Vehicle safety method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a vehicle risk avoidance method and device, electronic equipment and storage medium. The method determines a scene risk result according to vehicle driving information and environmental detection information of the vehicle; determines a real-time risk score of the vehicle according to accuracy attribute data, safety attribute data, credibility attribute data and the scene risk result of the vehicle; determines a risk level of the vehicle according to the real-time risk score and a risk score threshold, and controls the vehicle to perform a risk avoidance operation corresponding to the risk level. The present application analyzes the risk score under the actual driving scene dimension through the vehicle driving information and the environmental detection information, comprehensively considers four factors of the accuracy attribute, the safety attribute, the credibility attribute and the scene risk score to realize a linkage risk evaluation mechanism, meets the demand of the vehicle risk evaluation for the comprehensive monitoring of multi-dimensional parameters, has better scene adaptability, improves the risk evaluation accuracy, and guarantees the rationality and effectiveness of the risk avoidance decision.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle avoidance method, device, electronic device, and storage medium. Background Technology

[0002] During severe typhoon weather, strong winds and heavy rain affect vehicle safety, increasing the risk of loss of control, rollover, and collisions. Therefore, risk monitoring is crucial. Current technologies rely on monitoring only a single parameter—wind speed or rainfall—for risk assessment, failing to consider the dynamic changes in driving conditions. This results in incomplete and scenario-specific risk assessments, reduced accuracy, and a tendency for untimely or excessive hazard avoidance. For instance, compared to driving on surface roads, bridge surfaces are characterized by sudden crosswinds and turbulent airflow, making it impossible to apply a uniform risk monitoring and avoidance strategy. Summary of the Invention

[0003] This application provides a vehicle risk avoidance method, device, electronic device, and storage medium, which aims to improve upon and address the problems of incomplete risk assessment and insufficient scenario specificity in existing technologies.

[0004] A vehicle hazard avoidance method includes: Based on the vehicle's driving information and environmental monitoring information, the scenario risk result is determined. The scenario risk result is an assessment result used to measure the probability and severity of potential risks to the vehicle under the influence of environmental factors in a specific traffic scenario. Based on the vehicle's accuracy attribute data, safety attribute data, reliability attribute data, and the scenario risk results, a real-time risk score for the vehicle is determined. The accuracy attribute data is an attribute parameter characterizing the accuracy of the data acquisition component in collecting vehicle driving information and environmental detection information. The safety attribute data is an attribute parameter characterizing the redundancy and stability of the data acquisition function after a failure. The reliability attribute data is an attribute parameter characterizing the anti-interference level of the data acquisition component in collecting vehicle driving information and environmental detection information. Based on the real-time risk score and risk score threshold, the risk level of the vehicle is determined, and the vehicle is controlled to perform avoidance operations corresponding to the risk level.

[0005] This embodiment analyzes risk assessment results from vehicle driving information and environmental monitoring information within a real-world driving scenario. It comprehensively considers four factors—accuracy, safety, reliability, and scenario risk—to implement a linked risk assessment mechanism. This ensures that the risk assessment results provide data reliability and risk level support for the vehicle's risk avoidance decision-making module, preventing decision-making errors caused by assessment mistakes. This embodiment meets the need for comprehensive monitoring of multi-dimensional parameters in vehicle risk assessment, exhibits better scenario adaptability, improves the accuracy of risk assessment, and guarantees the rationality and effectiveness of risk avoidance decisions.

[0006] Furthermore, determining the scenario risk result based on the vehicle's driving information and environmental detection information includes: The environmental detection information is compensated based on the vehicle driving information to obtain environmental compensation information; Based on the vehicle driving information and the environmental compensation information, determine the scene indicator values ​​and scene indicator weights; Based on the scenario indicator values ​​and scenario indicator weights, a scenario risk score is determined, and the scenario risk score is determined as the scenario risk result.

[0007] This embodiment utilizes vehicle driving information to compensate for environmental detection information, effectively correcting detection errors and making the obtained environmental compensation information closer to the actual environmental conditions. Simultaneously, the scenario risk score calculated based on scenario indicator values ​​and reasonable scenario indicator weights can more accurately reflect the risk level of the current driving scenario, better adapting to various complex scenarios and providing a more reliable data foundation for subsequent comprehensive risk assessment.

[0008] Furthermore, the vehicle driving information includes real-time vehicle speed and real-time roll angle, and the environmental detection information includes real-time wind speed and real-time rainfall; The step of compensating the environmental detection information based on the vehicle driving information to obtain environmental compensation information includes: The wind speed correction coefficient is determined based on the real-time vehicle speed and real-time roll angle. The real-time corrected wind speed is determined based on the wind speed correction coefficient and the real-time wind speed. Obtain the historical corrected wind speed from the previous moment, and determine the wind speed deviation value based on the real-time corrected wind speed and the historical corrected wind speed; If the wind speed deviation value is less than or equal to the preset wind speed deviation threshold, then environmental compensation information is determined based on the real-time corrected wind speed and the real-time rainfall.

[0009] This embodiment calculates wind speed correction coefficients by introducing vehicle speed and tilt angle, thereby achieving dynamic correction of wind speed. At the same time, it combines the historical wind speed correction deviation value from the previous moment to filter out wind speed values ​​that deviate from the trend, ensuring the accuracy of wind speed data and providing a reliable data foundation for subsequent evaluation.

[0010] Furthermore, the vehicle driving information includes real-time vehicle speed and vehicle position, and the environmental compensation information includes real-time corrected wind speed and real-time rainfall. The step of determining scene indicator values ​​and scene indicator weights based on the vehicle driving information and the environmental compensation information includes: Based on the vehicle's location, determine the target scene and obtain the scene slope and scene weight data table corresponding to the target scene; The scene indicator weights corresponding to each scene indicator value are found in the scene weight data table; the scene indicator values ​​include the real-time corrected wind speed, the real-time rainfall, the real-time vehicle speed, and the scene slope.

[0011] This embodiment obtains a scenario weight data table corresponding to the target scenario. The scenario weight data table pre-assigns reasonable weights to each scenario indicator, thereby more accurately assessing the impact of each scenario indicator on vehicle driving risk and improving the scenario-specificity of vehicle risk assessment.

[0012] Further, determining the real-time risk score of the vehicle based on its accuracy attribute data, safety attribute data, credibility attribute data, and the scenario risk results includes: The accuracy attribute data, security attribute data, credibility attribute data, and scenario risk results are standardized to obtain a standard array, which includes accuracy standard values, security standard values, credibility standard values, and scenario risk standard values. Obtain the risk weight reassembly corresponding to the standard array, and perform weighted summation on the accuracy standard value, safety standard value, credibility standard value and scenario risk standard value according to the risk weight reassembly to obtain the real-time risk score.

[0013] This embodiment obtains a real-time risk score by standardizing and weighting the accuracy, safety, reliability attributes and scenario risk results. Standardization can eliminate differences between data from different sources and highlight the relative relationships between data. The real-time risk score can clearly reflect the quantitative level of driving risk in the current scenario, which is helpful for subsequent risk level analysis.

[0014] Furthermore, the risk scoring threshold includes a first risk scoring threshold and a second risk scoring threshold; The step of determining the risk level of the vehicle based on the real-time risk score and risk score threshold, and controlling the vehicle to perform avoidance operations corresponding to the risk level, includes: When the real-time risk score has not yet reached the first risk score threshold, the risk level is determined to be low risk level, and the vehicle is controlled to perform a warning prompt operation. When the real-time risk score reaches the first risk score threshold but has not yet reached the second risk score threshold, the risk level is determined to be medium risk level, and the vehicle is controlled to perform a deceleration operation based on the first preset deceleration duration, real-time vehicle speed, and safe recommended vehicle speed; the safe recommended vehicle speed is determined based on the environmental detection information. When the real-time risk score reaches the second risk score threshold, the risk level is determined to be high risk level, and the vehicle is controlled to perform a deceleration operation based on the second preset deceleration duration, real-time vehicle speed, and safe recommended vehicle speed; the safe recommended vehicle speed is determined based on the environmental detection information, and the second preset deceleration duration is less than the first preset deceleration duration.

[0015] This embodiment categorizes risk levels based on different scoring results and implements different measures for different risk levels, achieving precise response. At low risk levels, early warning prompts promptly alert drivers to potential risks without interfering with driving. At medium and high risk levels, it calculates recommended safe speeds and applies deceleration with varying reaction times to help drivers better control the vehicle and reduce the likelihood of accidents. Each risk level has clear judgment criteria and procedures, improving the reliability and stability of risk avoidance decisions.

[0016] Furthermore, the environmental monitoring information includes real-time rainfall; The recommended safe speed is determined based on the environmental detection information, including: The road surface friction coefficient is determined based on the real-time rainfall. Based on the vehicle model information, determine the critical lateral wind speed; The wheelbase width and center of gravity height of the vehicle are obtained, and a safe recommended speed is determined based on the wheelbase width, the center of gravity height, the critical lateral wind speed, and the road surface friction coefficient.

[0017] This embodiment calculates a safe recommended vehicle speed by determining the road surface friction coefficient based on real-time rainfall and combining it with the critical crosswind speed determined by vehicle model information. This ensures that the vehicle maintains stable driving under wet and slippery road conditions and crosswinds. It can perceive environmental changes in real time and provide safe speed suggestions for the current driving scenario, improving the pertinence in dealing with complex scenarios and enhancing the rationality and effectiveness of risk avoidance operations.

[0018] A vehicle safety device, comprising: The scenario risk analysis module is used to determine the scenario risk result based on the vehicle's driving information and environmental detection information. The scenario risk result is an assessment result used to measure the probability and severity of potential risks to the vehicle under the influence of environmental factors in a specific traffic scenario. The risk scoring determination module is used to determine the real-time risk score of the vehicle based on the vehicle's accuracy attribute data, safety attribute data, reliability attribute data, and the scenario risk results. The accuracy attribute data is an attribute parameter characterizing the accuracy of the data acquisition component in collecting vehicle driving information and environmental detection information. The safety attribute data is an attribute parameter characterizing the redundancy and stability of the data acquisition function after a failure. The reliability attribute data is an attribute parameter characterizing the anti-interference level of the data acquisition component in collecting vehicle driving information and environmental detection information. The risk avoidance decision module is used to determine the risk level of the vehicle based on the real-time risk score and the risk score threshold, and control the vehicle to perform risk avoidance operations corresponding to the risk level.

[0019] An electronic device includes a processor and a memory, wherein, Memory, used to store computer programs; The processor is used to execute the program stored in the memory to implement the vehicle avoidance method described above.

[0020] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described vehicle avoidance method. Attached Figure Description

[0021] Figure 1 This is a flowchart of a vehicle avoidance method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating step S101 of a vehicle avoidance method provided in an embodiment of this application; Figure 3 This is a flowchart illustrating step S201 of a vehicle avoidance method provided in an embodiment of this application; Figure 4 This is a flowchart illustrating step S202 of a vehicle avoidance method provided in an embodiment of this application; Figure 5 This is a flowchart illustrating step S102 of a vehicle avoidance method provided in an embodiment of this application; Figure 6 This is a flowchart illustrating step S103 of a vehicle avoidance method provided in an embodiment of this application; Figure 7This is a flowchart illustrating step S602 of a vehicle avoidance method provided in an embodiment of this application; Figure 8 This is a structural diagram of the vehicle avoidance device provided in the embodiments of this application; Figure 9 This is a structural diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0022] To make the technical problems, technical solutions, and beneficial effects solved by this application clearer, the following detailed description is provided in conjunction with embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0023] Terminology Explanation In this application, the vehicle avoidance method is applied to the vehicle's Electronic Control Unit (ECU). The ECU communicates with both a data acquisition component and a vehicle avoidance component. The data acquisition component is a terminal used to acquire data in real time, including but not limited to ultrasonic wind speed and direction sensors, piezoelectric rain sensors, inertial measurement units, and positioning sensors. The vehicle avoidance component refers to components that perform specified actions to achieve warning functions or change the vehicle's driving state, including but not limited to the instrument panel, speakers, accelerator, brakes, and steering wheel.

[0024] Specifically, in a typhoon weather driving scenario, the electronic control unit acquires vehicle driving information and environmental detection information, as well as vehicle accuracy attribute data, safety attribute data, and reliability attribute data through data acquisition components. Based on the vehicle driving information and environmental detection information, it determines the scenario risk result, which is an assessment result used to measure the probability and severity of potential risks to the vehicle under the influence of environmental factors in a specific traffic scenario.

[0025] Next, the electronic control unit determines the vehicle's real-time risk score based on the vehicle's accuracy attribute data, safety attribute data, reliability attribute data, and scenario risk results. The accuracy attribute data is an attribute parameter used to characterize the accuracy of the data acquisition component in collecting vehicle driving information and environmental detection information. The safety attribute data is an attribute parameter used to characterize the redundancy performance and stability of the data acquisition function after a failure. The reliability attribute data is an attribute parameter used to characterize the anti-interference level of the data acquisition component in collecting vehicle driving information and environmental detection information.

[0026] Then, the electronic control unit determines the vehicle's risk level based on the real-time risk score and risk score threshold, and controls the vehicle's risk avoidance components to perform risk avoidance operations corresponding to the risk level.

[0027] Vehicle driving information refers to various data parameters used to characterize the vehicle's motion state and performance during driving. Vehicle driving information includes, but is not limited to, real-time vehicle speed, real-time roll angle, and vehicle position. Real-time speed and roll angle can be acquired through an inertial measurement unit integrated into the chassis controller, while vehicle position can be acquired through a positioning sensor. Roll angle is an angular indicator used to measure vehicle stability during cornering. When a vehicle makes a sharp turn, the body tilts due to centrifugal force; the larger the roll angle, the easier it is for the vehicle to lose control. Environmental detection information is information detected by sensors that characterizes the actual characteristics of the surrounding environment during vehicle driving. Environmental detection information includes, but is not limited to, real-time wind speed (in meters per second), real-time wind direction angle (in degrees, based on the vehicle's heading), and real-time rainfall (in millimeters per hour). Specifically, actual wind speed and real-time wind direction angle can be acquired in real-time using ultrasonic wind speed and direction sensors. Continuous frequency conversion ultrasonic signals are used to detect wind speed and direction by measuring the relative phase, overcoming the requirements of high-precision timers and temperature interference. Real-time rainfall can be collected using a piezoelectric rain sensor mounted inside the windshield, with a resolution of 0.1 mm / min. Real-time wind direction angle is the relative angle between the wind direction and the vehicle's driving direction.

[0028] Scenario risk results are assessments used to measure the likelihood and severity of potential risks to a vehicle under the influence of environmental factors in a specific traffic scenario. Environmental compensation information refers to information obtained by correcting the raw environmental parameters detected by sensors using vehicle driving information. Since vehicle sensors may experience detection biases under severe weather conditions such as typhoons, the relationship between vehicle driving information and actual environmental parameters can be used to compensate for environmental detection information, resulting in environmental compensation information. Scenario index values ​​are quantitative descriptions of specific environmental factors in a particular traffic scenario, reflecting the actual condition or level of those factors. Scenario index weights characterize the importance of each index in the scenario risk assessment, reflecting the magnitude of the influence of different indicators on the final scenario risk score. The value range of scenario index weights is between 0 and 1. The scenario risk score is a comprehensive value calculated based on scenario index values ​​and scenario index weights, used to quantitatively characterize the likelihood and severity of potential risks to a vehicle under a specific traffic scenario.

[0029] When a vehicle is driving in a typhoon environment, the actual wind speed affects the vehicle's roll angle. There is a corresponding relationship between the vehicle's speed, roll angle, and actual wind speed. The wind speed correction factor is an adjustment factor used to correct the real-time wind speed collected by sensors. Different real-time vehicle speeds and roll angles correspond to different wind speed correction factors. Specifically, when the real-time vehicle speed is less than 60 km / h and the real-time roll angle is less than 5 degrees, the corresponding wind speed correction factor is 1. When the real-time vehicle speed is greater than or equal to 60 km / h, the corresponding wind speed correction factor increases by 0.15. When the real-time roll angle is greater than or equal to 5 degrees, the corresponding wind speed correction factor increases by 0.08. Real-time corrected wind speed refers to the result of correcting the real-time wind speed collected by the sensors. The sensors collect data at a fixed frequency and send it to the electronic control unit for subsequent processing, such as collecting data once every 0.1 seconds. Historical corrected wind speed refers to the result of correcting the wind speed collected by the sensors at the previous moment. The wind speed deviation value is the difference between the current real-time corrected wind speed and the previous historical corrected wind speed. The preset wind speed deviation threshold is a pre-set critical value used to judge whether the wind speed correction result is reasonable. It can be set to a default value or adjusted as needed. For example, the default value of the preset wind speed deviation threshold is 0.3 meters per second.

[0030] Vehicle accuracy attribute data are attribute parameters used to characterize the accuracy of data acquisition components in collecting vehicle driving information and environmental detection information. Safety attribute data are attribute parameters used to characterize the redundancy performance and stability of the data acquisition function after a failure. Reliability attribute data are attribute parameters used to characterize the anti-interference level of the data acquisition components in collecting vehicle driving information and environmental detection information. Vehicle accuracy attribute data, safety attribute data, and reliability attribute data are fixed attribute values ​​corresponding to a specific vehicle under specific conditions. Their initial values ​​are obtained through real-vehicle testing at the time of vehicle delivery and stored in the vehicle system. The electronic control unit can directly access and retrieve them, and the vehicle can also dynamically adjust them based on actual test results during use.

[0031] Specifically, the vehicle's accuracy attribute data is characterized by the compliance rate of wind speed error, rainfall resolution, and inertial measurement delay in 100 consecutive sets of data collected by the data acquisition component (the original data is a percentage, which needs to be standardized to 0-100 points). For example, if the wind speed measurement error of the ultrasonic anemometer array in the 100 sets of data does not exceed the wind speed compliance threshold (≤±0.5m / s), the resolution of the piezoelectric rain sensor does not exceed the rainfall compliance threshold (≤0.1mm / min), and the inertial measurement delay does not exceed the delay compliance threshold (≤10ms), then the overall compliance rate of the 100 consecutive sets of data is 100%, and the corresponding accuracy attribute data is 100%.

[0032] Vehicle safety attribute data is characterized by the functional redundancy rate after a simulated sensor failure (without redundancy design, the failure of a single sensor will directly lead to data interruption), data anomaly alarm response time, and stability in extreme environments. For example, an ultrasonic wind measurement array includes four ultrasonic probes. When one ultrasonic probe fails, it automatically switches to the remaining three ultrasonic probes for data fusion measurement of wind speed, achieving a functional redundancy rate of 90%. The data anomaly alarm response time is 150ms, which does not exceed the anomaly response time compliance threshold (≤200ms). It operates without failure for 1000 hours in extreme environments (-40℃~85℃) (operation time compliance threshold), achieving a comprehensive compliance rate of 95%, corresponding to a safety attribute data of 95%.

[0033] The reliability attribute data of a vehicle is characterized by the consistency between the detected data and the actual data under environmental interference. For example, when the wind speed consistency of the ultrasonic anemometer array is 92%, the corresponding reliability attribute data is 92 points. Real-time risk scoring is a quantitative value used to characterize the degree of safety risk of a specific vehicle under the influence of its own attribute factors and environmental factors. It can quantitatively assess the probability and severity of potential risks for different vehicles in different scenarios, providing a basis for safety warnings and decision-making control. Risk scoring thresholds are pre-set actual critical values ​​used to determine whether a vehicle's real-time risk score has reached the point where a specific avoidance operation is required. Risk level refers to the level used to distinguish different levels of risk severity and avoidance operation methods. Risk can be divided into two or more levels as needed. Specifically, risk levels are divided into three levels: low risk, medium risk, and high risk. In this case, the risk scoring thresholds include a first risk scoring threshold and a second risk scoring threshold, with the first risk scoring threshold being lower than the second risk scoring threshold. The first risk scoring threshold is the real-time risk scoring judgment standard used to measure whether the vehicle needs to adopt the avoidance operation corresponding to the medium risk level; for example, the default value of the first risk scoring threshold is 60. The second risk scoring threshold is the real-time risk scoring judgment standard used to measure whether the vehicle needs to adopt the avoidance operation corresponding to the high risk level; for example, the default value of the second risk scoring threshold is 80.

[0034] Different risk levels correspond to different avoidance maneuvers. Avoidance maneuvers are methods used to alert the driver or change the vehicle's driving state by performing specific actions through specific vehicle components. For example, warning actions to alert the driver of environmental changes through specific vehicle components include, but are not limited to, text prompts displayed on the central control screen, traffic light prompts, and speaker audible prompts. Another example is methods to directly change the vehicle's driving state by performing specific actions through specific vehicle components, such as actively reducing speed to the safe recommended speed when the vehicle is traveling too fast and is prone to skidding. The safe recommended speed refers to the critical speed at which the vehicle will not roll over in the current traffic scenario. When the real-time speed exceeds the safe recommended speed, a speed reduction maneuver is required (such as reducing the accelerator or increasing brake pressure). The first preset deceleration duration refers to the continuous deceleration period for reducing the vehicle speed to the safe recommended speed at a medium-risk level. The second preset deceleration duration refers to the continuous deceleration period for reducing the vehicle speed to the safe recommended speed at a high-risk level.

[0035] Vehicles traveling on surface roads are less affected by typhoons, while those traveling on bridges are more affected. The electronic control unit (ECU) queries the navigation map based on the vehicle's location to determine the target scenario. The target scenario refers to the road scene where the vehicle is currently located. A road scene is a traffic scenario comprised of the road itself and its surrounding environment within a specific geographical location and distance range. When the target scenario is a bridge / road scene, the ECU retrieves the corresponding scenario slope and scenario weight data tables. Scenario slope refers to the slope value in the road scene where the vehicle is currently located. The scenario weight data table is a pre-established table representing the mapping relationship between different scenario indicator values ​​and their corresponding scenario indicator weights under a specific traffic scenario. In this embodiment, separate scenario weight data tables are pre-established for different bridge / road scenarios, with one scenario weight data table corresponding to one bridge / road scenario. For example, based on historical environmental data and vehicle driving data of the Guangzhou Yaji Sha Bridge, a scenario weight data table corresponding to the Guangzhou Yaji Sha Bridge is constructed, including the mapping relationship between four aspects of indicator values ​​and indicator weights. The four indicators are crosswind level (divided into levels 0-12 based on wind speed data monitored by the bridge's meteorological station), rainfall intensity (divided into light rain, moderate rain, heavy rain, torrential rain, and extremely heavy rain based on rainfall of 0.1-100 mm per hour), vehicle speed (divided into intervals of 10 km / h), and bridge deck slope (divided into several intervals of 0-15 degrees). Each crosswind level, rainfall intensity, vehicle speed, and bridge deck slope is assigned a weight. For example, a level 12 crosswind corresponds to a weight of 0.8, and a torrential rain corresponds to a weight of 0.7. Each indicator value corresponds to an indicator weight, which characterizes the importance of that indicator value in the scenario risk assessment. This allows the electronic control unit to find the weights corresponding to the actual wind speed, rainfall, slope, and vehicle speed from the scenario weight data table when the target scenario is the Guangzhou Yaji Sha Bridge.

[0036] Scene indicator values ​​include real-time corrected wind speed, real-time rainfall, real-time vehicle speed, and scene slope. When the target scene is the Guangzhou Yaji Sha Bridge, the electronic control unit retrieves the wind speed weight corresponding to the real-time corrected wind speed, the rainfall weight corresponding to the real-time rainfall, the vehicle speed weight corresponding to the real-time vehicle speed, and the slope weight corresponding to the real-time slope from the scene weight data table corresponding to the Guangzhou Yaji Sha Bridge. The wind speed weight, rainfall weight, vehicle speed weight, and slope weight constitute the scene indicator weight. The scene indicator values ​​and scene indicator weights are then weighted and summed to obtain the scene risk score.

[0037] Standardization refers to the process of converting data to a uniform scale, and the standard array is the result of this standardization process. The standard array includes accuracy standard values, safety standard values, reliability standard values, and scenario risk standard values. Specifically, the electronic control unit (ECU) performs standardization by converting data into values ​​within the (0,100) range. The accuracy standard value converts accuracy attribute data to values ​​within the (0,100) range, the safety standard value converts safety attribute data to values ​​within the (0,100) range, the reliability standard value converts reliability attribute data to values ​​within the (0,100) range, and the scenario risk standard value converts scenario risk results to values ​​within the (0,100) range. The risk weighting structure corresponding to the standard array is a pre-defined quantitative value used to characterize the importance of accuracy, safety, reliability, and scenario risk factors in real-time risk scoring calculations. The risk weighting structure includes four preset weight values ​​of (0,1), and the sum of all preset weight values ​​equals 1.

[0038] The road surface friction coefficient is the ratio of the frictional force to the vertical pressure generated when a vehicle's tires contact the road surface. It measures the road's anti-skid performance and directly affects vehicle driving safety. Under different rainfall conditions, rainwater forms a water film between the tires and the road surface, reducing the direct contact area, and the road surface friction coefficient decreases due to the lubricating effect of the rainwater. Different real-time rainfall amounts correspond to different road surface friction coefficients. Crosswind speed is the wind speed projected laterally onto the vehicle's direction of travel. The critical crosswind speed is the wind speed threshold at which a lateral wind force can cause a rollover. Vehicle type information is used to classify different types of vehicles, categorized as sedans, SUVs, and MPVs. Based on the vehicle type information, the electronic control unit (ECU) can obtain the critical crosswind speed corresponding to the actual vehicle type. Based on the rollover dynamics critical conditions, the ECU can calculate the recommended safe speed based on wheelbase width, center of gravity height, critical crosswind speed, and road surface friction coefficient. The recommended safe speed is the maximum speed at which a vehicle will not rollover under the influence of crosswind speed.

[0039] This application provides a vehicle hazard avoidance method, which is illustrated using an example of the method being applied to the vehicle's electronic control unit. Please refer to [link / reference]. Figure 1 This includes the following steps: S101: Based on the vehicle's driving information and environmental detection information, determine the scenario risk result, which is an assessment result used to measure the probability and severity of potential risks to the vehicle under the influence of environmental factors in a specific traffic scenario. S102: Based on the vehicle's accuracy attribute data, safety attribute data, reliability attribute data, and the scenario risk results, determine the vehicle's real-time risk score. The accuracy attribute data is an attribute parameter characterizing the accuracy of the data acquisition component in collecting vehicle driving information and environmental detection information. The safety attribute data is an attribute parameter characterizing the data acquisition component's redundancy performance and stability after a failure. The reliability attribute data is an attribute parameter characterizing the data acquisition component's resistance to interference in collecting vehicle driving information and environmental detection information. S103: Based on the real-time risk score and risk score threshold, determine the risk level of the vehicle, and control the vehicle to perform avoidance operations corresponding to the risk level.

[0040] Understandably, the vehicle's electronic control unit (ECU) acquires vehicle driving information and environmental detection information, as well as the vehicle's accuracy attribute data, safety attribute data, and reliability attribute data. Then, based on the vehicle driving information and environmental detection information, the ECU analyzes the scenario risk results. Combining the accuracy attribute data, safety attribute data, reliability attribute data, and scenario risk results, the ECU performs a comprehensive risk assessment to determine the vehicle's real-time risk score. Finally, based on the relationship between the real-time risk score and a risk score threshold, the ECU determines the vehicle's risk level and controls the vehicle to perform avoidance actions corresponding to that risk level.

[0041] This embodiment analyzes risk assessment results from vehicle driving information and environmental monitoring information within a real-world driving scenario. It comprehensively considers four factors—accuracy, safety, reliability, and scenario risk—to implement a linked risk assessment mechanism. This ensures that the risk assessment results provide data reliability and risk level support for the vehicle's risk avoidance decision-making module, preventing decision-making errors caused by assessment mistakes. This embodiment meets the need for comprehensive monitoring of multi-dimensional parameters in vehicle risk assessment, exhibits better scenario adaptability, improves the accuracy of risk assessment, and guarantees the rationality and effectiveness of risk avoidance decisions.

[0042] In one embodiment, please refer to Figure 2 In step S101, which involves determining the scenario risk result based on the vehicle's driving information and environmental detection information, the following steps are included: S201: Compensate the environmental detection information based on the vehicle driving information to obtain environmental compensation information; S202: Determine the scene index value and scene index weight based on the vehicle driving information and the environmental compensation information; S203: Determine the scenario risk score based on the scenario indicator value and scenario indicator weight, and determine the scenario risk score as the scenario risk result.

[0043] Understandably, environmental detection information collected by sensors may deviate from actual environmental parameters, and vehicle driving information can indirectly reflect the impact of actual environmental parameters. Therefore, the electronic control unit (ECU) compensates for the environmental detection information based on vehicle driving information to obtain environmental compensation information. Then, the ECU considers both vehicle driving information and environmental compensation information simultaneously, enabling a comprehensive assessment of scenario risks from multiple dimensions. The impact of each scenario indicator on risk varies across different scenarios. The ECU determines the weights of scenario indicators by combining vehicle driving information and environmental compensation information, dynamically adjusting the importance of each scenario indicator according to actual conditions. The ECU performs a weighted summation calculation based on the scenario indicator values ​​and their weights to obtain a scenario risk score.

[0044] This embodiment utilizes vehicle driving information to compensate for environmental detection information, effectively correcting detection errors and making the obtained environmental compensation information closer to the actual environmental conditions. Simultaneously, the scenario risk score calculated based on scenario indicator values ​​and reasonable scenario indicator weights can more accurately reflect the risk level of the current driving scenario, better adapting to various complex scenarios and providing a more reliable data foundation for subsequent comprehensive risk assessment.

[0045] In one embodiment, the vehicle driving information includes real-time vehicle speed and real-time roll angle, and the environmental detection information includes real-time wind speed and real-time rainfall; please refer to Figure 3 In step S201, namely, compensating the environmental detection information based on the vehicle driving information to obtain environmental compensation information, the following steps are included: S301: Determine the wind speed correction coefficient based on the real-time vehicle speed and real-time roll angle; S302: Determine the real-time corrected wind speed based on the wind speed correction coefficient and the real-time wind speed; S303: Obtain the historical corrected wind speed of the previous moment, and determine the wind speed deviation value based on the real-time corrected wind speed and the historical corrected wind speed; S304: If the wind speed deviation value is less than or equal to the preset wind speed deviation threshold, then environmental compensation information is determined based on the real-time corrected wind speed and the real-time rainfall.

[0046] Understandably, when vehicles are driving in typhoon conditions, their safety is more sensitive to changes in wind speed. Therefore, it is necessary to compensate for the detected real-time wind speed to ensure that the wind speed is closer to the true value. The electronic control unit (ECU) determines a wind speed correction coefficient based on the impact of different wind speeds on vehicle speed and roll angle. Then, the ECU uses the product of the wind speed correction coefficient and the real-time wind speed as the real-time corrected wind speed and calculates the difference between this and the historical corrected wind speed from the previous moment, obtaining the wind speed deviation value. When the wind speed deviation value is less than or equal to a preset wind speed deviation threshold, it indicates that the wind speed correction result is reasonable, and the combination of the real-time corrected wind speed and real-time rainfall is determined as environmental compensation information. When the wind speed deviation value is greater than the preset wind speed deviation threshold, it indicates that the wind speed correction result is unreasonable (the wind speed change is too large, such as sensor instantaneous noise or outliers). In this case, a second correction of the real-time wind speed is required until the corrected wind speed deviation value is less than or equal to the preset wind speed deviation threshold. The combination of the real-time corrected wind speed and real-time rainfall is then determined as environmental compensation information.

[0047] This embodiment calculates wind speed correction coefficients by introducing vehicle speed and tilt angle, thereby achieving dynamic correction of wind speed. At the same time, it combines the historical wind speed correction deviation value from the previous moment to filter out wind speed values ​​that deviate from the trend, ensuring the accuracy of wind speed data and providing a reliable data foundation for subsequent evaluation.

[0048] In one embodiment, the vehicle driving information includes real-time vehicle speed and vehicle position, and the environmental compensation information includes real-time corrected wind speed and real-time rainfall; please refer to Figure 4 In step S202, namely, determining the scene index value and scene index weight based on the vehicle driving information and the environmental compensation information, the following steps are included: S401: Based on the vehicle's location, determine the target scene and obtain a scene slope and scene weight data table corresponding to the target scene; S402: Find the scene indicator weights corresponding to each scene indicator value from the scene weight data table; the scene indicator values ​​include the real-time corrected wind speed, the real-time rainfall, the real-time vehicle speed, and the scene slope.

[0049] Understandably, the impact of factors such as wind speed, rainfall, vehicle speed, and slope on vehicle driving risk varies significantly across different scenarios. The electronic control unit (ECU) can determine the target scenario based on the vehicle's current location and obtain the corresponding scenario weight data table, retrieving the weights of different factors from the table. Scenario index values ​​include real-time corrected wind speed, real-time rainfall, real-time vehicle speed, and scenario slope. Scenario index weights include the wind speed weight corresponding to the real-time corrected wind speed, the rainfall weight corresponding to the real-time rainfall, the vehicle speed weight corresponding to the real-time vehicle speed, and the slope weight corresponding to the real-time scenario slope.

[0050] This embodiment obtains a scenario weight data table corresponding to the target scenario. The scenario weight data table pre-assigns reasonable weights to each scenario indicator, thereby more accurately assessing the impact of each scenario indicator on vehicle driving risk and improving the scenario-specificity of vehicle risk assessment.

[0051] In one embodiment, please refer to Figure 5 In step S102, namely, determining the real-time risk score of the vehicle based on its accuracy attribute data, safety attribute data, credibility attribute data, and the scenario risk result, the following steps are included: S501: Standardize the accuracy attribute data, security attribute data, credibility attribute data and the scenario risk result to obtain a standard array, which includes accuracy standard value, security standard value, credibility standard value and scenario risk standard value; S502: Obtain the risk weight recombination corresponding to the standard array, and perform weighted summation on the accuracy standard value, safety standard value, credibility standard value and scenario risk standard value according to the risk weight recombination to obtain the real-time risk score.

[0052] Understandably, in one specific embodiment, the vehicle's accuracy attribute data is 100%, indicating that the compliance rate for wind speed error, rainfall resolution, and inertial measurement delay is 100%. The safety attribute data is 95%, indicating that the overall compliance rate for functional redundancy, data anomaly alarm response time, and fault-free operation time in extreme environments is 95%. The reliability attribute data is 92 points, indicating that the verification consistency score of the detection data is 92 points. The scenario risk result is 45.9 points, indicating that the risk assessment score of the vehicle under the influence of environmental factors in the current scenario is 45.9 points. The electronic control unit standardizes the accuracy attribute data, safety attribute data, reliability attribute data, and scenario risk result to obtain a standard array. The standard array includes a standard value for accuracy (represented by X1, and X1=100), a standard value for safety (represented by X2, and X2=95), a standard value for reliability (represented by X3, and X3=92), and a standard value for scenario risk (represented by X4, and X4=45.9). The risk weighting calculation includes preset weight values ​​corresponding to the accuracy standard value (denoted by W1, where W1=0.3), the safety standard value (denoted by W2, where W2=0.2), the credibility standard value (denoted by W3, where W3=0.2), and the scenario risk standard value (denoted by W4, where W4=0.3). The electronic control unit performs a weighted calculation on the standard array and the risk weighting calculation to obtain a real-time risk score. The real-time risk score is denoted by S, where S=(X1×W1)+(X2×W2)+(X3×W3)+(X4×W4)=79.17.

[0053] This embodiment obtains a real-time risk score by standardizing and weighting the accuracy, safety, reliability attributes and scenario risk results. Standardization can eliminate differences between data from different sources and highlight the relative relationships between data. The real-time risk score can clearly reflect the quantitative level of driving risk in the current scenario, which is helpful for subsequent risk level analysis.

[0054] In one embodiment, the risk scoring threshold includes a first risk scoring threshold and a second risk scoring threshold, wherein the first risk scoring threshold is less than the second risk scoring threshold; please refer to Figure 6 In step S103, namely, determining the risk level of the vehicle based on the real-time risk score and the risk score threshold, and controlling the vehicle to perform avoidance operations corresponding to the risk level, the steps include: S601: When the real-time risk score has not yet reached the first risk score threshold, the risk level is determined to be low risk level, and the vehicle is controlled to perform a warning prompt operation; S602: When the real-time risk score reaches the first risk score threshold but has not yet reached the second risk score threshold, the risk level is determined to be medium risk level, and the vehicle is controlled to perform a deceleration operation according to the first preset deceleration duration, real-time vehicle speed and safe recommended vehicle speed; the safe recommended vehicle speed is determined according to the environmental detection information; S603: When the real-time risk score reaches the second risk score threshold, the risk level is determined to be high risk level, and the vehicle is controlled to perform a deceleration operation according to the second preset deceleration duration, real-time vehicle speed and safe recommended vehicle speed; the safe recommended vehicle speed is determined according to the environmental detection information, and the second preset deceleration duration is less than the first preset deceleration duration.

[0055] Understandably, the electronic control unit (ECU) compares the real-time risk score with a first risk score threshold and a second risk score threshold, respectively, and determines the risk level and avoidance actions based on the comparison results. When the real-time risk score is less than the first risk score threshold, it indicates that the possibility of the vehicle encountering a risk is negligible or the risk level is very low. In this case, the ECU determines the risk level as low risk, and the corresponding avoidance action is to control the vehicle to perform a warning prompt. The warning prompt action specifically involves displaying the detected typhoon wind speed and rainfall information via the HUD or instrument panel. When the real-time risk score is greater than or equal to the first risk score threshold and less than the second risk score threshold, it indicates that the possibility of the risk encountering a risk is not negligible or there is a slight risk. In this case, the ECU determines the risk level as medium risk, and when the real-time vehicle speed is greater than the safe recommended speed, the corresponding avoidance action is to control the vehicle to perform an active deceleration operation according to a first preset deceleration duration, reducing the vehicle speed to the safe recommended speed determined by environmental detection information. When the real-time risk score is greater than the second risk score threshold, it indicates that there is a serious risk to the vehicle's driving safety. At this time, the electronic control unit determines the risk level to be high-risk. When the real-time vehicle speed is greater than the safe recommended speed, the corresponding avoidance operation is to control the vehicle to perform active deceleration operation according to the first preset deceleration time, reduce the vehicle speed to the safe recommended speed determined by the environmental detection information, and turn on the hazard warning lights (double flashers).

[0056] This embodiment categorizes risk levels based on different scoring results and implements different measures for different risk levels, achieving precise response. At low risk levels, early warning prompts promptly alert the driver to potential risks without interfering with driving. At medium and high risk levels, it calculates recommended safe speeds and applies deceleration with varying reaction times to help the driver better control the vehicle and reduce the likelihood of accidents. Each risk level has clear judgment criteria and procedures, improving the reliability and stability of risk avoidance decisions.

[0057] In one embodiment, the environmental monitoring information includes real-time rainfall; please refer to... Figure 7 In step S602 or S603, the recommended safe speed is determined based on the environmental detection information, including the following steps: S701: Determine the road surface friction coefficient based on the real-time rainfall; S702: Determine the critical lateral wind speed based on the vehicle model information; S703: Obtain the wheel track width and center of gravity height of the vehicle, and determine the recommended safe speed based on the wheel track width, the center of gravity height, the critical lateral wind speed, and the road surface friction coefficient.

[0058] Understandably, the electronic control unit (ECU) establishes a mathematical model of the relationship between rainfall and road surface friction coefficient through extensive real-vehicle test data and rainfall detection. Based on the correspondence between different rainfall amounts and road surface friction coefficients, the ECU can determine the road surface friction coefficient corresponding to the real-time rainfall. Specifically, when the real-time rainfall is less than or equal to 50 mm / hour, the road surface friction coefficient maintains the default initial value for rubber tires and asphalt roads. When the real-time rainfall is greater than 50 mm / hour, the road surface friction coefficient decreases by 30% compared to the default initial value. Furthermore, based on vehicle model information, the ECU can obtain the critical lateral wind speed corresponding to the actual vehicle model. When the vehicle model information is a sedan, the critical lateral wind speed is 15 m / s; when the vehicle model information is an SUV or MPV, the critical lateral wind speed is 12 m / s. The vehicle's wheelbase width and center of gravity height are fixed attributes of the vehicle itself. The ECU uses rollover dynamics formulas to perform critical condition analysis on wheelbase width, center of gravity height, critical lateral wind speed, and road surface friction coefficient to determine the recommended safe speed. The specific rollover dynamics formula is expressed as follows: ,in, Indicates the recommended safe speed. Represents gravitational acceleration. Indicates the wheelbase width. This indicates the critical lateral wind speed. This represents the safe rollover factor (taken as 0.3). Indicates the coefficient of friction of the road surface. This indicates the center of gravity height. When the gravitational acceleration is 9.8, the wheelbase width is 1.6, the critical crosswind speed is 31.5, the safe rollover coefficient is 0.3, the road friction coefficient is 0.6, and the center of gravity height is 0.6, the corresponding safe recommended speed is 74 km / h, indicating that the vehicle needs to be reduced to 74 km / h or below.

[0059] This embodiment calculates a safe recommended vehicle speed by determining the road surface friction coefficient based on real-time rainfall and combining it with the critical crosswind speed determined by vehicle model information. This ensures that the vehicle maintains stable driving under wet and slippery road conditions and crosswinds. It can perceive environmental changes in real time and provide safe speed suggestions for the current driving scenario, improving the pertinence in dealing with complex scenarios and enhancing the rationality and effectiveness of risk avoidance operations.

[0060] This application also provides a vehicle avoidance device 80, please refer to... Figure 8The system includes: a scenario risk analysis module 801, used to determine the scenario risk result based on the vehicle's driving information and environmental detection information; a risk score determination module 802, used to determine the real-time risk score of the vehicle based on the vehicle's accuracy attribute data, safety attribute data, credibility attribute data and the scenario risk result; and a risk avoidance decision module 803, used to determine the risk level of the vehicle based on the real-time risk score and risk score threshold, and control the vehicle to perform risk avoidance operations corresponding to the risk level.

[0061] This application also provides an electronic device 90, please refer to... Figure 9 It includes a memory 901 and a processor 902, wherein the memory 901 is used to store computer programs; and the processor 902 is used to execute the programs stored in the memory 901 to implement the vehicle avoidance method described in any embodiment of this application.

[0062] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle avoidance method described in any embodiment of this application.

[0063] In this application, "multiple" refers to two or more.

[0064] The terms “first,” “second,” “third,” “fourth,” etc., in this application (if present) are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0065] In this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, in this application, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0066] Unless otherwise specified, all steps in this application may be performed sequentially or randomly. For example, if the method includes steps A and B, it means that the method may include steps A and B performed sequentially, or it may include steps B and A performed sequentially. For example, if the method may also include step C, it means that step C may be added to the method in any order. For example, the method may include steps A, B, and C, or it may include steps A, C, and B, or it may include steps C, A, and B, etc.

[0067] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A vehicle hazard avoidance method, characterized in that, include: Based on the vehicle's driving information and environmental monitoring information, the scenario risk result is determined. The scenario risk result is an assessment result used to measure the probability and severity of potential risks to the vehicle under the influence of environmental factors in a specific traffic scenario. Based on the vehicle's accuracy attribute data, safety attribute data, reliability attribute data, and the scenario risk results, a real-time risk score for the vehicle is determined. The accuracy attribute data is an attribute parameter characterizing the accuracy of the data acquisition component in collecting vehicle driving information and environmental detection information. The safety attribute data is an attribute parameter characterizing the redundancy and stability of the data acquisition function after a failure. The reliability attribute data is an attribute parameter characterizing the anti-interference level of the data acquisition component in collecting vehicle driving information and environmental detection information. Based on the real-time risk score and risk score threshold, the risk level of the vehicle is determined, and the vehicle is controlled to perform avoidance operations corresponding to the risk level. The step of determining the scenario risk result based on the vehicle's driving information and environmental detection information includes: The environmental detection information is compensated based on the vehicle driving information to obtain environmental compensation information; Based on the vehicle driving information and the environmental compensation information, determine the scene indicator values ​​and scene indicator weights; Based on the scenario indicator values ​​and scenario indicator weights, a scenario risk score is determined, and the scenario risk score is determined as the scenario risk result. The step of determining the real-time risk score of the vehicle based on its accuracy attribute data, safety attribute data, credibility attribute data, and the scenario risk results includes: The accuracy attribute data, security attribute data, credibility attribute data, and scenario risk results are standardized to obtain a standard array, which includes accuracy standard values, security standard values, credibility standard values, and scenario risk standard values. Obtain the risk weight reassembly corresponding to the standard array, and perform weighted summation on the accuracy standard value, safety standard value, credibility standard value and scenario risk standard value according to the risk weight reassembly to obtain the real-time risk score.

2. The vehicle hazard avoidance method according to claim 1, characterized in that, The vehicle driving information includes real-time vehicle speed and real-time roll angle, and the environmental detection information includes real-time wind speed and real-time rainfall. The step of compensating the environmental detection information based on the vehicle driving information to obtain environmental compensation information includes: The wind speed correction coefficient is determined based on the real-time vehicle speed and real-time roll angle. The real-time corrected wind speed is determined based on the wind speed correction coefficient and the real-time wind speed. Obtain the historical corrected wind speed from the previous moment, and determine the wind speed deviation value based on the real-time corrected wind speed and the historical corrected wind speed; If the wind speed deviation value is less than or equal to the preset wind speed deviation threshold, then environmental compensation information is determined based on the real-time corrected wind speed and the real-time rainfall.

3. The vehicle hazard avoidance method according to claim 1, characterized in that, The vehicle driving information includes real-time vehicle speed and vehicle location, and the environmental compensation information includes real-time corrected wind speed and real-time rainfall. The step of determining scene indicator values ​​and scene indicator weights based on the vehicle driving information and the environmental compensation information includes: Based on the vehicle's location, determine the target scene and obtain the scene slope and scene weight data table corresponding to the target scene; The scene indicator weights corresponding to each scene indicator value are found in the scene weight data table; the scene indicator values ​​include the real-time corrected wind speed, the real-time rainfall, the real-time vehicle speed, and the scene slope.

4. The vehicle hazard avoidance method according to claim 1, characterized in that, The risk scoring threshold includes a first risk scoring threshold and a second risk scoring threshold, wherein the first risk scoring threshold is less than the second risk scoring threshold; The step of determining the risk level of the vehicle based on the real-time risk score and risk score threshold, and controlling the vehicle to perform avoidance operations corresponding to the risk level, includes: When the real-time risk score has not yet reached the first risk score threshold, the risk level is determined to be low risk level, and the vehicle is controlled to perform a warning prompt operation. When the real-time risk score reaches the first risk score threshold but has not yet reached the second risk score threshold, the risk level is determined to be medium risk level, and the vehicle is controlled to perform a deceleration operation based on the first preset deceleration duration, real-time vehicle speed, and safe recommended vehicle speed; the safe recommended vehicle speed is determined based on the environmental detection information. When the real-time risk score reaches the second risk score threshold, the risk level is determined to be high risk level, and the vehicle is controlled to perform a deceleration operation based on the second preset deceleration duration, real-time vehicle speed, and safe recommended vehicle speed; the safe recommended vehicle speed is determined based on the environmental detection information, and the second preset deceleration duration is less than the first preset deceleration duration.

5. The vehicle hazard avoidance method according to claim 4, characterized in that, The environmental monitoring information includes real-time rainfall; The recommended safe speed is determined based on the environmental detection information, including: The road surface friction coefficient is determined based on the real-time rainfall. Based on the vehicle model information, determine the critical lateral wind speed; The wheelbase width and center of gravity height of the vehicle are obtained, and a safe recommended speed is determined based on the wheelbase width, the center of gravity height, the critical lateral wind speed, and the road surface friction coefficient.

6. A vehicle safety avoidance device, characterized in that, include: The scenario risk analysis module is used to determine scenario risk results based on vehicle driving information and environmental detection information. The scenario risk results are assessments used to measure the likelihood and severity of potential risks to a vehicle under the influence of environmental factors in a specific traffic scenario. The process of determining the scenario risk results based on vehicle driving information and environmental detection information includes: compensating the environmental detection information based on the vehicle driving information to obtain environmental compensation information; determining scenario indicator values ​​and scenario indicator weights based on the vehicle driving information and the environmental compensation information; determining a scenario risk score based on the scenario indicator values ​​and scenario indicator weights; and defining the scenario risk score as the scenario risk result. The risk scoring determination module is used to determine the real-time risk score of the vehicle based on its accuracy attribute data, safety attribute data, reliability attribute data, and the scenario risk results. The accuracy attribute data is a parameter characterizing the accuracy of the data acquisition component in collecting vehicle driving information and environmental detection information. The safety attribute data is a parameter characterizing the redundancy and stability of the data acquisition component's data acquisition function after a failure. The reliability attribute data is a parameter characterizing the interference resistance of the data acquisition component in collecting vehicle driving information and environmental detection information. The step of determining the real-time risk score of the vehicle based on its accuracy attribute data, safety attribute data, credibility attribute data, and scenario risk results includes: standardizing the accuracy attribute data, safety attribute data, credibility attribute data, and scenario risk results to obtain a standard array, wherein the standard array includes a standard value for accuracy, a standard value for safety, a standard value for credibility, and a standard value for scenario risk; obtaining a risk weighted reorganization corresponding to the standard array; and performing a weighted summation of the standard values ​​for accuracy, safety, credibility, and scenario risk based on the risk weighted reorganization to obtain the real-time risk score. The risk avoidance decision module is used to determine the risk level of the vehicle based on the real-time risk score and the risk score threshold, and control the vehicle to perform risk avoidance operations corresponding to the risk level.

7. An electronic device, characterized in that, Including processor and memory, among which Memory, used to store computer programs; A processor for executing a program stored in memory to implement the vehicle avoidance method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the vehicle avoidance method according to any one of claims 1-5.

Images