Test and analysis method, system and equipment of lane departure suppression system and medium

Abstract

The invention provides a test and analysis method, system and device for a lane departure suppression system and a medium, and belongs to the technical field of intelligent driving. The method comprises the following steps: configuring a heavy commercial vehicle equipped with a to-be-tested system, constructing a multi-dimensional data acquisition system, and synchronously acquiring vehicle dynamic, system state, driver operation and vehicle pose signals; executing a test scene based on a plurality of preset man-machine interaction modes, exciting system intervention and recording data, and forming a synchronous test data set; extracting single intervention event data, and calculating an intervention conflict degree index for describing man-machine mechanics conflicts, a takeover behavior index for evaluating driver response and a dynamic comfort index for evaluating process smoothness; after the indexes are standardized, a comprehensive man-machine collaboration degree score is generated based on weight model fusion calculation, and a report is output. According to the method, the multi-dimensional quantitative index group and the comprehensive evaluation model are constructed, so that the man-machine cooperation performance of the system of the heavy-duty commercial vehicle under the complex working condition is accurately evaluated.

Description

Technical Field

[0001] This invention belongs to the field of intelligent driving technology, and more specifically relates to a testing and analysis method, system, equipment and medium for a lane departure suppression system. Background Technology

[0002] Currently, lane departure mitigation systems on heavy commercial vehicles have evolved from early warning functions to control systems with active steering or braking intervention capabilities, becoming a key driver assistance safety technology. Industry testing and evaluation of these systems generally focus on verifying their basic functions and performance. This mainly includes: whether the system can effectively trigger and complete correction actions under preset deviation conditions; and measuring its basic performance parameters, such as intervention delay time, the smoothness of the vehicle's return trajectory, and the maximum lateral acceleration during intervention. These methods constitute the benchmark test for determining whether the system's functionality is up to standard.

[0003] However, the aforementioned traditional evaluation systems suffer from a fundamental limitation: they treat the system and the driver as independent test subjects, primarily evaluating performance from the single dimension of the vehicle and control algorithm. This "machine-centric" testing paradigm completely ignores the basic fact that in real-world driving scenarios, the driver is always at the core of the control loop. The system does not operate in a vacuum; every intervention inevitably interacts with the driver's real-time state and operational intentions.

[0004] This "human-machine separation" evaluation approach has led to several key bottlenecks in the development and verification of existing technologies: First, it is impossible to quantify and assess "human-machine conflict." When the system actively applies corrective torque, if the driver reverses the operation due to emergency obstacle avoidance or other intentions, potential control conflicts and safety risks arise. Existing methods lack objective measurement standards for the severity of such conflicts. Second, it is impossible to scientifically evaluate driver acceptance and comfort. Overly abrupt or forceful intervention strategies, even if they successfully correct lane departure, may be disabled due to driver discomfort. Existing vehicle motion-based indicators are difficult to directly correlate with the driver's true subjective feelings. Finally, the verification of the system's intelligence level is insufficient. Existing tests struggle to accurately assess the rationality of the system's decisions in complex human-machine co-driving scenarios, such as distinguishing between unintentional deviations and conscious lane changes by the driver. This results in a lack of data support for parameter optimization, leading to a dilemma of subjective trade-offs.

[0005] Therefore, the core technical problem that urgently needs to be overcome in this field is that existing testing methods, due to the lack of consideration for the driver interaction dimension, cannot construct a scientific, quantitative, and comprehensive evaluation system for "human-machine collaboration." This not only creates blind spots in the interactive safety and user experience of the system in real-world use, but also severely restricts the iterative optimization of its control strategies towards a more intelligent and human-centered direction. Summary of the Invention

[0006] To address the above problems, the present invention aims to provide a testing and analysis method, system, device, and medium for lane departure mitigation systems. By constructing a group of quantitative indicators and a comprehensive evaluation model based on multi-dimensional synchronous data, it achieves accurate and objective evaluation of the lane departure mitigation system of heavy commercial vehicles in terms of human-machine conflict, takeover behavior, and dynamic comfort, effectively solving the problem of the difficulty in scientifically evaluating human-machine cooperative performance due to the complexity of vehicle dynamics.

[0007] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, embodiments of this application provide a method for testing and analyzing a lane departure suppression system, including: A heavy commercial vehicle equipped with a lane departure mitigation system under test is configured, and a multi-dimensional data acquisition system integrated on the vehicle is constructed to simultaneously collect multi-dimensional data; the multi-dimensional data includes vehicle dynamic signals, lane departure mitigation system status signals, driver operation signals, and vehicle position and posture signals; Based on multiple preset human-computer interaction modes, the heavy commercial vehicle is driven to execute corresponding test scenarios to stimulate the intervention behavior of the lane departure suppression system under test and simultaneously use a multi-dimensional data acquisition system to record multi-dimensional data to form a multi-dimensional synchronous test dataset. Based on a multi-dimensional synchronous test dataset, process data of a single intervention event is extracted, and intervention conflict degree index for characterizing human-machine mechanical conflict, takeover behavior index for assessing driver response state, and dynamic comfort index for evaluating the smoothness of the intervention process are calculated as indicators to be evaluated. The evaluation indicators are standardized and fused based on a preset weight model to generate a comprehensive human-machine collaboration score, and a test analysis report is output.

[0008] In one optional implementation, the vehicle dynamic signals include vehicle speed, yaw rate, lateral acceleration, steering wheel angle, and steering wheel torque acquired via the vehicle CAN bus. The lane departure mitigation system status signal includes the activation status of the lane departure mitigation system and the system-requested auxiliary steering torque T. sys (t) or braking pressure, and intervention level; The driver operation signal includes the actual steering wheel torque T applied by the driver. driver (t), turn signal status, driver's facial orientation, and eye movement signals; The vehicle pose signal includes the vehicle's lateral position y(t) and heading angle relative to the lane line, acquired by a high-precision GPS / INS integrated navigation system.

[0009] In one optional implementation, the preset multiple human-computer interaction modes include: Unintentional deviation mode corresponds to the test scenario where the driver takes both hands off the steering wheel; Mild resistance mode corresponds to the test scenario where the driver applies and maintains a counter-torque below a preset threshold when the lane departure mitigation system intervenes; Strong resistance mode corresponds to test scenarios where the driver applies a reverse torque greater than a preset threshold when the lane departure mitigation system intervenes; The cooperative operation mode corresponds to the test scenario where the driver applies auxiliary steering torque after the lane departure mitigation system intervenes.

[0010] In an optional implementation, the intervention conflict index includes the torque conflict integral C. T and intention divergence index I d ; Torque conflict integral C T The calculation process includes: considering the time t from the start of the lane departure mitigation system intervention... start Until the end time t end The intervention process is calculated using the following formula: Torque conflict integral C T :

[0011] Intent to deviate from index I d Based on the intervention trigger time t of the lane departure suppression system trigger Previous preset time window [t0, t trigger The data within is used to quantify the consistency between the driver's operational intentions and the vehicle's deviation from the intended direction; the intention deviation index I d The calculation formula is as follows:

[0012] Where y(t) is the lateral position of the vehicle relative to the lane line, and y′(t) is its rate of change; when I d When I > 0, it indicates a deviation from the intended intent; when I d When <0, it indicates intentional collaboration.

[0013] In an optional implementation, the takeover behavior indicator includes: intervention interruption rate R. interrupt and average takeover time ; Where M is the total number of tests, and K is the number of times the driver voluntarily terminated the intervention;

[0014] Where N is the total number of effective intervention events, t action The point in time at which the driver first applies an intentional steering, acceleration, or braking action.

[0015] In an optional implementation, the dynamic comfort index includes: intervention abruptness J. sys And vehicle motion oscillation index O vehicle ; Intervention abruptness J sys This is obtained by calculating the maximum rate of change of the torque signal during the initial rising phase of the lane departure mitigation system intervention, i.e.:

[0016] Vehicle motion oscillation index O vehicle By performing frequency domain analysis on the vehicle yaw rate signal ω(t) during the lane departure mitigation system intervention process, the values ​​in the human-sensitive frequency band [f] are calculated. l ,f h The average power spectral density within the range is obtained, and the calculation formula is:

[0017] Among them, f l and f h The preset lower and upper limits of frequency, It is the frequency domain function corresponding to ω(t).

[0018] In an optional implementation, the preset weight model includes:

[0019] Among them, S HMI The overall score is the score for human-computer collaboration. Let j be the weight of the indicator to be evaluated. Let be the standardized value of the j-th indicator to be evaluated, and n be the total number of indicators to be evaluated.

[0020] Secondly, embodiments of this application also provide a testing and analysis system for a lane departure suppression system, comprising: The test system construction and signal definition module is used to configure a heavy commercial vehicle equipped with the lane departure suppression system under test, and to build a multi-dimensional data acquisition system integrated on the vehicle to simultaneously collect multi-dimensional data. The multi-dimensional data includes vehicle dynamic signals, lane departure suppression system status signals, driver operation signals, and vehicle position and posture signals. The test condition execution module is used to drive the heavy commercial vehicle to execute corresponding test scenarios based on a variety of preset human-computer interaction modes, so as to stimulate the intervention behavior of the lane departure suppression system under test and simultaneously use the multi-dimensional data acquisition system to record multi-dimensional data to form a multi-dimensional synchronous test dataset. The human-machine collaboration index quantification module is used to extract process data of a single intervention event based on a multi-dimensional synchronous test dataset, and calculate the intervention conflict degree index used to characterize human-machine mechanical conflict, the takeover behavior index used to evaluate the driver's response state, and the dynamic comfort index used to evaluate the smoothness of the intervention process, as indicators to be evaluated. The comprehensive evaluation and report generation module is used to standardize the indicators to be evaluated, perform fusion calculation based on a preset weight model, generate a comprehensive human-machine collaboration score, and output a test analysis report.

[0021] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the test and analysis method for the lane departure suppression system as described in any of the above.

[0022] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the testing and analysis method for the lane departure suppression system as described in any of the above claims.

[0023] As can be seen from the above technical solutions, the present invention has the following advantages: The testing and analysis method for the lane departure mitigation system provided in this application simultaneously collects vehicle dynamics, lane departure mitigation system control signals, and driver operation signals during the testing process. Based on these signals, a group of indicators for quantifying human-machine interaction quality is calculated, including but not limited to intervention conflict degree, driver takeover behavior, and dynamic comfort indicators. Finally, by fusing these indicators, a comprehensive human-machine coordination evaluation report is generated. This application is the first to use "human-machine coordination" as the core evaluation dimension of the lane departure mitigation system, solving the deficiency of existing technologies that only focus on functional effectiveness while neglecting interaction quality and driving experience. This provides data support for system optimization and significantly improves the system's safety, comfort, and user acceptance.

[0024] This application achieves objective quantification of human-computer interaction quality, filling a gap in the evaluation system: for the first time, subjective concepts such as the elusive "human-computer conflict", "driving comfort" and "willingness to take over" are transformed into a series of measurable and calculable objective physical indicators (such as torque conflict integral, intervention abruptness, etc.), enabling the evaluation system to expand from a single functional verification to a comprehensive experience evaluation.

[0025] This application significantly improves the development and optimization efficiency of lane departure mitigation systems: it provides control system engineers with clear optimization objectives and data support. Engineers can optimize the compliance of the control algorithm based on the high "torque conflict integral" result, and adjust the torque ramp rate based on the high "intervention abruptness" result. This transforms parameter tuning from "experience-driven" to "data-driven," shortening the development cycle.

[0026] This application effectively safeguards the system's functional safety and user acceptance: by testing under "strong adversarial conditions" and using the "intervention conflict degree" indicator, system design flaws that may cause dangerous conflicts during driver emergency avoidance can be identified in advance. Simultaneously, by optimizing the "dynamic comfort" indicator, driver trust and acceptance can be significantly improved, preventing users from disabling the system due to poor experience, thus allowing the safety functions to truly function.

[0027] This application provides a standardized and reproducible testing and evaluation process, enabling fair comparison of lane departure mitigation systems from different manufacturers and versions under the same "ruler," providing a powerful decision-making tool for OEMs in selection and system suppliers in technology iteration. Attached Figure Description

[0028] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 A flowchart illustrating the testing and analysis method for the lane departure suppression system provided in this application.

[0030] Figure 2 A schematic diagram of the structure of the test and analysis system for the lane departure suppression system provided in this application.

[0031] Figure 3 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0032] The various embodiments of this disclosure will be described more fully in the detailed steps of the testing and analysis methods for the lane departure suppression system described below. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0033] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] Please see Figure 1 The diagram shows a flowchart of a testing and analysis method for a lane departure suppression system in a specific embodiment. The method includes: S1: A heavy commercial vehicle equipped with a lane departure suppression system to be tested, and a multi-dimensional data acquisition system integrated on the vehicle is built to collect multi-dimensional data simultaneously; the multi-dimensional data includes vehicle dynamic signals, lane departure suppression system status signals, driver operation signals and vehicle position signals.

[0036] In a specific implementation, a heavy commercial vehicle equipped with a lane departure mitigation system is configured, and the vehicle is equipped with a high-precision multi-dimensional data acquisition system to simultaneously collect key sensors and signals from multiple dimensions.

[0037] Key sensors and signals include: Vehicle dynamic signals: collected via the vehicle's CAN bus, including vehicle speed, yaw rate, lateral acceleration, steering wheel angle, and steering wheel torque.

[0038] Lane departure mitigation system status signals: including system activation status and the system-requested auxiliary steering torque T. sys (t) or braking pressure, intervention level, etc.

[0039] Driver operation signal: The actual steering wheel torque T applied by the driver. driver (t) Turn signal status.

[0040] Vehicle position and attitude signal: The vehicle's lateral position y(t) and heading angle relative to the lane line are collected through a high-precision GPS / INS integrated navigation system.

[0041] Additionally, a computer running high-precision vehicle dynamics simulation software such as CarSim / TruckSim can be used to simulate vehicle dynamics. A virtual scene generation computer is used to generate a view including lane lines. A video injection device is used to inject virtual lane line images into the vehicle's forward-facing camera in real time, replacing real images.

[0042] S2: Based on multiple preset human-computer interaction modes, drive the heavy commercial vehicle to execute corresponding test scenarios to stimulate the intervention behavior of the lane departure suppression system under test and simultaneously use the multi-dimensional data acquisition system to record multi-dimensional data to form a multi-dimensional synchronous test dataset.

[0043] In a specific implementation, the preset multiple human-computer interaction modes include: Unintentional deviation mode corresponds to the test scenario where the driver takes both hands off the steering wheel; Mild resistance mode corresponds to the test scenario where the driver applies and maintains a counter-torque below a preset threshold when the lane departure mitigation system intervenes; Strong resistance mode corresponds to test scenarios where the driver applies a reverse torque greater than a preset threshold when the lane departure mitigation system intervenes; The cooperative operation mode corresponds to the test scenario where the driver applies auxiliary steering torque after the lane departure mitigation system intervenes.

[0044] For example, within the safe area of ​​the test track, the driver operates the test vehicle from inside the actual vehicle. Test engineers assist in setting up the following typical operating scenarios and executing the tests: 1. Unintentional deviation from the driving condition: When the vehicle is traveling at 80 km / h on a straight road, the driver takes both hands off the steering wheel, and the vehicle naturally deviates from the lane.

[0045] 2. Mild resistance condition: Repeat condition 1, but after the lane departure mitigation system intervenes for about 0.5 seconds, the driver applies a slight and steady torque of about 2 N.m in the direction of deviation.

[0046] 3. Intense Countermeasure Condition: Repeat Condition 1, but after the lane departure mitigation system intervenes for about 0.3 seconds, the driver quickly and forcefully applies a torque of about 10 N·m in the direction of deviation to simulate emergency obstacle avoidance.

[0047] Each operating condition was repeated at least 10 times to ensure the statistical significance of the data.

[0048] S3: Based on the multi-dimensional synchronous test dataset, process data of a single intervention event is extracted, and intervention conflict degree index for characterizing human-machine mechanical conflict, takeover behavior index for evaluating driver response state, and dynamic comfort index for evaluating the smoothness of the intervention process are calculated as indicators to be evaluated.

[0049] The intervention conflict index includes the torque conflict integral C. T and intention divergence index I d ; Torque conflict integral C T The calculation process includes: considering the time t from the start of the lane departure mitigation system intervention... start Until the end time t end The intervention process is calculated using the following formula: Torque conflict integral C T :

[0050] The higher the value, the more intense the "competition" between humans and machines, and the greater the degree of conflict.

[0051] Intent to deviate from index I d Based on the intervention trigger time t of the lane departure suppression system trigger Previous preset time window [t0, t trigger The data within is used to quantify the consistency between the driver's operational intentions and the vehicle's deviation from the intended direction; the intention deviation index I d The calculation formula is as follows:

[0052] Where y(t) is the lateral position of the vehicle relative to the lane line, and y′(t) is its rate of change; when I d When I > 0, it indicates a deviation from the intended intent; when I d When the torque is less than 0, it indicates intentional coordination. Therefore, if the driver's torque direction is to straighten the vehicle, it is considered intentional. Figure 1 Conversely, if the intention is to align, then it is to deviate. This indicator can be used as a Boolean value or a weighted coefficient to explain the root cause of the degree of conflict. The takeover behavior indicators include: intervention interruption rate R. interrupt and average takeover time These indicators are used to assess a driver's acceptance of system intervention and willingness to take over.

[0053]

[0054] Where M represents the total number of tests, and K represents the number of times the driver actively terminated the intervention. It can be seen that the intervention interruption rate is used to count the proportion of the total number of tests in which the driver actively terminated the intervention by applying a reverse torque exceeding a set threshold before the system completed its intervention.

[0055]

[0056] Where N is the total number of effective intervention events, t action The mean takeover time is the point in time at which the driver first applies an intentional steering, acceleration, or braking action. Therefore, the mean takeover time is calculated as the average time interval between the start of the intervention and the driver's first intentional action (such as counter-steering, acceleration, or braking) after the system intervention begins. An excessively short takeover time may indicate that the intervention strategy is causing driver anxiety or a lack of trust.

[0057] The dynamic comfort index includes: intervention abruptness J. sys And vehicle motion oscillation index O vehicle ; Intervention abruptness J sys This is obtained by calculating the maximum rate of change of the torque signal during the initial rising phase of the lane departure mitigation system intervention, i.e.:

[0058] As can be seen, the intervention abruptness is used to calculate the initial rate of increase of the system intervention torque. This value directly reflects the degree of "abruptness" or "gentleness" of the system intervention.

[0059] Vehicle motion oscillation index O vehicle By performing frequency domain analysis on the vehicle yaw rate signal ω(t) during the lane departure mitigation system intervention process, the corresponding frequency domain function is generated. And calculate in the human sensitive frequency band [f l ,f h The average power spectral density within the range is obtained, and the calculation formula is:

[0060] Among them, f l and f h These are the preset lower and upper frequency limits. It can be seen that the vehicle motion oscillation index is used to calculate the power spectral density of the vehicle's yaw rate or lateral acceleration signal within a specific frequency band during intervention. The more severe the oscillation, the worse the comfort.

[0061] S4: Standardize the indicators to be evaluated, perform fusion calculation based on the preset weight model, generate a comprehensive human-machine collaboration score, and output a test analysis report.

[0062] In a specific implementation, a preset weighting model is used to normalize and weight the calculated multiple indicators to be evaluated, forming a comprehensive "human-machine collaboration score".

[0063] The preset weight model includes:

[0064] Among them, S HMI The overall score is the score for human-computer collaboration. The weight of the j-th indicator to be evaluated can be determined based on expert experience or statistical analysis. Let be the standardized value of the j-th indicator to be evaluated, and n be the total number of indicators to be evaluated.

[0065] Finally, a test report is generated, containing details of each sub-indicator and the overall score, intuitively demonstrating the human-machine collaborative performance of the lane departure mitigation system under test. The report clearly displays the individual indicator scores and overall scores in the form of tables and radar charts, and compares them with the benchmark system, intuitively pointing out the advantages and disadvantages of the tested system.

[0066] To better illustrate the specific implementation process of the testing and analysis method for the lane departure suppression system disclosed in this invention, the following example provides a detailed explanation of the testing and analysis process: In this example, based on steps S3 and S4 of this method, we conducted a series of standard tests (M=20 times) on the lane departure mitigation system, covering various scenarios such as unintentional deviation and driver resistance. The following is the processed summary data: First, based on step S3, the following indicators are analyzed and calculated: (1) Intervention conflict index: Torque conflict integral (C T ): Calculate C for each of the 20 tests. T Values. Assume an average value of 8.2 Nm·s, a minimum value of 0.5 Nm·s (good coordination), and a maximum value of 18.0 Nm·s (severe conflict).

[0067] Intentional divergence index (I) d ): In 20 tests, it was judged as I 3 times. d >0 (intentional deviation), the remaining 17 times are I. d ≤0 (intentional cooperation or no intention).

[0068] (2) Takeover behavior indicators: Intervention interruption rate (R) interrupt In 20 tests, the driver actively terminated the intervention 4 times by applying a reverse torque exceeding a threshold (e.g., 10 Nm). Therefore, K=4, M=20, Rinterrupt =4 / 20 = 0.20 (or 20%).

[0069] Average takeover time ( ): Among all valid intervention events that were not interrupted by the driver (N=16 times), the average time interval between the driver's first intentional action (such as a slight correction of direction) was 1.2 seconds.

[0070] (3) Dynamic comfort index: Intervention abruptness (J) sys ): The maximum value of the initial rate of increase of system torque was calculated during 20 interventions, and its average value was 65 Nm / s.

[0071] Vehicle motion oscillation index (O) vehicle ): Calculate the average power spectral density of the yaw rate in the sensitive frequency band [0.5Hz, 2.0Hz] during each intervention process. The average value is 0.15 (deg / s)² / Hz.

[0072] Then, based on step S4, the indicators are standardized and the comprehensive score is calculated.

[0073] Step 1: Standardize the indicators.

[0074] Map the raw values ​​of each indicator to a score range of [0, 100], where a higher score indicates better human-machine collaboration. Define "optimal" and "worst" values ​​for each indicator as benchmarks. See Table 1 below for details.

[0075] Table 1: Standardized Comparison Table of Evaluation Indicators

[0076] Step 2: Fusion based on a preset weight model.

[0077] Through expert Delphi method or historical data analysis, we determined the weights of each indicator. j This reflects its relative importance to the overall "human-machine collaboration". See Table 2 below for details.

[0078] Table 2: Evaluation Indicator Score Comparison Table

[0079] Step 3: Calculate the overall human-machine collaboration score.

[0080] According to formula S HMI = Σ (w j × S j Referring to Table 2 above, the final score S can be calculated. HMI = 58.84 points (out of 100).

[0081] Finally, output the test analysis report.

[0082] The specific contents of the human-machine collaboration test analysis report are as follows: ① Tested System: Type A Lane Departure Suppression System ② Test scenario: Standard comprehensive operating conditions (20 valid tests in total) ③ Overall score: 58.8 / 100 in: ①Intent recognition (I d =70) is relatively the best, indicating that the system can correctly understand the driver's intentions in most cases.

[0083] ② Conflict Management (C T =59) and takeover behavior (R interrupt =50, =55.6) The performance is below average, indicating that when the system decides to intervene, its control method does not cooperate smoothly with the driver, resulting in a certain degree of resistance and early driver takeover.

[0084] ③ Dynamic comfort (J sys =55, O vehicle =60) Performance was average, the intervention and start-up were rather abrupt, and caused some body sway.

[0085] Compared with the benchmark system (Competitor B, score 72.3): ① Weakness: System A lags significantly behind System B in conflict management and intervention smoothness (System B scored 75 and 70 respectively). This is the main reason for its lower overall score.

[0086] ② Advantage: The accuracy of intent recognition of system A is comparable to that of system B.

[0087] Suggestions for improvement: ① Optimize control strategy: Focus on reducing the initial rate of increase of intervention torque (J) sys It also employs a smoother torque control curve to reduce torque conflict integral (C). T ) and vehicle oscillation (O vehicle ).

[0088] ② Adjusting the trigger threshold: Appropriately increasing the intervention trigger sensitivity to reduce slight resistance to driver intent in boundary situations may help improve takeover time (O). vehicle ) and interruption rate (R interrupt ).

[0089] The above example fully demonstrates the entire analytical process, from raw data to six core metrics, and finally to a single, comparable composite score. This S...HMI The score of 58.84 provides management with an intuitive performance overview, while the underlying sub-indicators offer the engineering team clear, data-driven optimization directions, perfectly demonstrating the value of the proposed method.

[0090] In this embodiment, a multi-dimensional data acquisition system and typical human-machine co-driving test scenarios are constructed. Based on the collected synchronous data, a group of quantitative indicators covering three dimensions—"conflict, takeover, and comfort"—is calculated and finally integrated to generate a comprehensive human-machine coordination score. The beneficial effect of this method is that it provides, for the first time, a systematic and quantifiable human-machine coordination performance testing and evaluation system for lane departure mitigation systems in heavy-duty commercial vehicles. This method specifically considers the characteristics of commercial vehicles, such as large steering wheel torque and the significant impact of load changes on vehicle dynamics. By directly measuring and analyzing core physical signals such as torque interaction between the system and the driver, it can more profoundly and accurately characterize the unique human-machine interaction contradictions and coordination levels of heavy-duty vehicles. The final comprehensive report not only comprehensively and objectively evaluates the overall performance of the system in terms of safety intervention, driver acceptance, and ride comfort, but also provides precise data feedback and clear improvement directions for the system's optimized design and calibration, thereby effectively improving the actual user experience and safety benefits of advanced driver assistance systems for heavy-duty commercial vehicles.

[0091] like Figure 2 As shown, the following are embodiments of the testing and analysis system for the lane departure suppression system provided in this disclosure. This system and the testing and analysis methods for the lane departure suppression system in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the testing and analysis system for the lane departure suppression system, please refer to the embodiments of the testing and analysis methods for the lane departure suppression system described above.

[0092] A testing and analysis system for lane departure mitigation systems includes: The test system construction and signal definition module is used to configure a heavy commercial vehicle equipped with the lane departure suppression system under test, and to build a multi-dimensional data acquisition system integrated on the vehicle to simultaneously collect multi-dimensional data. The multi-dimensional data includes vehicle dynamic signals, lane departure suppression system status signals, driver operation signals, and vehicle position and posture signals.

[0093] The test condition execution module is used to drive the heavy commercial vehicle to execute corresponding test scenarios based on a variety of preset human-computer interaction modes, so as to stimulate the intervention behavior of the lane departure suppression system under test and simultaneously use the multi-dimensional data acquisition system to record multi-dimensional data to form a multi-dimensional synchronous test dataset.

[0094] The human-machine collaboration index quantification module is used to extract process data of a single intervention event based on a multi-dimensional synchronous test dataset, and calculate intervention conflict degree index for characterizing human-machine mechanical conflict, takeover behavior index for evaluating driver response state, and dynamic comfort index for evaluating the smoothness of the intervention process, as indicators to be evaluated.

[0095] The comprehensive evaluation and report generation module is used to standardize the indicators to be evaluated, perform fusion calculation based on a preset weight model, generate a comprehensive human-machine collaboration score, and output a test analysis report.

[0096] The lane departure mitigation system testing and analysis system provided in this embodiment constructs a group of quantitative indicators across three dimensions: "conflict, takeover, and comfort." Based on high-precision synchronous data, it calculates specific indicators such as torque conflict integral, intention deviation index, intervention interruption rate, and dynamic comfort, forming a multi-dimensional and quantifiable human-machine collaboration evaluation system. This method specifically considers complex operating conditions such as the large steering wheel torque of heavy commercial vehicles and significant differences in vehicle dynamics due to load variations, enabling a more accurate characterization and evaluation of the unique human-machine interaction and adversarial processes of this type of vehicle. Finally, the system outputs a collaboration score through a comprehensive evaluation model, providing a scientific and comprehensive technical means for objective comparison of system performance, strategy optimization, and the establishment of industry testing standards.

[0097] Figure 3 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0098] The testing and analysis method for the lane departure suppression system provided in this application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0099] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0100] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0101] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0102] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0103] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0104] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0105] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0106] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0107] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0108] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0109] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0110] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0111] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0112] The aforementioned electronic device realizes the testing and analysis method of the lane departure suppression system of this application. By constructing a group of quantitative indicators and a comprehensive evaluation model based on multi-dimensional synchronous data, it achieves accurate and objective evaluation of the human-machine collaborative performance of the lane departure suppression system of heavy commercial vehicles under complex loads and dynamic characteristics, and achieves the beneficial effect of providing a scientific basis for system optimization and performance evaluation.

[0113] The storage medium provided in this application stores a program product capable of implementing test and analysis methods for lane departure suppression systems.

[0114] The testing and analysis methods for lane departure mitigation systems include: A heavy commercial vehicle equipped with a lane departure mitigation system under test is configured, and a multi-dimensional data acquisition system integrated on the vehicle is constructed to simultaneously collect multi-dimensional data; the multi-dimensional data includes vehicle dynamic signals, lane departure mitigation system status signals, driver operation signals, and vehicle position and posture signals; Based on multiple preset human-computer interaction modes, the heavy commercial vehicle is driven to execute corresponding test scenarios to stimulate the intervention behavior of the lane departure suppression system under test and simultaneously use a multi-dimensional data acquisition system to record multi-dimensional data to form a multi-dimensional synchronous test dataset. Based on a multi-dimensional synchronous test dataset, process data of a single intervention event is extracted, and intervention conflict degree index for characterizing human-machine mechanical conflict, takeover behavior index for assessing driver response state, and dynamic comfort index for evaluating the smoothness of the intervention process are calculated as indicators to be evaluated. The evaluation indicators are standardized and fused based on a preset weight model to generate a comprehensive human-machine collaboration score, and a test analysis report is output. In some possible implementations, the testing and analysis method of the lane departure suppression system of this disclosure can be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0115] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0116] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A testing and analysis method for a lane departure suppression system, characterized in that, include: A heavy commercial vehicle equipped with a lane departure mitigation system under test is configured, and a multi-dimensional data acquisition system integrated on the vehicle is constructed to simultaneously collect multi-dimensional data; the multi-dimensional data includes vehicle dynamic signals, lane departure mitigation system status signals, driver operation signals, and vehicle position and posture signals; Based on multiple preset human-computer interaction modes, the heavy commercial vehicle is driven to execute corresponding test scenarios to stimulate the intervention behavior of the lane departure suppression system under test and simultaneously use a multi-dimensional data acquisition system to record multi-dimensional data to form a multi-dimensional synchronous test dataset. Based on a multi-dimensional synchronous test dataset, process data of a single intervention event is extracted, and intervention conflict degree index for characterizing human-machine mechanical conflict, takeover behavior index for assessing driver response state, and dynamic comfort index for evaluating the smoothness of the intervention process are calculated as indicators to be evaluated. The evaluation indicators are standardized and fused based on a preset weight model to generate a comprehensive human-machine collaboration score, and a test analysis report is output.

2. The method of testing and analyzing a lane departure mitigation system of claim 1, wherein, The vehicle dynamic signals include vehicle speed, yaw rate, lateral acceleration, steering wheel angle, and steering wheel torque, all collected via the vehicle's CAN bus. The lane-departure mitigation system status signal comprises an activation status of the lane-departure mitigation system, a system-requested assist steering torque T sys (t) or brake pressure, and an intervention level; The driver operation signal comprises a driver actually applied steering wheel torque T driver (t), a steering light status, a driver's face orientation and eye movement signals; The vehicle pose signal includes the vehicle's lateral position y(t) and heading angle relative to the lane line, acquired by a high-precision GPS / INS integrated navigation system.

3. The method of testing and analysis of a lane departure mitigation system according to claim 1, characterized in that, The preset multiple human-computer interaction modes include: Unintentional deviation mode corresponds to the test scenario where the driver takes both hands off the steering wheel; Mild resistance mode corresponds to the test scenario where the driver applies and maintains a counter-torque below a preset threshold when the lane departure mitigation system intervenes; Strong resistance mode corresponds to test scenarios where the driver applies a reverse torque greater than a preset threshold when the lane departure mitigation system intervenes; The cooperative operation mode corresponds to the test scenario where the driver applies auxiliary steering torque after the lane departure mitigation system intervenes.

4. The method of testing and analysis of a lane departure mitigation system according to claim 2, characterized in that The intervention conflict indicator comprises a torque conflict integral C T and an intention deviation index I d ; Torque conflict integral C T The calculation process includes: considering the time t from the start of the lane departure mitigation system intervention... start Until the end time t end The intervention process is calculated using the following formula: Torque conflict integral C T : Intent to deviate from index I d Based on the intervention trigger time t of the lane departure suppression system trigger Previous preset time window [t0, t trigger The data within is used to quantify the consistency between the driver's operational intentions and the vehicle's deviation from the intended direction; the intention deviation index I d The calculation formula is as follows: Where y(t) is the lateral position of the vehicle relative to the lane line, and y′(t) is its rate of change; when I d When I > 0, it indicates a deviation from the intended intent; when I d When <0, it indicates intentional collaboration.

5. The method of testing and analysis of a lane departure mitigation system according to claim 4, characterized in that The takeover behavior index comprises: intervention interruption rate R interrupt and average takeover time ; Where M is the total number of tests, and K is the number of times the driver voluntarily terminated the intervention; where N is the total number of effective intervention events, t action is the time point at which the driver first applies an intentional steering, acceleration or braking operation.

6. The method of testing and analysis of a lane departure mitigation system according to claim 5, characterized in that The dynamic comfort indicator comprises an intervention jerk J sys and a vehicle motion oscillation index O vehicle ; Intervention abruptness J sys The maximum rate of change of the initial rising phase of the lane departure suppression system intervention torque signal is obtained by calculation, i.e.: Vehicle motion oscillation index O vehicle By performing frequency domain analysis on the vehicle yaw rate signal ω(t) during the lane departure mitigation system intervention process, the values ​​in the human-sensitive frequency band [f] are calculated. l ,f h The average power spectral density within the range is obtained, and the calculation formula is: Among them, f l and f h The preset lower and upper limits of frequency, It is the frequency domain function corresponding to ω(t).

7. The method of testing and analysis of a lane departure mitigation system according to claim 1, characterized in that, The preset weight model includes: Among them, S HMI The overall score is the score for human-computer collaboration. Let j be the weight of the indicator to be evaluated. Let be the standardized value of the j-th indicator to be evaluated, and n be the total number of indicators to be evaluated.

8. A test and analysis system for a lane departure mitigation system, characterized by The system employs the testing and analysis method for the lane departure suppression system as described in any one of claims 1 to 7; The system includes: The test system construction and signal definition module is used to configure a heavy commercial vehicle equipped with the lane departure suppression system under test, and to build a multi-dimensional data acquisition system integrated on the vehicle to simultaneously collect multi-dimensional data. The multi-dimensional data includes vehicle dynamic signals, lane departure suppression system status signals, driver operation signals, and vehicle position and posture signals. The test condition execution module is used to drive the heavy commercial vehicle to execute corresponding test scenarios based on a variety of preset human-computer interaction modes, so as to stimulate the intervention behavior of the lane departure suppression system under test and simultaneously use the multi-dimensional data acquisition system to record multi-dimensional data to form a multi-dimensional synchronous test dataset. The human-machine collaboration index quantification module is used to extract process data of a single intervention event based on a multi-dimensional synchronous test dataset, and calculate the intervention conflict degree index used to characterize human-machine mechanical conflict, the takeover behavior index used to evaluate the driver's response state, and the dynamic comfort index used to evaluate the smoothness of the intervention process, as indicators to be evaluated. The comprehensive evaluation and report generation module is used to standardize the indicators to be evaluated, perform fusion calculation based on a preset weight model, generate a comprehensive human-machine collaboration score, and output a test analysis report.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the test and analysis method for the lane departure suppression system as described in any one of claims 1 to 7.

10. A storage medium having stored thereon a computer program, characterized in that When the computer program is executed by the processor, it implements the steps of the test and analysis method for the lane departure suppression system as described in any one of claims 1 to 7.

Images