the objectivity and accuracy of the evaluation results.

[0063] In one feasible embodiment, step S20 specifically includes: determining the actual behavior of the target vehicle based on behavioral data; determining the deviation parameters of the actual behavior from the expected standard behavior during the scene switching process in each dimension; and substituting the deviation parameters of each dimension into the weighted scoring model to calculate the scene adaptability score of the target vehicle during the scene switching process.

[0064] Among them, the deviation parameter is the core indicator for quantifying the difference between the vehicle's actual behavior and the expected standard behavior. Its quantification dimensions need to cover the key evaluation points in the scene switching process. Optionally, the dimensions of the deviation parameter specifically include at least one of the following: reaction delay time deviation (such as the difference between the actual reaction time and the standard reaction time), trajectory deviation (such as the lateral / longitudinal deviation between the actual trajectory and the ideal trajectory), number of decision-making errors (such as the number of misoperations that occur during scene switching, including but not limited to incorrect lane changes, improper acceleration and deceleration, etc.), and comfort index deviation (i.e., the degree of deviation between the vehicle's driving comfort quantification characteristics and the preset comfort threshold, where comfort quantification characteristics include but are not limited to the magnitude of rapid acceleration, the magnitude of rapid deceleration, the magnitude of rapid steering, and the frequency and duration of the above behaviors per unit time).

[0065] Optionally, each deviation parameter can be calculated using a preset algorithm. For example, the trajectory deviation can be calculated using the Hausdorff distance algorithm, and the reaction delay time deviation can be calculated using the ratio of the actual value to the standard value.

[0066] Weighting coefficients are used to characterize the importance of each deviation parameter in the scenario adaptability assessment, and their allocation follows a core principle: safety-related dimensions have higher weights than comfort-related dimensions. For example, the weighting coefficient for trajectory deviation (directly related to driving safety) can be set to 0.4, the weighting coefficient for reaction delay time deviation can be set to 0.3, the weighting coefficient for the number of decision-making errors can be set to 0.2, and the weighting coefficient for comfort index deviation can be set to 0.1. Furthermore, these weighting coefficients are not fixed values ​​and are dynamically adjusted according to the scenario type and safety requirements. For example, in a high-speed ramp switching scenario, the weight of trajectory deviation will be further increased; in a nighttime rain scenario, the weight of reaction delay time deviation will increase.

[0067] In this embodiment, the scene suitability score SAS_score is calculated using a weighted deduction model. The specific calculation formula for the weighted deduction model is as follows:

[0068] SAS_score = 1 - Σ(wi * di)

[0069] In the formula, Σ represents the summation operation, wi is the weight coefficient of the i-th dimension (Σwi=1), and di is the deviation parameter of the i-th dimension (normalized to the [0,1] interval). When the actual behavior of the vehicle fully conforms to the expected standard behavior, the deviation parameter di of each dimension is 0, and the scene fit score SAS_score=1; when the vehicle behavior deviates significantly from the standard, Σ(wi*di) approaches 1, and the scene fit score SAS_score approaches 0.

[0070] For example, if a scenario switching test includes trajectory deviation (w1=0.4, d1=0.2), reaction delay time deviation (w2=0.3, d2=0.1), decision error number deviation (w3=0.2, d3=0), and comfort index deviation (w4=0.1, d4=0.3), then SAS_score=1 - (0.4*0.2 + 0.3*0.1 + 0.2*0 + 0.1*0.3) = 1 - 0.14 = 0.86, indicating that the vehicle has good adaptability to the scenario switching.

[0071] Step S30: Based on the scene adaptability score, determine whether to terminate the scene switching level test for the target vehicle.

[0072] In practical applications, termination conditions for scene switching level tests can be preset, such as a scene adaptability score falling below a certain threshold; or continuation conditions can be preset, such as a scene adaptability score exceeding a certain threshold. Optionally, this threshold can be set based on historical experience or relevant requirements; or it can be adaptively set based on the current scene switching level or other relevant factors, and so on. In this way, based on the scene adaptability score, the preset conditions, and other possible requirements, it can be determined whether to terminate the scene switching level test for the target vehicle.

[0073] This application embodiment sets up dynamic transition test scenarios to test the vehicle's adaptability under complex scenario switching, thereby achieving an accurate assessment of the vehicle's scenario switching adaptability. In addition, based on the scenario adaptability score, it determines whether to terminate the scenario switching level test of the target vehicle, which can terminate incompatible scenario switching tests in real time, significantly improving the scientificity, accuracy and reliability of driver's license testing.

[0074] In one implementation, step S30 may include: combining the scene adaptability score, the current scene level of the target vehicle, and the target scene level challenged by the target vehicle, to determine whether to terminate the scene switching level test of the target vehicle.

[0075] It should be noted that the scenario level is a quantitative classification of the complexity of the test scenario, and its classification is based on a comprehensive evaluation of traffic flow density, environmental interference factors, and operational difficulty coefficient. For example, it is specifically divided into four levels: basic complexity scenario (such as simple turning on an empty road), medium complexity scenario (such as turning between urban roads), high complexity scenario (such as turning from an urban road to a highway ramp), and extremely high complexity scenario (such as turning at a complex intersection during nighttime rain).

[0076] The current scenario level refers to the difficulty level of the scenario switching test that the target vehicle is currently undergoing. The target scenario level refers to the final difficulty level of the scenario switching test that needs to be completed. The quantitative standards for the current scenario level and the target scenario level are consistent (e.g., both adopt a 1-10 level classification system).

[0077] Understandably, current technologies often use fixed thresholds for test termination, failing to dynamically adjust based on scenario level differences. This results in security risks in highly complex scenarios not being mitigated in a timely manner. This step addresses this by integrating a three-dimensional judgment logic based on "scenario suitability score - current level - target level," achieving precise control over test termination. This ensures test security in high-risk scenarios while preventing excessive termination in low-risk scenarios.

[0078] The scene adaptability qualification threshold is a critical value used to determine whether a vehicle's scene adaptability meets the standard. Its value ranges from 0.3 to 0.6, and the specific value can be dynamically adjusted according to the driver's license test level. Optionally, scene complexity is positively correlated with the scene adaptability qualification threshold; for low-complexity scenes, the scene adaptability qualification threshold can be set to a lower value; for high-complexity scenes, the scene adaptability qualification threshold can be set to a higher value. For example, for basic complexity scenes, the scene adaptability qualification threshold can be set to 0.3~0.35; for medium complexity scenes, it can be set to 0.35~0.45; for high complexity scenes, it can be set to 0.45~0.55; and for extremely high complexity scenes, it can be set to 0.55~0.6.

[0079] The steps for determining whether to terminate the scene switching level test for the target vehicle, based on the scene adaptability score, the current scene level of the target vehicle, and the target scene level that the target vehicle is challenging, may further include:

[0080] 1. If the current scene level of the target vehicle is higher than the target scene level of the vehicle's challenge, and the scene adaptation score is less than the acceptable scene adaptation threshold, the scene switching level test for the target vehicle will be terminated immediately. This situation indicates that the vehicle's adaptability in high-complexity scenes beyond its own challenge level is insufficient, and continuing the test poses a safety risk, requiring immediate termination.

[0081] 2. If the current scene level is not higher than the target scene level, and / or the scene adaptation score is greater than or equal to the scene adaptation qualification threshold, then the scene switching level test for the target vehicle continues. This situation includes three sub-scenarios: First, the current scene level does not exceed the target level, and even if the scene adaptation score is slightly lower, it can still be further evaluated through subsequent scene tests; second, although the current scene level exceeds the target scene level, the vehicle's scene adaptation score meets the standard, indicating that the vehicle has an adaptation capability beyond expectations, and testing can continue to comprehensively evaluate its extreme capabilities; third, the current scene level does not exceed the target scene level, and the vehicle's scene adaptation score meets the standard, indicating that the vehicle's adaptation capability meets the basic requirements of the current scene and the preset target, and continuing testing can complete the full-process scene coverage evaluation, ensuring that its adaptation capability covers all target difficulty scenes and avoiding misjudgment of capability due to partial compliance.

[0082] By using the methods described above, behavioral data of the target vehicle in the scene switching test level is obtained. The adaptation score is calculated using a weighted scoring model that integrates multi-dimensional behavioral data. The test termination is dynamically determined by combining the scene level and the scene adaptation score. This achieves accurate evaluation and flexible control of driver's license test scene switching, thereby effectively ensuring test safety while improving the scientific nature and efficiency of driver's license test evaluation.

[0083] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 After determining in step S30 to continue the scene switching level test for the target vehicle, the driver's license test method further includes step S40: calculating the final score of the current scene switching level based on the scene adaptability score and the baseline score of the current scene switching level.

[0084] In this embodiment, the baseline score is a preset maximum score (e.g., 1 point) for each scene switching test level, used to convert the normalized scene adaptability score ([0,1] interval) into an intuitive test score. For example, the formula for calculating the final score of the scene switching level is as follows:

[0085] Final score = Base_Score * SAS_score

[0086] Where Base_Score represents the baseline score; SAS_score represents the scenario adaptation score.

[0087] For example, if the baseline score for a scene transition level is 1 point, and the vehicle's scene adaptability score is 0.86, then the final score for that scene transition level is 0.86 points. This calculation method clearly reflects the vehicle's specific performance in each level, providing an intuitive basis for subsequent capability assessments.

[0088] Based on the first embodiment of this application, in the third embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Figure 2 Based on this, please refer to Figure 3 Following step S40, the driver's license testing method further includes step S50: comparing the final score of the scene switching level with the preset passing score to determine whether there is room for improvement in the scene switching capability of the target vehicle; if so, outputting improvement suggestions; and / or, recording behavioral data during the test period. This behavioral data includes at least one of the following: scene switching time points, deviation parameters for each dimension, corresponding weight coefficients, scene adaptability score, real-time trajectory data of the target vehicle, and decision operation records.

[0089] Specifically, it includes two aspects: First, it determines whether there is room for improvement in the scene switching capability of the target vehicle based on the final score of the current scene switching level. For example, if the final score is lower than 0.8 points (the preset excellent line), the system automatically locates the deviation dimension with the lower score (such as excessive trajectory deviation) and generates targeted improvement suggestions. Second, it records relevant data throughout the entire testing process to provide data support for subsequent test optimization and problem tracing. The recorded data includes, but is not limited to, scene switching time points, deviation parameters of each dimension, corresponding weight coefficients, scene adaptability scores, real-time trajectory data of the target vehicle, and decision operation records.

[0090] The method described in this embodiment enables the quantification of test scores and the full-process traceability of test data, providing clear directions for vehicle capability improvement and data support for the optimization of the driver's license testing system.

[0091] Based on the first embodiment of this application, in the fourth embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, refer to... Figure 4 After determining the termination of the scene switching checkpoint test for the target vehicle in step S30, the driver's license test method also includes step S60: performing emergency handling and data recording after the test is terminated.

[0092] In this embodiment, if the system determines to terminate the scene switching test for the target vehicle, it will perform a series of emergency handling and recording operations, specifically including: First, determining that the scene adaptation score of the current scene switching level is 0, which will be included in the vehicle's total score for this driver's license test; Second, automatically triggering a safety officer takeover signal, with the safety officer guiding the target vehicle to a safe area to prevent accidents during the test; Third, recording the core data of the test termination, including the reason for termination, the termination time, and behavioral data for the corresponding time period, for subsequent test quality analysis and vehicle skill deficiency identification. The behavioral data for the corresponding time period includes, but is not limited to, deviation parameters of each dimension, corresponding weight coefficients, scene adaptation score, real-time trajectory data of the target vehicle, and decision operation records. This data will be used for subsequent analysis of the termination reasons (such as vehicle operation errors, vehicle performance limitations, etc.), providing a basis for optimizing driver's license test standards and vehicle training.

[0093] This embodiment, by clearly defining the handling process after test termination, not only ensures driving safety after test termination but also enables traceability of the reason for termination, thereby improving the standardization of driver's license testing.

[0094] Based on the first embodiment of this application, content that is the same as or similar to Embodiment 1 above can be referred to the above description and will not be repeated hereafter. Building upon this, this embodiment further refines the scene level classification criteria and adaptation logic:

[0095] Step S010: Clarify the basis and specific standards for classifying scene levels;

[0096] The classification of scene levels is based on a comprehensive score of traffic flow density, environmental interference factors, and operational difficulty coefficient, and is specifically divided into four levels, with the following standards for each level:

[0097] 1. Basic complexity scenario: Traffic flow density ≤ 10 vehicles / km, no obvious environmental interference factors (such as sunny daytime), operation difficulty coefficient ≤ 0.3 (only simple turning and constant speed driving are required);

[0098] 2. Moderate complexity scenario: 10 vehicles / km < traffic flow density ≤ 30 vehicles / km, with slight environmental interference (such as cloudy days), and an operation difficulty coefficient of 0.3~0.5 (requiring simple avoidance and speed change).

[0099] 3. High-complexity scenarios: 30 vehicles / km < traffic flow density ≤ 50 vehicles / km, with significant environmental interference (such as light rain, streetlights at night), and an operation difficulty coefficient of 0.5~0.8 (requiring precise trajectory control and rapid decision-making).

[0100] 4. Extremely complex scenarios: Traffic flow density > 50 vehicles / km, with severe environmental interference (such as heavy rain, no streetlights at night), and an operational difficulty coefficient > 0.8 (requiring handling of emergencies and complex avoidance).

[0101] Step S020: Dynamically configure test parameters according to the scene level;

[0102] The system presets the target scenario level for the challenge based on the test level of the target vehicle (new driver, upgrade, or recertification). For example, the highest target scenario level for new driver tests is a medium complexity scenario, while the target scenario level for upgrade tests can be increased to a high complexity scenario. Simultaneously, the system dynamically adjusts the weighting coefficients of the weighted scoring model based on the current scenario level. For instance, in extremely high complexity scenarios, the weighting coefficient for the number of decision-making errors is increased from 0.2 to 0.3, further strengthening the assessment weight of the safety dimension.

[0103] This embodiment provides a basis for the precise design of scenario switching tests by clarifying the scenario level classification standards and dynamic adaptation logic, ensuring the matching degree between the test scenario and the vehicle test level.

[0104] To enable those skilled in the art to better understand the methods of the embodiments of this application, the following detailed description of this application will be provided through specific implementation examples.

[0105] Specifically, a target vehicle participates in a driver's license test, and the target scenario level it challenges is a medium-complexity scenario. The preset scenario adaptability qualification threshold θ=0.5, and the test level is "switching from urban roads to highway ramps" (medium-complexity scenario, base score Base_Score=1 point). The weights of each dimension of the weighted scoring model are: trajectory deviation w1=0.4, reaction delay time deviation w2=0.3, number of decision-making errors w3=0.2, and comfort index w4=0.1.

[0106] During the test, the vehicle-mounted test unit collected vehicle behavior data in real time and calculated the deviation parameters for each dimension: d1=0.2, d2=0.1, d3=0.1, d4=0.2. The scene adaptability score was calculated using a weighted scoring model: SAS_score=1 -(0.4*0.2 + 0.3*0.1 + 0.2*0.1 + 0.1*0.2) = 1 - 0.15 = 0.85, which is higher than the threshold of 0.5. Since the current scene level (medium) does not exceed the target scene level, the level test continues.

[0107] The final score for this test level was 1*0.85=0.85 points. The system determined that the vehicle's scene switching capability was good and there was no obvious room for improvement. It also recorded information such as scene switching time points, deviation parameters in various dimensions, and trajectory data.

[0108] If, during subsequent testing, the vehicle enters a "complex intersection switching under nighttime rain" scenario (a high-complexity scenario exceeding the beginner target level), and the calculated SAS_score is 0.4 < 0.5, the system will immediately terminate the test, the scenario adaptation score for the level will be 0, and the safety officer will take over the vehicle and guide it to a safe area. The reason for termination will be recorded as "insufficient scenario adaptation exceeding the target level".

[0109] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the driver's license testing method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0110] This application also provides a driver's license testing system; please refer to... Figure 5 The driver's license testing system 50 includes:

[0111] The acquisition module 10 is used to acquire the behavior data of the target vehicle in the preset scene switching test level. The preset scene switching test level includes dynamic transition test scenarios with different complexity from low to high.

[0112] Calculation module 20 is used to determine the scene adaptability score of the target vehicle during scene switching based on behavioral data;

[0113] Decision module 30 is used to determine whether to terminate the scene switching level test of the target vehicle based on the scene adaptability score.

[0114] In one embodiment, the decision module 30 is specifically used to: terminate the scene switching level test of the target vehicle when the current scene level of the target vehicle is higher than the target scene level challenged by the target vehicle, and the scene adaptation score is less than the scene adaptation qualification threshold; and continue the scene switching level test of the target vehicle when the current scene level is not higher than the target scene level, and / or the scene adaptation score is greater than or equal to the scene adaptation qualification threshold.

[0115] In one embodiment, the decision module 30 is further configured to: after the above-mentioned step of continuing the scene switching level test of the target vehicle, trigger the calculation module 20 to calculate the final score of the current scene switching level based on the scene adaptability score and the baseline score of the current scene switching level.

[0116] In one embodiment, the threshold value for scene adaptability is in the range of 0.3 to 0.6.

[0117] In one embodiment, the calculation module 20 is specifically used to: determine the actual behavior of the target vehicle based on behavioral data; determine the deviation parameter coefficients of the actual behavior and the expected standard behavior during the scene switching process in each dimension; and substitute the deviation parameters of each dimension into the weighted scoring model to calculate the scene adaptability score of the target vehicle during the scene switching process, wherein the weighted scoring model is used to reflect the correlation between the scene adaptability score and the deviation parameters of each dimension and their corresponding weight coefficients.

[0118] In one embodiment, the driver's license testing system further includes a debriefing module (not shown) for post-test debriefing steps:

[0119] Compare the final score of the scene transition level with the preset passing score to determine if there is room for improvement in the target vehicle's scene transition capability. If so, output improvement suggestions; and / or,

[0120] Record behavioral data for the test period, including at least one of the following: scene switching time points, deviation parameters for each dimension, corresponding weight coefficients, scene adaptability score, real-time trajectory data of the target vehicle, and decision operation records.

[0121] In one embodiment, the dimensions of the aforementioned deviation parameter include at least one of reaction delay time deviation, trajectory deviation, number of decision-making errors, and comfort index deviation.

[0122] In one embodiment, the above-mentioned dynamic transition test scenario includes at least one of the following:

[0123] Switch from city roads to highway entrance ramps;

[0124] From sunny daytime weather to rainy or foggy nighttime weather;

[0125] Shifting from one-way, low-density traffic flow to multi-way, complex intersections;

[0126] Switch from driving straight through unobstructed areas to avoiding sudden obstacles.

[0127] In one embodiment, the decision module 30 is further configured to: perform at least one of the following operations when it is determined that the scene switching level test of the target vehicle will be terminated:

[0128] The scene adaptation score for the current scene transition level is determined to be 0;

[0129] The safety officer takeover signal is automatically triggered, which prompts the safety officer to guide the target vehicle to a safe area.

[0130] Record the reason for test termination, the time of termination, and the behavioral data for the corresponding time period.

[0131] By recording the reasons for test termination and related data, subsequent analysis can be conducted to provide a basis for test optimization and vehicle improvement.

[0132] In one embodiment, scenarios of varying complexity from low to high include basic complexity scenarios, medium complexity scenarios, high complexity scenarios, and extremely high complexity scenarios. The complexity of each scenario level is determined by traffic flow density, environmental interference factors, and operational difficulty coefficients.

[0133] The driver's license testing system provided in this application, employing the driver's license testing method described in the above embodiments, can solve the technical problems of one-sided evaluation of driver's license testing scenario switching and rigid termination conditions in the prior art. Compared with the prior art, the beneficial effects of the driver's license testing system provided in this application are the same as those of the driver's license testing method provided in the above embodiments, and other technical features of the driver's license testing system are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0134] This application provides a driver's license testing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the driver's license testing method in the first embodiment described above.

[0135] The following is for reference. Figure 6 The diagram illustrates a structural schematic suitable for implementing the driver's license testing equipment in the embodiments of this application. The driver's license testing equipment in the embodiments of this application may include, but is not limited to, fixed or mobile terminals such as vehicle-mounted testing terminals, desktop computers, and laptops. Figure 6 The driver's license testing equipment shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0136] like Figure 6As shown, the driver's license testing equipment may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the driver's license testing equipment. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus 1005. Typically, the following systems can be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, etc.; an output device 1008 including, for example, a liquid crystal display, a speaker, etc.; a storage device 1003 including, for example, a hard disk; and a communication device 1009. The communication device 1009 allows the driver's license testing equipment to exchange data via wireless or wired communication with other devices. Although the diagram shows driver's license testing equipment with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0137] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0138] The driver's license testing equipment provided in this application, employing the driver's license testing method described in the above embodiments, can solve the technical problems of inaccurate evaluation of driver's license testing scenario switching and rigid termination conditions in the prior art. Compared with the prior art, the beneficial effects of the driver's license testing equipment provided in this application are the same as those of the driver's license testing method provided in the above embodiments, and other technical features of this driver's license testing equipment are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0139] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0140] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A driver's license testing method, characterized in that, include: Acquire behavioral data of the target vehicle in a preset scenario switching test level, wherein the preset scenario switching test level includes dynamic transition test scenarios with different complexity from low to high. Based on the behavioral data, the scene adaptability score of the target vehicle during the scene switching process is determined; Based on the scene adaptability score, determine whether to terminate the scene switching level test for the target vehicle.

2. The driver's license testing method as described in claim 1, characterized in that, The step of determining whether to terminate the scene switching level test for the target vehicle based on the scene adaptability score includes: If the current scene level of the target vehicle is higher than the target scene level that the target vehicle is challenging, and the scene adaptation score is less than the scene adaptation qualification threshold, then the scene switching level test of the target vehicle will be terminated. If the current scene level is not higher than the target scene level, and / or the scene adaptation score is greater than or equal to the scene adaptation qualification threshold, then the scene switching level test for the target vehicle continues.

3. The driver's license testing method as described in claim 2, characterized in that, Following the step of continuing the scene switching level test for the target vehicle, the method further includes: The final score of the current scene switching level is calculated based on the scene adaptability score and the baseline score of the current scene switching level.

4. The driver's license testing method as described in claim 2, characterized in that, The threshold value for scene adaptability is between 0.3 and 0.

6.

5. The driver's license testing method as described in any one of claims 1 to 4, characterized in that, The determination of the scene adaptability score of the target vehicle during scene switching based on the behavioral data includes: Based on the behavioral data, the actual behavior of the target vehicle is determined; Determine the deviation parameters of the actual behavior from the expected standard behavior during scene switching in each dimension; The deviation parameters of each dimension are substituted into the weighted deduction model to calculate the scene adaptability score of the target vehicle during scene switching. The weighted deduction model is used to reflect the correlation between the scene adaptability score and the deviation parameters of each dimension and their corresponding weight coefficients.

6. The driver's license testing method as described in claim 5, characterized in that, The dimensions of the deviation parameter include at least one of the following: reaction delay time deviation, trajectory deviation, number of decision-making errors, and comfort index deviation.

7. The driver's license testing method as described in claim 5, characterized in that, It also includes post-test debriefing steps: Compare the final score of the scene switching level with the preset passing score to determine whether there is room for improvement in the scene switching capability of the target vehicle. If so, output improvement suggestions. And / or, Record behavioral data for the test period, including at least one of the following: scene switching time points, deviation parameters for each dimension, corresponding weight coefficients, scene adaptability score, real-time trajectory data of the target vehicle, and decision operation records.

8. The driver's license testing method as described in any one of claims 1 to 4, characterized in that, The dynamic transition test scenario includes at least one of the following: Switch from city roads to highway entrance ramps; From sunny daytime weather to rainy or foggy nighttime weather; Shifting from one-way, low-density traffic flow to multi-way, complex intersections; Switch from driving straight through unobstructed areas to avoiding sudden obstacles.

9. The driver's license testing method as described in any one of claims 1 to 4, characterized in that, If it is determined that the scene switching level test of the target vehicle will be terminated, then at least one of the following operations will be performed: The scene adaptation score for the current scene transition level is determined to be 0; The safety officer takeover signal is automatically triggered, and the safety officer takeover signal is used to prompt the safety officer to guide the target vehicle to a safe area; Record the reason for test termination, the time of termination, and the behavioral data for the corresponding time period.

10. The driver's license testing method as described in any one of claims 1 to 4, characterized in that, The scenarios with varying degrees of complexity, from low to high, include basic complexity scenarios, medium complexity scenarios, relatively high complexity scenarios, and extremely high complexity scenarios. The complexity of each scenario level is determined by traffic flow density, environmental interference factors, and operational difficulty coefficients.

11. A driver's license testing device, characterized in that, The driver's license testing device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the driver's license testing method as described in any one of claims 1 to 10.

Images