Intelligent driving sensing data evaluation system

Abstract

An intelligent driving sensing data evaluation system, comprising a wet and slippery bridge deck real-time monitoring module, a wet and slippery bridge deck sensing information processing module, a grip evaluation model construction module, a dynamic braking strategy adjustment module, and a feedback optimization and model update module. The wet and slippery bridge deck sensing information processing module is configured to acquire, in real time, wet and slippery bridge deck sensing information when a vehicle is moving at a high speed on a surface of a wet and slippery bridge, and analyze the acquired information to generate a wet and slippery bridge deck friction coefficient and a grip response hysteresis index respectively. The grip evaluation model construction module is configured to construct a grip evaluation model for the generated wet-slip bridge deck friction coefficient and grip response hysteresis index, generate a grip evaluation coefficient, and analyze the generated grip evaluation coefficient.

Description

Intelligent driving perception data evaluation system Technical Field

[0001] This invention relates to the field of driving perception data evaluation technology, and more specifically to an intelligent driving perception data evaluation system. Background Technology

[0002] Driving perception refers to the process by which intelligent driving vehicles perceive their surrounding environment in real time through various sensors (such as cameras, lidar, radar, and ultrasound), and identify and analyze key elements such as obstacles, pedestrians, traffic lights, and lane markings. During this process, the vehicle generates a large amount of perception data, including the distance, speed, position, shape, and category of objects, lane marking information, and dynamic changes in the surrounding environment. This data directly affects the vehicle's safety and decision-making capabilities; therefore, evaluating the data generated by driving perception is crucial. Through evaluation, the accuracy, real-time performance, and stability of vehicle perception can be quantified, potential perception errors and delays can be identified, and perception algorithms and sensor configurations can be optimized. This ensures that intelligent driving vehicles possess sufficient environmental adaptability and reaction speed in various complex scenarios, thereby improving driving safety and reliability.

[0003] Existing intelligent driving perception data evaluation technologies typically employ a multi-step comprehensive analysis for detailed evaluation. First, various vehicle sensors (such as cameras, LiDAR, and radar) collect real-time data on the surrounding environment, including the position, speed, and distance of objects, as well as lane markings and obstacle information. Then, a data preprocessing module denoises, synchronizes, and formats the raw data to ensure accuracy and consistency. Next, a feature extraction module extracts key features, such as the vehicle's obstacle recognition accuracy, response time, and environmental adaptability. After feature extraction, the system calculates several key parameters, such as perception error rate, recognition accuracy, and response latency index. Finally, the evaluation module analyzes these parameters to generate perception capability evaluation coefficients and compares them with preset thresholds to determine whether the vehicle's perception capabilities meet requirements. The entire evaluation process not only focuses on sensor accuracy but also assesses the stability and real-time performance of the perception system in various complex driving scenarios, ensuring safe driving in changing environments. Technical issues

[0004] The existing technology has the following shortcomings:

[0005] When driving at high speeds on a wet, slippery bridge surface, the friction between the vehicle's tires and the road surface decreases significantly. The formation of a water film on the road surface further weakens tire grip. In this situation, the system needs to adjust its braking strategy in real time to ensure safety. However, due to the high vehicle speed and the significant difference in friction coefficient between the wet, slippery bridge surface and ordinary roads, the system sensors cannot detect changes in tire grip in a timely manner, resulting in a perception lag. This lag makes it difficult for the system to quantify the impact of the wet surface on tire grip in real time, leading to insufficient braking response and difficulty in accurately controlling braking distance. Ultimately, misjudging grip by the system may cause the vehicle to skid due to insufficient friction, increasing the risk of accidents or loss of vehicle control. Especially at high speeds, inaccurate grip assessment significantly increases the likelihood of accidents.

[0006] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Technical solutions

[0007] The purpose of this invention is to provide an intelligent driving perception data evaluation system to solve the problems mentioned in the background art.

[0008] To achieve the above objectives, the present invention provides the following technical solution: an intelligent driving perception data evaluation system, including a real-time monitoring module for slippery bridge surfaces, a processing module for perception information of slippery bridge surfaces, a grip evaluation model construction module, a dynamic braking strategy adjustment module, and a feedback optimization and model update module;

[0009] The wet and slippery bridge surface real-time monitoring module monitors the wet and slippery conditions of the bridge surface and the vehicle speed in real time through a sensor network when driving at high speed on a wet and slippery bridge surface. Based on the needs of changes in the friction of the wet and slippery bridge surface, it establishes a real-time monitoring framework for assessing the grip and braking response of the wet and slippery bridge surface.

[0010] The wet and slippery bridge surface perception information processing module acquires real-time wet and slippery bridge surface perception information when vehicles are traveling at high speed on the wet and slippery bridge surface, and analyzes the acquired information to generate the wet and slippery bridge surface friction coefficient and grip response hysteresis index, respectively.

[0011] The grip assessment model construction module constructs a grip assessment model based on the generated wet and slippery bridge surface friction coefficient and grip response hysteresis index, generates grip assessment coefficients, analyzes them after generation, and analyzes the current grip condition of the vehicle based on the generated grip assessment coefficients, classifying them into sufficient grip, critical grip, and insufficient grip.

[0012] The dynamic braking strategy adjustment module dynamically adjusts the braking strategy based on the analysis results of the grip evaluation coefficient for different grip conditions.

[0013] The feedback optimization and model update module continuously monitors the grip condition and braking response of wet and slippery bridge surfaces, adjusts the grip assessment model and braking strategy in real time, and optimizes braking control in wet and slippery environments through feedback data.

[0014] Preferably, the wet bridge surface perception information processing module is used to acquire real-time wet bridge surface perception information when vehicles are traveling at high speed on a wet bridge surface, and analyze the acquired information to generate the wet bridge surface friction coefficient and grip response hysteresis index, respectively. The specific analysis logic is as follows:

[0015] Real-time acquisition of wet bridge surface perception information when vehicles travel at high speed on a wet bridge surface, and preprocessing after acquisition;

[0016] Extract the wet and slippery bridge surface friction force information and grip response hysteresis information from the preprocessed wet and slippery bridge surface perception information;

[0017] The extracted information on the friction force and grip response hysteresis of the wet and slippery bridge surface were analyzed to generate the friction coefficient and grip response hysteresis index of the wet and slippery bridge surface, respectively.

[0018] Preferably, the logic for obtaining the friction coefficient of the wet and slippery bridge surface is as follows:

[0019] Extract the wet bridge surface friction information from the preprocessed wet bridge surface perception information. Specifically, this includes the average thickness of the water film in the contact area between the vehicle tires and the bridge surface at different times over a period of time when the vehicle is traveling at high speed on the wet bridge surface, the actual speed of the vehicle, and the slip ratio of the vehicle tires, and denoted as HW respectively. m V m and S m HW m V represents the average thickness of the water film in the contact area between the vehicle's tires and the bridge surface at time m over a period of time when the vehicle is traveling at high speed on a wet bridge surface. m S represents the actual speed of a vehicle at time m over a period of time when the vehicle is traveling at high speed on a wet bridge surface. m Let g represent the tire slip ratio of a vehicle at time m during a certain period of time when the vehicle is traveling at high speed on a wet bridge surface, where m = 1, 2, 3, ..., g, and g is a positive integer;

[0020] Empirical coefficients were obtained to correct the influence of the average thickness of the water film in the contact area between the vehicle tire and the bridge surface, the actual speed of the vehicle, and the slip ratio of the vehicle tire on the friction force, and were calibrated as α, β, and γ, respectively.

[0021] The specific formula for calculating the coefficient of friction on a wet and slippery bridge surface is as follows:

[0022]

[0023] In the formula, GFWBS is the friction coefficient of the wet and slippery bridge surface.

[0024] Preferably, the logic for obtaining the grip response hysteresis index is as follows:

[0025] The grip response hysteresis information is extracted from the preprocessed wet and slippery bridge surface perception information. Specifically, this includes the delay required for the vehicle's onboard sensors to transmit real-time collected information to the central processing unit at different times over a period of time when the vehicle is traveling at high speed on the wet and slippery bridge surface; the time taken for the central control unit to analyze the wet and slippery bridge surface perception information and generate the friction coefficient; the time required from the central control unit issuing a braking command to the actual execution of the braking system; the vehicle's average speed; and the vehicle's total weight, calibrated as ∆TS. n ∆TP n ∆TB n VP and ZG, ∆TS n ∆TP represents the delay required for the vehicle's sensors to transmit real-time data collected at time n to the central processing unit when the vehicle is traveling at high speed on a slippery bridge surface. n ∆TB represents the time taken by the central control unit at time n within a certain period when a vehicle is traveling at high speed on a slippery bridge surface to analyze the perceived information of the slippery bridge surface and generate the friction coefficient. n Let n represent the time required from when the central control unit issues a braking command to when the braking system actually executes it during a period of time when the vehicle is traveling at high speed on a wet and slippery bridge surface. Let VP represent the average speed of the vehicle when traveling at high speed on a wet and slippery bridge surface, and ZG represent the total weight of the vehicle when traveling at high speed on a wet and slippery bridge surface. n = 1, 2, 3, ..., k, where k is a positive integer.

[0026] Obtain correction coefficients for the effects of the vehicle's total weight and average speed on the lag time, and calibrate them as δ after obtaining them;

[0027] The specific formula for calculating the grip response hysteresis index is as follows:

[0028]

[0029] In the formula, GRLI is the grip hysteresis index.

[0030] Preferably, a grip evaluation model is constructed based on the generated wet and slippery bridge surface friction coefficient and grip response hysteresis index to generate grip evaluation coefficients. This specifically includes the following steps:

[0031] Collect several wet and slippery bridge surface friction coefficients, grip response hysteresis indices, and corresponding grip evaluation coefficients generated over a period of time, and label them as CFWBSx, GRLIx, and GECx, respectively. x represents the number of several wet and slippery bridge surface friction coefficients, grip response hysteresis indices, and corresponding grip evaluation coefficients generated over a period of time, x = 3, 4, 5, ..., d, where d is a positive integer. The collected data over a period of time will be formed into a historical dataset.

[0032] A multiple regression model was chosen as the grip assessment model, and it was trained using historical datasets to determine the values ​​of the regression coefficients, based on the formula:

[0033]

[0034] In the formula, β0, β1, and β2 are regression coefficients;

[0035] By minimizing the error between the predicted and actual values, the regression coefficients are optimized, and the values ​​of the regression coefficients β0, β1, and β2 are finally determined.

[0036] Using the final determined regression coefficients, the grip assessment model is input with the real-time generated wet and slippery bridge surface friction coefficient CFWBS and grip response hysteresis index GRLI to generate the grip assessment coefficient GEC in real time.

[0037] Preferably, the generated grip evaluation coefficient GEC is compared with the pre-set grip evaluation coefficient threshold range GEC. min GEC max A comparison was conducted, and the current grip status of the vehicles was analyzed based on the comparison results, classifying them into three categories: sufficient grip, critical grip, and insufficient grip. The specific comparison analysis and classification are as follows:

[0038] If GEC < GEC min The vehicle's current grip condition is insufficient.

[0039] If GEC min ≤ GEC ≤ GEC max The vehicle's current grip condition is at the critical grip level;

[0040] If GEC > GEC max The vehicle's current grip is sufficient.

[0041] Preferably, in the dynamic braking strategy adjustment module, based on the analysis results of the grip evaluation coefficient, the braking strategy is dynamically adjusted for different grip conditions, specifically as follows:

[0042] If the grip condition is insufficient, the dynamic adjustment braking strategy is to immediately take emergency braking measures and at the same time issue an emergency warning to the driver to indicate that the current grip condition is insufficient.

[0043] When the grip condition is critical, the dynamic adjustment braking strategy is to adopt a preventive braking strategy, while reminding the driver that the current grip condition is critical and advising them to drive cautiously.

[0044] If the grip condition is sufficient, the dynamic braking strategy adopted is: no braking strategy is required, and the vehicle continues to drive in its current state. Beneficial effects

[0045] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0046] 1. The technical solution of this invention demonstrates extremely high technical effectiveness, particularly in addressing the problems of decreased grip and delayed braking response on slippery bridge surfaces, exhibiting significant advantages. Firstly, by monitoring the friction conditions of the slippery bridge surface and the vehicle's operating status in real time, the system can accurately capture changes in the friction between the tires and the road surface. Utilizing dynamic data from a sensor network, combined with calculations of the friction coefficient of the slippery bridge surface and the grip response lag index, the system achieves accurate assessment of grip at different points in time. This dynamic monitoring significantly improves the real-time perception capability of grip changes, avoiding misjudgments of grip caused by perception lag in traditional technologies.

[0047] 2. This invention establishes a grip assessment model. The system dynamically adjusts the grip assessment coefficient based on different road surface conditions and vehicle speeds, and performs real-time analysis. The application of this multiple regression model enables the system to flexibly respond to grip changes under different environmental and driving conditions, ensuring accurate differentiation of sufficient, critical, or insufficient grip when vehicles are driving on slippery bridge surfaces. Compared to traditional fixed assessment models, this technology can more adaptively handle combinations of different bridge surface slipperiness and vehicle speeds, greatly improving the accuracy of grip assessment.

[0048] 3. The greatest advantage of this invention lies in its dynamic braking strategy adjustment and feedback optimization module. The system can not only make timely adjustments based on the current grip condition, such as taking emergency braking, deceleration, or alerting the driver, but also continuously optimize the braking strategy through a feedback mechanism. By collecting past braking data, the system can optimize the grip assessment model and adjust the strategy, improving the accuracy of the braking response. This adaptive feedback mechanism ensures the long-term stability and continuous optimization capability of the system, enabling the vehicle to maintain optimal grip and braking control when driving on slippery bridge surfaces, significantly reducing the risk of skidding and loss of control, and improving driving safety. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0050] Figure 1 is a schematic diagram of the modules of the intelligent driving perception data evaluation system of the present invention. The best embodiment of the present invention

[0051] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0052] This invention provides an intelligent driving perception data evaluation system as shown in Figure 1, including a wet and slippery bridge surface real-time monitoring module, a wet and slippery bridge surface perception information processing module, a grip force evaluation model construction module, a dynamic braking strategy adjustment module, and a feedback optimization and model update module.

[0053] The wet and slippery bridge surface real-time monitoring module monitors the wet and slippery conditions of the bridge surface and the vehicle speed in real time through a sensor network when driving at high speed on a wet and slippery bridge surface. Based on the needs of changes in the friction of the wet and slippery bridge surface, it establishes a real-time monitoring framework for assessing the grip and braking response of the wet and slippery bridge surface.

[0054] When driving at high speeds on a wet and slippery bridge surface, the system can monitor the bridge's slipperiness in real time using sensors installed on the vehicle chassis and the bridge surface. Specifically, humidity and temperature sensors measure the thickness of the water film and temperature changes on the bridge surface, while barometric pressure sensors detect humidity and rainfall to determine if the bridge surface is slippery. Simultaneously, vehicle speed is acquired in real time via a speed sensor. This data is integrated into the vehicle's central control system and transmitted to the central processing unit via a data communication protocol. Through a sensor network, the system can collect and synchronize this information at a high frequency, laying the foundation for subsequent grip assessment. The data undergoes preliminary cleaning and filtering by an onboard processing system to ensure the real-time nature and accuracy of the monitoring information.

[0055] To address the safety hazards posed by varying grip on slippery bridge surfaces, the system dynamically assesses the required friction changes by analyzing sensor data on bridge surface slippage and vehicle speed. Specifically, it converts the degree of slippage into a friction variation coefficient using a physical friction model. This coefficient is then used to calculate the actual friction between the tires and the road surface based on the slippery surface data. The system combines the friction variation data with vehicle speed data to generate a grip status using a real-time grip assessment algorithm. Based on this assessment, the system establishes a braking response framework, classifying different grip scenarios (e.g., sufficient, critical, insufficient), and triggering corresponding braking strategies according to different grip states. The entire process is executed through software algorithms, requiring no additional hardware, achieving automated adjustment and real-time response.

[0056] The "Real-time Monitoring Module for Wet and Slippery Bridge Surfaces" addresses the issue of systems failing to promptly detect changes in grip when driving at high speeds on wet and slippery bridge surfaces. On wet and slippery bridges, factors such as water film cause a sharp decrease in friction between the tires and the road surface, resulting in rapid and complex changes in grip. Conventional systems struggle to assess these changes accurately and promptly, leading to delayed braking response and increased accident risk. Therefore, by using a sensor network to monitor the bridge surface's slipperiness and vehicle speed in real time, the system can accurately perceive the current environment, dynamically generate friction change requirements, and establish a real-time grip assessment and braking response framework. Through this software implementation, the system can continuously monitor wet and slippery road conditions and adjust the vehicle's braking strategy according to environmental changes, avoiding braking lag caused by grip changes and thus improving driving safety on wet and slippery bridge surfaces. This mechanism ensures that vehicles can respond promptly to insufficient grip at high speeds, reducing the risk of loss of control and meeting the safety requirements of intelligent driving.

[0057] The wet and slippery bridge surface perception information processing module acquires real-time wet and slippery bridge surface perception information when vehicles are traveling at high speed on the wet and slippery bridge surface, and analyzes the acquired information to generate the wet and slippery bridge surface friction coefficient and grip response hysteresis index, respectively.

[0058] In this embodiment, the wet bridge surface perception information processing module is used to acquire real-time wet bridge surface perception information when a vehicle is traveling at high speed on a wet bridge surface, and analyze the acquired information to generate the wet bridge surface friction coefficient and grip response hysteresis index, respectively. The specific analysis logic is as follows:

[0059] Real-time acquisition of wet bridge surface perception information when vehicles travel at high speed on a wet bridge surface, and preprocessing after acquisition;

[0060] Real-time acquisition of information about slippery bridge surfaces during high-speed vehicle travel is typically achieved through onboard sensor networks and remote data communication. Specifically, this involves using humidity sensors, temperature sensors, and road surface condition sensors to collect real-time data on the bridge surface's slipperiness (such as water film thickness and temperature), while simultaneously using vehicle speed sensors and tire slippage sensors to obtain vehicle speed and tire grip information. All this sensor data is transmitted to a central processing unit via an onboard network (such as a CAN bus), where it is aggregated and synchronized. Furthermore, the system can interact with external infrastructure via wireless communication technologies (such as 5G or V2X vehicle-to-everything communication) to obtain more detailed road condition information, ensuring accurate grip data in slippery bridge conditions. The core of real-time data transmission is minimizing data latency, enabling vehicles to react quickly to slippery conditions.

[0061] The main purpose of preprocessing is to ensure that the acquired information about the slippery bridge surface is clean, accurate, and suitable for subsequent grip analysis and calculation. Firstly, since sensors may be affected by noise, external interference, or data acquisition errors in complex environments, preprocessing steps typically include noise filtering (such as Kalman filtering algorithms to smooth signals and reduce sensor noise), data format standardization (converting data from different sources to the same data format and units), and missing data imputation (filling in missing data using historical data or extrapolation methods). Specifically, preprocessing is implemented through software algorithms that process the input data stream in real time, eliminating abnormal data and performing consistency correction on data from multiple sources to ensure that the perceived information input to the system accurately reflects the current slippery bridge surface condition and vehicle grip. This process is executed by an automated data processing module in the background, ensuring high-quality analytical data is provided even with high-frequency sensor data input.

[0062] Extract the wet and slippery bridge surface friction force information and grip response hysteresis information from the preprocessed wet and slippery bridge surface perception information;

[0063] Extracting frictional force and grip hysteresis information from preprocessed wet and slippery bridge surface sensing data can be achieved through feature extraction algorithms and data classification methods. First, in the preprocessed sensing data, the system automatically identifies key variables related to friction, such as water film thickness, road surface roughness, tire slip ratio, and vehicle speed, based on the data source and predefined data type labels, using feature selection algorithms (such as PCA principal component analysis or feature engineering). These variables are included as part of the wet and slippery bridge surface frictional force information. Then, the system extracts grip hysteresis information by analyzing data related to system reaction time, such as sensor delay, data processing time, and vehicle speed. The entire extraction process is implemented through logical judgments and feature clustering algorithms in the data flow pipeline, decomposing the raw data into different feature datasets, each used for calculating frictional force and hysteresis response. In this way, the system can accurately extract the required frictional force and grip hysteresis information according to specific rules, providing accurate basic data for subsequent calculations.

[0064] The extracted information on the friction force and grip response hysteresis of the wet and slippery bridge surface were analyzed to generate the friction coefficient and grip response hysteresis index of the wet and slippery bridge surface, respectively.

[0065] In this embodiment, the logic for obtaining the friction coefficient of the wet and slippery bridge surface is as follows:

[0066] Extract the wet bridge surface friction information from the preprocessed wet bridge surface perception information. Specifically, this includes the average thickness of the water film in the contact area between the vehicle tires and the bridge surface at different times over a period of time when the vehicle is traveling at high speed on the wet bridge surface, the actual speed of the vehicle, and the slip ratio of the vehicle tires, and denoted as HW respectively. m V m and S m HW m V represents the average thickness of the water film in the contact area between the vehicle's tires and the bridge surface at time m over a period of time when the vehicle is traveling at high speed on a wet bridge surface. m S represents the actual speed of a vehicle at time m over a period of time when the vehicle is traveling at high speed on a wet bridge surface. m Let g represent the tire slip ratio of a vehicle at time m during a certain period of time when the vehicle is traveling at high speed on a wet bridge surface, where m = 1, 2, 3, ..., g, and g is a positive integer;

[0067] In the extraction of friction information from wet and slippery bridge surfaces, several key quantitative data types can be acquired in real time through sensor networks and onboard systems, and then analyzed through software processing. First, the average thickness of the water film is acquired in real time by humidity sensors, rain sensors, and road surface detection devices installed under the vehicle chassis. These sensors detect the thickness of the water film on the bridge surface during vehicle movement and transmit the data to the central control system for aggregation and averaging. Second, the actual vehicle speed is acquired in real time by vehicle speed sensors (such as onboard GPS or wheel speed sensors). These sensors continuously record the vehicle's speed information during driving and update and transmit it in real time through the vehicle's control system. Finally, the tire slip ratio is acquired in real time by slip sensors or wheel speed difference sensors installed on the tires. The slip ratio reflects the difference between tire slippage and vehicle speed, helping to determine whether tire slippage has occurred. All this data is transmitted synchronously through an onboard network (such as a CAN bus) and cleaned and processed by the software's real-time data processing module to ensure that the final friction information used for calculation is accurate and timely.

[0068] Empirical coefficients were obtained to correct the influence of the average thickness of the water film in the contact area between the vehicle tire and the bridge surface, the actual speed of the vehicle, and the slip ratio of the vehicle tire on the friction force, and were calibrated as α, β, and γ, respectively.

[0069] Empirical coefficients for correcting the effects of average water film thickness, actual vehicle speed, and tire slip ratio on friction in the contact area between vehicle tires and bridge surfaces are typically determined in advance using experimental data and historical scenario simulations. These coefficients are not required for real-time dynamic acquisition during actual system operation. However, during system operation, software systems can automatically adjust calculations based on these pre-defined empirical coefficients. Specifically, the α empirical coefficient corrects for the effect of water film thickness on friction; a thicker water film results in lower friction. This coefficient is pre-defined based on extensive experimental data regarding the friction-reducing effect of the water film. The β empirical coefficient corrects for the effect of vehicle speed on friction; higher speeds result in greater friction reduction due to hydroplaning. The γ empirical coefficient corrects for the effect of slip ratio on friction; a higher slip ratio indicates more severe tire slippage and lower friction. The purpose of obtaining these empirical coefficients is to correct the key variables affecting friction so that the friction model can accurately reflect the actual grip of the vehicle under various conditions. This ensures that the system can adjust the calculation results in real time according to the current water film thickness, vehicle speed and slip ratio, thereby providing a more accurate friction estimate and improving driving safety.

[0070] The specific formula for calculating the coefficient of friction on a wet and slippery bridge surface is as follows:

[0071]

[0072] In the formula, CFWBS is the coefficient of friction of the wet and slippery bridge surface.

[0073] The formula for calculating the coefficient of friction (CFWBS) of a wet and slippery bridge surface combines multiple key factors to calculate the actual friction force under wet and slippery conditions using a weighted average method. First, each term in the formula represents the coefficient of friction of the wet and slippery bridge surface at a different time point. By accumulating the friction force at all times (m = 1 to g), the average value is taken (divided by g), thus reflecting the dynamic change of friction force under wet and slippery conditions over a period of time. Specifically, each part of the formula has a specific physical meaning: Used to correct water film thickness (HW) m The thicker the water film, the lower the friction. Used to correct vehicle speed V m Regarding the impact on friction, the faster the vehicle speed, the more severe the hydroplaning phenomenon and the more significant the decrease in friction; finally, Used to correct tire slip ratio (S) m The influence of factors on friction is considered; a higher slip ratio results in lower friction. Multiplying these factors and averaging them over time ensures the system dynamically reflects changes in friction at different points in time, ultimately generating a comprehensive friction coefficient for wet, slippery bridge surfaces. This calculation method effectively captures changes in environmental and vehicle conditions, ensuring the accuracy of friction estimation and thus helping the system better assess grip and adjust braking strategies.

[0074] The relationship between the coefficient of friction (CFWBS) on wet bridge surfaces and the analysis of a vehicle's current grip is that the coefficient of friction is a core parameter reflecting the strength of grip between the tires and the bridge surface. A higher coefficient of friction on wet bridge surfaces means stronger friction between the tires and the road surface, sufficient vehicle grip, and safe driving. Conversely, a lower coefficient of friction indicates weaker friction between the tires and the bridge surface, insufficient vehicle grip, and a higher risk of skidding or loss of control. By analyzing the coefficient of friction on wet bridge surfaces, the system can assess the vehicle's current grip in real time and dynamically adjust the braking strategy based on the assessment results, ensuring safe driving in wet conditions. Therefore, the coefficient of friction directly determines the adequacy of the vehicle's current grip and is a crucial basis for the intelligent driving system's decision-making.

[0075] In this embodiment, the logic for obtaining the grip response hysteresis index is as follows:

[0076] The grip response hysteresis information is extracted from the preprocessed wet and slippery bridge surface perception information. Specifically, this includes the delay required for the vehicle's onboard sensors to transmit real-time collected information to the central processing unit at different times over a period of time when the vehicle is traveling at high speed on the wet and slippery bridge surface; the time taken for the central control unit to analyze the wet and slippery bridge surface perception information and generate the friction coefficient; the time required from the central control unit issuing a braking command to the actual execution of the braking system; the vehicle's average speed; and the vehicle's total weight, calibrated as ∆TS. n ∆TP n ∆TB n VP and ZG, ∆TS n ∆TP represents the delay required for the vehicle's sensors to transmit real-time data collected at time n to the central processing unit when the vehicle is traveling at high speed on a slippery bridge surface. n ∆TB represents the time taken by the central control unit at time n within a certain period when a vehicle is traveling at high speed on a slippery bridge surface to analyze the perceived information of the slippery bridge surface and generate the friction coefficient. n Let n represent the time required from when the central control unit issues a braking command to when the braking system actually executes it during a period of time when the vehicle is traveling at high speed on a wet and slippery bridge surface. Let VP represent the average speed of the vehicle when traveling at high speed on a wet and slippery bridge surface, and ZG represent the total weight of the vehicle when traveling at high speed on a wet and slippery bridge surface. n = 1, 2, 3, ..., k, where k is a positive integer.

[0077] When extracting grip response lag information from the perceived information of slippery bridge surfaces, several key quantitative data can be acquired in real time through the vehicle-mounted sensor network and the central processing system, and processed by the software system. First, the sensor data transmission delay time (the delay required for the vehicle's sensors to transmit real-time collected information to the central processing unit) can be monitored in real time through the data transmission link delay between the vehicle-mounted sensors and the central control unit. When the vehicle's sensors collect information about the slippery bridge surface, they transmit the data to the central control system via the vehicle bus (such as the CAN bus) or a wireless communication network. The software estimates the delay time by measuring the round-trip time of this data transmission. Second, the central control unit's data processing time (the time spent by the central control unit to analyze the perceived information of the slippery bridge surface and generate the friction coefficient) can be calculated in real time through the software's internal timing mechanism. The processing time for the system to analyze the friction coefficient and other parameters after receiving sensor data is determined by the processor performance and task complexity of the control unit. The software can obtain the data processing time by recording timestamps at the start and end of the analysis. Braking system response time (the time required from the central control unit issuing a braking command to the actual execution of the braking system) is obtained by measuring the time difference between the central control system sending the braking command and the braking system's execution. The system can monitor the execution status of the braking command in real time through an internal feedback mechanism. The vehicle's average speed is acquired in real time by vehicle speed sensors (such as wheel speed sensors or GPS), and a relatively stable speed value is calculated based on the vehicle's average speed during driving. The vehicle's total weight is usually a preset value, input from the vehicle's factory data or a load monitoring system at system startup, and used as a constant. All this data is automatically collected and processed by software, providing accurate input for calculating the grip response lag index, thereby evaluating the system's response speed and lag time.

[0078] Obtain correction coefficients for the effects of the vehicle's total weight and average speed on the lag time, and calibrate them as δ after obtaining them;

[0079] Correction coefficients used to adjust for the impact of vehicle weight and average speed on lag time are typically determined in advance through historical experimental data or simulation analysis and preset as constants in the software system, rather than being dynamically acquired in real time. However, during system operation, the software automatically applies these empirical coefficients to correct for lag time based on the vehicle's total weight and average speed. Specifically, the correction coefficient for total vehicle weight reflects the impact of vehicle load on system response lag; the heavier the vehicle, the greater its inertia, and the longer the lag time may be. Therefore, this coefficient adjusts the impact of weight on response time. The correction coefficient for average vehicle speed corrects for the impact of speed on lag time; the faster the speed, the longer the vehicle's reaction time during braking, because grip decreases at high speeds, increasing braking time. The purpose of obtaining these empirical coefficients is to ensure that the system can automatically adjust the lag time calculation based on different vehicle weights and speeds, thereby more accurately reflecting the actual system response and ensuring the effectiveness and safety of braking operations. Through the automatic correction mechanism in the software, these coefficients can be dynamically applied to the calculation of the lag index to ensure accurate lag time assessment under various operating conditions.

[0080] The specific formula for calculating the grip response hysteresis index is as follows:

[0081]

[0082] In the formula, GRLI is the grip hysteresis index.

[0083] The formula for the Grip Response Lag Index (GRLI) combines multiple variables to accurately assess the braking response lag of a vehicle traveling at high speeds on a slippery bridge surface. First, in the formula, ∆TSn, ∆TPn, and ∆TBn represent sensor data delay, data processing time, and braking system response time at different time points, respectively. The sum of these three values ​​reflects the total response lag of the system at each moment. By accumulating n = 1 to k time points and averaging (dividing by k), the average lag value over a period of time can be obtained. Second, the vehicle's average speed VP and total vehicle weight ZG affect the vehicle's inertia and braking effect on the slippery bridge surface, respectively. Therefore, the formula uses an empirical correction coefficient δ to combine the vehicle's weight and speed to correct for the lag time. Higher speeds and heavier loads may increase the system lag time; therefore, VP is adjusted in the denominator. This method is used to correct for the effect of weight on hysteresis. This calculation method ensures that the hysteresis index can reflect the combined effects of different vehicle speeds, loads, and system response times, thus providing a scientific basis for the dynamic adjustment of grip and braking response.

[0084] The relationship between the Grip Response Lag Index (GRLI) and the analysis of a vehicle's current grip condition lies in the fact that GRLI quantifies the time delay from the system's perception of a change in grip to the actual braking action. This directly affects the vehicle's grip performance in slippery conditions. A larger lag index means a longer system response time to changes in grip, lower grip utilization, and the vehicle may not be able to adjust its braking action in time on slippery surfaces, leading to insufficient grip and increasing the risk of skidding or loss of control. By analyzing the GRLI, the system can assess the vehicle's braking effectiveness under current grip conditions and take necessary preventative measures, such as adjusting speed or triggering braking commands earlier, to ensure safe driving in slippery environments. Therefore, GRLI directly affects the effective use of grip and is a key evaluation indicator for ensuring vehicle safety in complex road conditions.

[0085] The grip assessment model construction module constructs a grip assessment model based on the generated wet and slippery bridge surface friction coefficient and grip response hysteresis index, generates grip assessment coefficients, analyzes them after generation, and analyzes the current grip condition of the vehicle based on the generated grip assessment coefficients, classifying them into sufficient grip, critical grip, and insufficient grip.

[0086] In this embodiment, a grip evaluation model is constructed based on the generated wet and slippery bridge surface friction coefficient and grip response hysteresis index, and grip evaluation coefficients are generated. The specific steps include:

[0087] Several coefficients of friction, grip response hysteresis index, and corresponding grip evaluation coefficients for wet and slippery bridge surfaces generated over a period of time were collected and labeled as CFWBS. x GRLI x and GEC x x represents the number of several wet and slippery bridge surface friction coefficients, grip response hysteresis indexes and corresponding grip evaluation coefficients generated in the past period, x = 3, 4, 5, ..., d, where d is a positive integer, and the collected data in the past period are formed into a historical dataset;

[0088] Collecting the friction coefficient, grip response hysteresis index, and corresponding grip evaluation coefficient of wet-slip bridge surfaces generated over a period of time can be achieved through the data recording module of the software system. Specifically, when the system calculates the friction coefficient and grip response hysteresis index in real time, it automatically records the calculation results at each moment to the data storage module. The system stores this data according to timestamps to ensure accurate traceability to specific values ​​within a particular time period. The software can periodically save these values ​​using a database or distributed storage technology, storing the friction coefficient and grip response hysteresis index along with the actually calculated grip evaluation coefficients, ensuring that this data can be retrieved in subsequent analysis and model training. Through this automated data storage and collection method, the system can continuously and reliably accumulate historical data, providing sufficient reference for the training and optimization of the subsequent grip evaluation model.

[0089] The value of x is a positive integer greater than or equal to 3 because there are three variables (the coefficient of friction of the wet and slippery bridge surface, the grip response hysteresis index, and the grip evaluation coefficient), and it is necessary to solve for three regression coefficients β. 0、 β1 and β 2， Therefore, at least three independent equations are needed to accurately calculate these three regression coefficients. Based on this, the value of x must be greater than or equal to 3 to ensure we have enough equations for regression analysis. To further explain, each equation in the regression analysis corresponds to a data point (a combination of the wet / slippery bridge surface friction coefficient, the grip response hysteresis index, and the grip assessment coefficient). The more data points there are, the better the model fits, and the better it can capture the changing trends of grip assessment under different conditions. Therefore, the value of x is greater than or equal to 3, both to meet the mathematical requirements and to ensure sufficient data to improve the accuracy and robustness of the model, ensuring the rationality and robustness of the regression coefficients.

[0090] A multiple regression model was chosen as the grip assessment model, and it was trained using historical datasets to determine the values ​​of the regression coefficients, based on the formula:

[0091]

[0092] In the formula, β0, β1, and β2 are regression coefficients;

[0093] The multiple regression model was chosen as the grip assessment model because grip assessment involves the influence of multiple independent variables (the coefficient of friction of the wet bridge surface and the grip response lag index) on a single dependent variable (the grip assessment coefficient), which is precisely the strength of the multiple regression model. The multiple regression model is a statistical method used to analyze the combined influence of multiple independent variables on the dependent variable. It can train the model using historical data, identify the degree of influence of each variable on the target outcome under different conditions, and adjust the results using regression coefficients. In the formula, β0 is a constant term, representing the baseline value of the grip assessment coefficient when both the coefficient of friction of the wet bridge surface and the grip response lag index are zero; β1 is the regression coefficient of the coefficient of friction of the wet bridge surface, representing its contribution to the grip assessment; and β2 is the regression coefficient of the grip response lag index, representing the negative impact of lag time on the grip assessment. Through the multiple regression model, we can calculate these three regression coefficients, enabling the model to accurately assess the vehicle's current grip condition under different conditions, thereby optimizing driving safety.

[0094] By minimizing the error between the predicted and actual values, the regression coefficients are optimized, and the values ​​of the regression coefficients β0, β1, and β2 are finally determined.

[0095] Optimizing the regression coefficients by minimizing the error between predicted and actual values ​​ensures that the model's predictive accuracy reaches its best level. The goal is to find the most suitable regression coefficient β by training with historical data. 0、 β1 and β 2， This allows the model to more accurately estimate grip assessment coefficients in future predictions. This process is typically achieved through optimization algorithms such as least squares in software. These algorithms iteratively calculate the difference between predicted and actual values ​​and adjust the regression coefficients to minimize the error. Specifically, during model training, the software automatically calculates the grip assessment coefficients for each prediction, compares them with the actual grip values ​​in the historical dataset, calculates the error, and adjusts the regression coefficients using algorithms until the error converges to a minimum. This process is automated by the software's iterative optimization module, ensuring that the trained model can accurately predict vehicle grip conditions.

[0096] Using the final determined regression coefficients, the grip assessment model is input with the real-time generated wet and slippery bridge surface friction coefficient CFWBS and grip response hysteresis index GRLI to generate the grip assessment coefficient GEC in real time.

[0097] In this embodiment, the generated grip evaluation coefficient GEC is compared with the pre-set grip evaluation coefficient threshold range GEC. min GEC maxA comparison was conducted, and the current grip status of the vehicles was analyzed based on the comparison results, classifying them into three categories: sufficient grip, critical grip, and insufficient grip. The specific comparison analysis and classification are as follows:

[0098] If GEC < GEC min The vehicle's current grip condition is insufficient.

[0099] When GEC < GEC min This means the friction between the vehicle and the road surface is too low, resulting in severely insufficient grip. In this situation, the tires cannot effectively maintain sufficient contact with the road surface, potentially leading to skidding or loss of control during braking or steering. Especially in wet, icy, or other adverse road conditions, insufficient grip significantly increases the likelihood of traffic accidents. Once the system detects this situation, it must immediately take emergency measures, such as slowing down, issuing warnings, or automatically executing emergency braking, to minimize the risk of an accident.

[0100] If GEC min ≤ GEC ≤ GEC max The vehicle's current grip condition is at the critical grip level;

[0101] When GEC min ≤ GEC ≤ GEC max This indicates that the vehicle's current grip is at a critical point, meaning that while the grip between the vehicle and the road surface is still acceptable, it is approaching a safe threshold. At this point, although the vehicle can still be controlled, the grip may be insufficient to handle sudden situations (such as emergency braking or sudden turning). The system should issue a warning in this situation, advising the driver to drive cautiously, reduce speed, and avoid sudden driving maneuvers to ensure that vehicle stability does not further deteriorate.

[0102] If GEC > GEC max The vehicle's current grip is sufficient.

[0103] When GEC > GEC max This indicates that the vehicle currently has sufficient grip, the tires maintain good friction with the road surface, and the vehicle can drive stably and safely. At this time, the system assessment considers that the vehicle's braking, acceleration, and steering are all within a controllable range, and driving safety is high. In this state, the vehicle can continue to drive at normal speed, and the system does not need to take special measures; it only needs to routinely monitor the grip status to respond promptly to any potential changes.

[0104] The pre-defined threshold range for grip evaluation coefficients can be determined by analyzing a large amount of historical driving data, experimental data, and simulation data, and then adjusted and optimized through software. Specifically, the system first collects relevant data from grip evaluation results under various environments (such as wet / slippery, dry, icy / snowy conditions), and then performs a correlation analysis between the vehicle's grip evaluation coefficient and actual driving safety. Using statistical analysis tools in the software, such as regression analysis or classification algorithms, the system can identify the critical value ranges for insufficient, critical, and sufficient grip under different conditions. These results are then repeatedly optimized to ensure optimal GEC (Grip Performance). min and GEC max It meets the safety requirements of actual driving. This process, through model training and automatic adjustment, ensures that the set thresholds are applicable to different vehicle models, road conditions, and environments, ultimately generating a scientific and reasonable range of grip evaluation coefficients to ensure that the system can accurately determine the vehicle's grip status.

[0105] The dynamic braking strategy adjustment module dynamically adjusts the braking strategy based on the analysis results of the grip evaluation coefficient for different grip conditions.

[0106] In this embodiment, the dynamic braking strategy adjustment module dynamically adjusts the braking strategy based on the analysis results of the grip evaluation coefficient, specifically for different grip conditions:

[0107] If the grip condition is insufficient, the dynamic adjustment braking strategy is to immediately take emergency braking measures and at the same time issue an emergency warning to the driver to indicate that the current grip condition is insufficient.

[0108] In situations of insufficient traction, the system can detect the vehicle's grip on the road surface in real time through an onboard sensor network (such as tire slip sensors and accelerometers), and activate an emergency braking strategy via the software's emergency braking module. Specifically, once the system calculates that the grip assessment coefficient is below a threshold, the software automatically activates the emergency braking function, triggering the anti-lock braking system (ABS) and the vehicle stability control system (ESC), while simultaneously transmitting braking signals to the braking system for a rapid response. Furthermore, the system will issue an emergency warning to the driver via the in-vehicle display or an audible alarm, indicating insufficient traction and requiring immediate action. The aim is to minimize the risk of vehicle slippage and loss of control in situations of insufficient traction, ensuring the vehicle stops or slows down safely.

[0109] When the grip condition is critical, the dynamic adjustment braking strategy is as follows: adopt a preventive braking strategy, and at the same time remind the driver that the current grip condition is critical, and advise cautious driving and avoid sudden acceleration or steering operations.

[0110] When grip is at a critical level, the system can mitigate risk through a preventative braking control module in the software. Specifically, when the grip assessment coefficient is within the critical range, the system automatically decelerates or limits acceleration to control the vehicle's speed and reduce the risk of skidding. Through a speed control algorithm in the software, the system can monitor vehicle speed in real time and adjust throttle and brake force to ensure the vehicle stays within a safe speed range. Simultaneously, the system alerts the driver via the in-vehicle display that grip is at a critical level, advising the driver to avoid sudden steering or rapid acceleration. This preventative strategy aims to ensure the vehicle remains controllable in potentially dangerous situations and prevent further deterioration of grip.

[0111] If the grip condition is sufficient, the dynamic braking strategy adopted is: no braking strategy is required, and the vehicle continues to drive in its current state.

[0112] When traction is sufficient, the system does not require special braking measures, but continuous monitoring of traction is still necessary. Specifically, the software continuously monitors the friction coefficient and grip response hysteresis index of the slippery bridge surface using onboard sensors, and calculates the grip assessment coefficient in real time. The system maintains real-time data collection and analysis of the vehicle and environment through a background monitoring module to ensure that traction is always adequate. Under these conditions, the vehicle can travel at normal speed, but the system retains real-time monitoring to take immediate action should traction conditions change. This is to ensure that the vehicle remains under safety monitoring even with sufficient traction and can quickly respond to any unexpected changes, ensuring driving safety.

[0113] The feedback optimization and model update module continuously monitors the grip condition and braking response of wet and slippery bridge surfaces, adjusts the grip assessment model and braking strategy in real time, and optimizes braking control in wet and slippery environments through feedback data.

[0114] The software system collects real-time data on grip on wet bridge surfaces and the vehicle's braking response through an onboard sensor network. Grip condition is quantified using the friction coefficient of the wet bridge surface and the grip response hysteresis index. Specifically, the software system periodically acquires data from sensors, updates the vehicle's current grip condition in real time, and monitors the response of each braking action, including braking distance, vehicle slip rate, and deceleration rate. A continuously running data analysis module in the background compares this data with the expected response to ensure that grip and braking response remain within safe ranges. If the system detects that the grip condition is lower than expected or the braking response is unsatisfactory, it immediately triggers a feedback optimization mechanism. This continuous monitoring aims to ensure that the system can quickly respond to changes in grip under complex road conditions, thereby making adjustments in advance and preventing dangerous situations.

[0115] When the system detects a mismatch between the grip assessment model and actual road conditions, the software automatically adjusts the model. This is achieved by comparing the actual braking results with predicted values ​​using feedback data, calculating the error, and automatically adjusting parameters in the model, such as the weights of the friction coefficient and response hysteresis index on slippery bridge surfaces, or correcting certain empirical coefficients. The adjusted model more accurately reflects the current grip condition of the road surface, providing a more suitable braking strategy. For example, when a vehicle is traveling on a slippery bridge surface, if a significant decrease in friction is detected, the system will improve the sensitivity of the braking response through an optimization algorithm. The purpose of this is to ensure that the grip assessment model always maintains a high degree of adaptability to the current environment, ensuring that the braking strategy can automatically optimize according to changes in road conditions, reducing the risk of accidents.

[0116] The software system continuously optimizes its braking control strategy through a feedback mechanism to enhance its intelligent decision-making capabilities. Specifically, the system compares actual data after each braking maneuver (such as braking distance and tire slip ratio) with model predictions, calculates the error, and gradually reduces this error through machine learning or feedback-based control algorithms. For example, if the braking distance is found to be longer than expected, the system automatically adjusts braking intensity, speed limits, or braking trigger conditions, progressively optimizing control parameters. Furthermore, the system can further adjust the overall braking model based on long-term accumulated data, making its grip response more accurate and stable under different road conditions. The purpose of this feedback mechanism is to ensure that the system maintains optimal braking response through continuous self-optimization, especially in high-risk environments such as slippery roads, thereby improving driving safety.

[0117] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0118] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0119] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0120] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0122] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0124] 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. An intelligent driving perception data evaluation system, characterized in that, The system comprises a wet bridge surface real-time monitoring module, a wet bridge surface sensing information processing module, a grip force evaluation model construction module, a dynamic braking strategy adjustment module, and a feedback optimization and model updating module. The wet bridge surface real-time monitoring module monitors the wet bridge surface condition and vehicle speed in real time through a sensor network when the vehicle is running at high speed on the wet bridge surface, and establishes a real-time monitoring framework for wet bridge surface grip force evaluation and braking response according to the demand for wet bridge surface friction force change. The wet bridge surface sensing information processing module obtains wet bridge surface sensing information in real time when the vehicle is running at high speed on the wet bridge surface, and analyzes the information to generate wet bridge surface friction coefficient and grip force response lag index. The grip force evaluation model construction module constructs a grip force evaluation model based on the generated wet bridge surface friction coefficient and grip force response lag index, generates a grip force evaluation coefficient, and analyzes the coefficient to divide the current grip force condition of the vehicle into sufficient grip force, critical grip force, and insufficient grip force. The dynamic braking strategy adjustment module dynamically adjusts the braking strategy according to different grip force conditions based on the analysis result of the grip force evaluation coefficient. The feedback optimization and model updating module continuously monitors the grip force condition and braking response effect of the wet bridge surface, adjusts the grip force evaluation model and braking strategy in real time, and optimizes the braking control in the wet environment through feedback data.

2. The intelligent driving perception data evaluation system of claim 1, wherein, The wet bridge surface sensing information processing module is used to obtain wet bridge surface sensing information in real time when the vehicle is running at high speed on the wet bridge surface, and analyze the information to generate wet bridge surface friction coefficient and grip force response lag index. The wet bridge surface sensing information processing module is used to obtain wet bridge surface sensing information in real time when the vehicle is running at high speed on the wet bridge surface, and analyze the information to generate wet bridge surface friction coefficient and grip force response lag index. The wet bridge surface sensing information processing module is used to obtain wet bridge surface sensing information in real time when the vehicle is running at high speed on the wet bridge surface, and analyze the information to generate wet bridge surface friction coefficient and grip force response lag index. The wet bridge surface friction coefficient is obtained as follows:

3. The intelligent driving perception data evaluation system of claim 2, wherein, The empirical coefficients for correcting the average thickness of the water film in the contact area between the vehicle tire and the bridge surface, the actual speed of the vehicle, and the slip rate of the vehicle tire on the friction force are obtained, and are respectively denoted as α, β, and γ. The wet and slippery bridge friction information in the preprocessed wet and slippery bridge perception information is extracted, specifically including the water film average thickness of the contact area between the vehicle tire and the bridge surface, the actual speed of the vehicle and the slip rate of the vehicle tire at different time points within a period of time when the vehicle is running at high speed on the wet and slippery bridge surface, and is respectively labeled as H m , V m and S m , HW m represents the water film average thickness of the contact area between the vehicle tire and the bridge surface at time m within a period of time when the vehicle is running at high speed on the wet and slippery bridge surface, V m represents the actual speed of the vehicle at time m within a period of time when the vehicle is running at high speed on the wet and slippery bridge surface, S m represents the slip rate of the vehicle tire at time m within a period of time when the vehicle is running at high speed on the wet and slippery bridge surface, m =1, 2, 3, …, g, g is a positive integer; The wet bridge surface friction coefficient is calculated as follows: In the formula, CFWBS is the wet bridge surface friction coefficient. The grip force response lag index is obtained as follows:

4. The intelligent driving perception data evaluation system of claim 3, wherein, The correction coefficient for correcting the total weight of the vehicle and the average speed of the vehicle on the lag time is obtained, and is denoted as δ after being obtained. The grip response hysteresis information is extracted from the preprocessed wet and slippery bridge surface perception information. Specifically, this includes the delay required for the vehicle's onboard sensors to transmit real-time collected information to the central processing unit at different times over a period of time when the vehicle is traveling at high speed on the wet and slippery bridge surface; the time taken for the central control unit to analyze the wet and slippery bridge surface perception information and generate the friction coefficient; the time required from the central control unit issuing a braking command to the actual execution of the braking system; the vehicle's average speed; and the vehicle's total weight, calibrated as ∆TS. n ∆TP n ∆TB n VP and ZG, ∆TS n ∆TP represents the delay required for the vehicle's sensors to transmit real-time data collected at time n to the central processing unit when the vehicle is traveling at high speed on a slippery bridge surface. n ∆TB represents the time taken by the central control unit at time n within a certain period when a vehicle is traveling at high speed on a slippery bridge surface to analyze the perceived information of the slippery bridge surface and generate the friction coefficient. n Let n represent the time required from when the central control unit issues a braking command to when the braking system actually executes it during a period of time when the vehicle is traveling at high speed on a wet and slippery bridge surface. Let VP represent the average speed of the vehicle when traveling at high speed on a wet and slippery bridge surface, and ZG represent the total weight of the vehicle when traveling at high speed on a wet and slippery bridge surface. n = 1, 2, 3, ..., k, where k is a positive integer. The grip force response lag index is calculated as follows: In the formula, GRLI is the grip force response lag index. The grip force evaluation model construction module constructs a grip force evaluation model based on the generated wet bridge surface friction coefficient and grip force response lag index, generates a grip force evaluation coefficient, and analyzes the coefficient to divide the current grip force condition of the vehicle into sufficient grip force, critical grip force, and insufficient grip force.

5. The intelligent driving perception data evaluation system of claim 4, wherein, ​ The wet-slippery bridge surface friction coefficients, the grip response lag indexes, and the corresponding grip evaluation coefficients generated in the past period of time are collected and respectively marked as CFWBS x , GRLI x , and GEC x , x represents the number of the wet-slippery bridge surface friction coefficients, the grip response lag indexes, and the corresponding grip evaluation coefficients generated in the past period of time, x = 3, 4, 5, …, d, d is a positive integer, and the collected data in the past period of time is formed into a historical data set; The multiple regression model is selected as the grip evaluation model, and is trained by the historical data set to determine the values of the regression coefficients according to the formula: In the formula, β0, β1 and β2 are the regression coefficients. The regression coefficients are optimized by minimizing the error between the predicted value and the actual value, and the values of the regression coefficients β0, β1 and β2 are finally determined. The finally determined regression coefficients are used to input the real-time generated wet bridge friction coefficient CFWBS and the grip response lag index GRLI into the constructed grip evaluation model to generate the grip evaluation coefficient GEC in real time.

6. The intelligent driving perception data evaluation system of claim 5, wherein, The generated grip evaluation coefficient GEC is compared with a pre-set grip evaluation coefficient threshold interval [GEC min , GEC max ], and the current grip condition of the vehicle is analyzed according to the comparison result, and is divided into sufficient grip, critical grip and insufficient grip, and the specific comparison analysis and division are as follows: if GEC < GEC min , the current grip condition of the vehicle is insufficient grip; if GEC min ≤ GEC ≤ GEC max , the current grip condition of the vehicle is a critical grip condition; If GEC > GEC max , the current vehicle grip condition is adequate grip.

7. The intelligent driving perception data evaluation system of claim 6, wherein, In the dynamic braking strategy adjustment module, the braking strategy is dynamically adjusted according to different grip conditions based on the analysis result of the grip evaluation coefficient, specifically: For the grip condition of insufficient grip, the dynamic adjustment braking strategy adopted is to immediately take emergency braking measures and issue an emergency alarm to the driver to prompt the current insufficient grip condition; For the grip condition of critical grip, the dynamic adjustment braking strategy adopted is to take a preventive braking strategy and remind the driver that the current grip condition is in a critical state and suggest cautious driving; For the grip condition of sufficient grip, the dynamic adjustment braking strategy adopted is that no braking strategy needs to be taken and the vehicle continues to travel in the current state.

Images