A method and device for evaluating the risk of instability of an oncoming vehicle

Abstract

This invention discloses a method and apparatus for assessing the instability risk of oncoming vehicles. The method includes: if the trajectories of an oncoming vehicle and a vehicle overlap in a spatial region within a preset time period in the future, obtaining the road surface adhesion coefficient and the lateral velocity, lateral acceleration, and azimuth angle deviation of the oncoming vehicle; determining a sideslip risk term based on the lateral velocity and road surface adhesion coefficient; determining a runaway acceleration risk term based on the lateral acceleration and road surface adhesion coefficient; determining a fishtail-lateral displacement risk term based on the lateral velocity and azimuth angle deviation; and determining the instability risk of the oncoming vehicle based on the sideslip risk term, the runaway acceleration risk term, and the fishtail-lateral displacement risk term. This method overcomes the limitations of existing technologies that rely solely on basic motion parameters such as position and velocity, and can capture the instability precursor characteristics of oncoming vehicles, such as sideslip and fishtail, from the perspective of vehicle dynamics. It achieves accurate quantitative assessment of instability risk and effectively improves the accuracy and reliability of identifying collision risks of oncoming vehicles.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, and in particular to a method and device for assessing the instability risk of oncoming vehicles. Background Technology

[0002] With the rapid development of intelligent driving technology, the vehicle's safety decision-making ability in complex road environments is receiving increasing attention. Especially in high-risk driving scenarios (such as curves), oncoming vehicles may experience skidding, fishtailing, or other instability due to slippery road surfaces, excessive speed, or improper handling, and may even veer out of their lane and into the driving area of ​​the vehicle, posing a serious collision threat to the vehicle itself.

[0003] In existing technologies, the assessment of vehicle collision risk mainly relies on the analysis of the spatiotemporal intersection between the vehicle and other vehicles. For example, it predicts the driving trajectory using basic motion parameters such as the position and speed of the vehicle and other vehicles, and judges whether there is a possibility of collision between the vehicle and other vehicles based on the driving trajectory. These methods usually only consider basic motion parameters such as position and speed, which has limitations in dealing with dangerous scenarios such as sudden instability of oncoming vehicles, and it is difficult to accurately quantify the degree of instability risk.

[0004] Therefore, how to accurately identify the instability risk of oncoming vehicles and achieve a quantitative assessment of the degree of instability has become a pressing technical problem to be solved in the field of intelligent driving safety. Summary of the Invention

[0005] In order to accurately quantify the degree of instability risk of oncoming vehicles, this invention provides a method and apparatus for assessing the instability risk of oncoming vehicles.

[0006] In a first aspect, embodiments of the present invention provide a method for assessing the instability risk of oncoming vehicles, which may include: If the trajectories of oncoming vehicles and other vehicles overlap in a spatial area within a preset time period in the future, the road surface adhesion coefficient, as well as the lateral velocity, lateral acceleration, and orientation angle deviation of the oncoming vehicles, are obtained. Based on the lateral velocity and the road surface adhesion coefficient, the sideslip risk item is determined; Based on the lateral acceleration and the road surface adhesion coefficient, the risk of runaway acceleration is determined; Based on the lateral velocity and the heading angle deviation, a tail-flip risk item is determined; The instability risk of the oncoming vehicle is determined based on the sideslip risk item, the runaway acceleration risk item, and the fishtail-side shift risk item.

[0007] In one or more optional embodiments of this application, determining the drift-lateral risk term based on the lateral velocity and the heading angle deviation includes: Based on the absolute value of the lateral velocity and the preset lateral velocity limit value, a first normalized value of the lateral velocity is obtained; Based on the absolute value of the orientation angle deviation and the preset orientation angle deviation limit value, the normalized value of the orientation angle deviation is obtained; Based on the first normalized lateral velocity value and the normalized azimuth angle deviation value, the tail-slip risk term is obtained.

[0008] In one or more optional embodiments of this application, determining the sideslip risk item based on the lateral velocity and the road surface adhesion coefficient includes: Based on the lateral velocity and the preset lateral velocity limit value, a second normalized lateral velocity value is obtained; Based on the road surface adhesion coefficient and the baseline value of the adhesion coefficient, the normalized value of road surface adhesion is obtained; The sideslip risk term is obtained based on the second normalized lateral velocity value and the normalized road surface adhesion value.

[0009] In one or more optional embodiments of this application, determining the runaway acceleration risk item based on the lateral acceleration and the road surface adhesion coefficient includes: The runaway acceleration risk term is obtained based on the absolute value of the lateral acceleration, the road surface adhesion coefficient, and the standard gravitational acceleration.

[0010] In one or more optional embodiments of this application, determining the instability risk of the oncoming vehicle based on the sideslip risk item, the runaway acceleration risk item, and the drift-lateral shift risk item includes: Determine the first weight value, the second weight value, and the third weight value corresponding to the sideslip risk item, the runaway acceleration risk item, and the tail-side slip risk item, respectively; Based on the first weight value, the second weight value, and the third weight value, the sideslip risk item, the runaway acceleration risk item, and the fishtail-side shift risk item are weighted and summed to obtain the instability risk of the oncoming vehicle.

[0011] In one or more optional embodiments of this application, after determining the instability risk of the oncoming vehicle based on the sideslip risk item, the runaway acceleration risk item, and the drift-lateral shift risk item, the method further includes: Based on the first weight value, the second weight value, the third weight value, and the vehicle environmental parameters, determine the update of the first weight value, the update of the second weight value, and the update of the third weight value; Based on the updated first weight value, updated second weight value, and updated third weight value, the sideslip risk item, the runaway acceleration risk item, and the fishtail-side slip risk item are weighted and summed to obtain the dynamic instability risk of the oncoming vehicle. Based on the aforementioned instability risk and the aforementioned dynamic instability risk, an early warning strategy is determined.

[0012] In one or more optional embodiments of this application, the vehicle environmental parameters include road surface adhesion coefficient, curve radius of curvature, relative speed between the oncoming vehicle and the vehicle, and road slope. The step of determining, updating the first weight value, updating the second weight value, and updating the third weight value based on the first weight value, the second weight value, the third weight value, and the vehicle environmental parameters includes: Based on the road surface adhesion coefficient, the curve radius of curvature, the relative speed, and the road slope, respectively determine the road surface adhesion coefficient correction factor, the curve radius of curvature correction factor, the relative speed correction factor, and the slope correction factor; Based on the road surface adhesion coefficient correction factor, the curve curvature radius correction factor, the relative speed correction factor, and the slope correction factor, the first weight value, the second weight value, and the third weight value are corrected respectively to obtain the updated first weight value, the updated second weight value, and the updated third weight value.

[0013] In one or more optional embodiments of this application, determining the early warning strategy based on the instability risk and the dynamic instability risk includes: Based on the dynamic instability risk, a first-level instability risk and a second-level instability risk are determined; wherein, the first-level instability risk is less than the second-level instability risk, and the second-level instability risk is less than the dynamic instability risk; If the instability risk is greater than or equal to the first-level instability risk, the vehicle instrument panel will display a warning icon. If the instability risk is greater than or equal to the secondary instability risk, the vehicle is controlled to output a voice alarm signal to suggest that the driver make slight adjustments to the lane position or reduce speed. If the instability risk is greater than or equal to the dynamic instability risk, then the vehicle is controlled to brake suddenly and reverse or change lanes to avoid a collision.

[0014] Secondly, embodiments of the present invention provide a device for assessing the instability risk of oncoming vehicles, which may include: The judgment module is used to obtain the road surface adhesion coefficient, the lateral velocity, lateral acceleration and orientation angle deviation of the oncoming vehicle if the driving trajectories of the oncoming vehicle and the vehicle overlap in a spatial area within a preset time period in the future. The first risk module is used to determine the sideslip risk item based on the lateral velocity and the road surface adhesion coefficient; The second risk module is used to determine the runaway acceleration risk item based on the lateral acceleration and the road surface adhesion coefficient; The third risk module is used to determine the tail-slip risk item based on the lateral velocity and the heading angle deviation; The determination module is used to determine the instability risk of the oncoming vehicle based on the sideslip risk item, the runaway acceleration risk item, and the drift-lateral shift risk item.

[0015] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program / instruction stored thereon, which, when executed by a processor, implements the above-described method for assessing the instability risk of oncoming vehicles.

[0016] Fourthly, embodiments of the present invention provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-described method for assessing the instability risk of oncoming vehicles.

[0017] Fifthly, embodiments of the present invention provide a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-described method for assessing the instability risk of oncoming vehicles.

[0018] The beneficial effects of the above-described technical solutions provided in the embodiments of the present invention include at least the following: This invention provides a method for assessing the instability risk of oncoming vehicles. This method uses the existence of a spatiotemporal intersection between the oncoming vehicle and the vehicle itself as a trigger condition. Based on this, it constructs a sideslip risk term, a runaway acceleration risk term, and a fishtail-lateral displacement risk term using the oncoming vehicle's lateral velocity, lateral acceleration, heading angle deviation, and road adhesion coefficient, ultimately generating the instability risk. This method overcomes the limitations of traditional spatiotemporal intersection analysis, which relies solely on basic motion parameters such as position and velocity. It can capture the instability precursor characteristics of oncoming vehicles, such as sideslip and fishtailing, from a vehicle dynamics perspective, achieving accurate quantitative assessment of instability risk and effectively improving the accuracy and reliability of oncoming vehicle collision risk identification under curve conditions.

[0019] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0020] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0021] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating the method for assessing the instability risk of oncoming vehicles provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the oncoming vehicle instability risk assessment device provided in an embodiment of the present invention. Detailed Implementation

[0022] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0023] The inventors discovered that existing technologies for assessing vehicle collision risk primarily rely on analyzing the spatiotemporal intersection between the vehicle and other vehicles, such as predicting driving trajectories to determine the likelihood of a collision. These methods typically only consider basic motion parameters like position and speed, which limits their effectiveness in handling dangerous scenarios such as sudden instability of oncoming vehicles, making it difficult to accurately quantify the degree of instability risk. Existing solutions often employ single braking or warning measures, lacking response mechanisms for intrusive vehicle intrusion scenarios, and failing to provide sufficient avoidance space for the vehicle in emergency situations. Based on this, the inventors, through further research and development, created this invention, providing a method and device for assessing the instability risk of oncoming vehicles.

[0024] Example 1 Embodiment 1 of the present invention provides a method for assessing the instability risk of oncoming vehicles, referring to... Figure 1 As shown, the method may include the following steps S101-S105: S101: If the trajectories of oncoming vehicles and vehicles overlap in a spatial area within a preset time period in the future, then obtain the road surface adhesion coefficient and the lateral velocity, lateral acceleration and orientation angle deviation of the oncoming vehicles.

[0025] S102: Determine the sideslip risk items based on lateral velocity and road adhesion coefficient.

[0026] S103: Determine the risk of runaway acceleration based on lateral acceleration and road adhesion coefficient.

[0027] S104: Determine the fishtail-side slip risk term based on lateral velocity and heading angle deviation.

[0028] S105: Determine the instability risk of the oncoming vehicle based on the sideslip risk item, the runaway acceleration risk item, and the fishtail-lateral shift risk item.

[0029] This invention provides a method for assessing the instability risk of oncoming vehicles. This method uses the existence of a spatiotemporal intersection between the oncoming vehicle and the vehicle itself as a trigger condition. Based on this, it constructs a sideslip risk term, a runaway acceleration risk term, and a fishtail-lateral displacement risk term using the oncoming vehicle's lateral velocity, lateral acceleration, heading angle deviation, and road adhesion coefficient, ultimately generating the instability risk. This method overcomes the limitations of traditional spatiotemporal intersection analysis, which relies solely on basic motion parameters such as position and velocity. It can capture the instability precursor characteristics of oncoming vehicles, such as sideslip and fishtailing, from a vehicle dynamics perspective, achieving accurate quantitative assessment of instability risk and effectively improving the accuracy and reliability of oncoming vehicle collision risk identification under curve conditions.

[0030] In step S101 above, if the trajectories of the oncoming vehicle and the vehicle overlap in a spatial region within a preset time period in the future, the road surface adhesion coefficient, as well as the lateral velocity, lateral acceleration, and orientation angle deviation of the oncoming vehicle, are obtained.

[0031] Specifically, this can be achieved by using an onboard visual perception system and millimeter-wave radar to collect real-time motion status information of oncoming vehicles and predict their trajectory within a preset time period. If the predicted trajectory overlaps with the trajectory of the vehicle itself in a spatial region, and this overlap persists for multiple consecutive sampling periods, it is determined that there is a long-term spatiotemporal intersection between the two.

[0032] The system acquires the lateral velocity, lateral acceleration, and directional angle deviation of oncoming vehicles, and simultaneously estimates the adhesion coefficient of the current road surface in real time through the vehicle chassis system. These parameters are then used as inputs for subsequent risk calculations.

[0033] In step S102 above, the sideslip risk item is determined based on the lateral velocity and the road surface adhesion coefficient. Specifically, this includes the following steps S1021-S1023: S1021: Based on the lateral velocity and the preset lateral velocity limit value, obtain the second normalized value of the lateral velocity.

[0034] Specifically, it can be based on the lateral speed of oncoming vehicles detected in real time, retaining its original sign to reflect the direction of lateral deviation (positive values ​​indicate deviation towards the lane, and negative values ​​indicate deviation away from the lane).

[0035] Dividing this lateral velocity by a preset lateral velocity limit value yields a second normalized lateral velocity value. The preset lateral velocity limit value is pre-calibrated based on vehicle dynamics characteristics and common road conditions, and is used to characterize the safety boundary of lateral velocity under normal driving conditions.

[0036] The above division operation yields a second normalized value for the lateral velocity, which ranges from -1 to 1. The sign of the value represents the direction of the offset, and the magnitude of the absolute value represents the severity of the lateral slip.

[0037] S1022: Based on the road surface adhesion coefficient and the baseline value of the adhesion coefficient, the normalized value of the road surface adhesion is obtained.

[0038] Specifically, it could be based on the road adhesion coefficient estimated in real time by the vehicle chassis system, which reflects the ultimate grip level between the current road surface (such as dry asphalt, wet cement, or icy and snowy road surface) and the tires.

[0039] Divide the road surface adhesion coefficient by the reference value of the adhesion coefficient to obtain the normalized value of the road surface adhesion. The reference value of the adhesion coefficient is usually taken as the typical adhesion coefficient of dry asphalt pavement (with a value range of 0.8 to 1.0) to eliminate the influence of different pavement conditions on the dimensions of subsequent calculations.

[0040] Through the above normalization process, a road surface adhesion normalization value with a range of 0 to 1 is obtained. The smaller the value, the worse the current road surface adhesion conditions are, and the more likely the vehicle is to skid.

[0041] S1023: Based on the normalized value of the second lateral velocity and the normalized value of road surface adhesion, the sideslip risk term is obtained.

[0042] Specifically, the sideslip risk term can be obtained by multiplying the normalized value of the second lateral velocity by the normalized value of the road surface adhesion. The normalized value of the second lateral velocity retains the directional information of the lateral deviation, and the normalized value of the road surface adhesion is a non-negative value. Therefore, the sign of the sideslip risk term is determined by the sign of the normalized value of the second lateral velocity, which is used to characterize the lateral deviation direction of the oncoming vehicle (a positive value indicates deviation towards the lane, and a negative value indicates deviation away from the lane).

[0043] The absolute value of the sideslip risk term is determined by both the intensity of the lateral velocity and the road adhesion conditions. The larger the absolute value of the lateral velocity and the lower the road adhesion coefficient, the larger the absolute value of the product, indicating that the kinetic energy of the oncoming vehicle's lateral movement is closer to or exceeds the lateral adhesion limit between the tire and the road surface, and the higher the sideslip risk. This calculation achieves a joint quantification of the intensity and direction of sideslip risk.

[0044] To facilitate understanding of this method by those skilled in the art, step S102 is explained more clearly here based on a formula. The complete calculation method of step S102 is shown in Formula 1 below:

[0045] In the formula, This is a side-slip risk item. For lateral velocity, The road surface adhesion coefficient, To preset the lateral velocity limit, This is the baseline value for the adhesion coefficient.

[0046] In step S103 above, the risk of runaway acceleration is determined based on lateral acceleration and road surface adhesion coefficient.

[0047] Specifically, the runaway acceleration risk term can be obtained based on the absolute value of lateral acceleration, the road surface adhesion coefficient, and the standard gravitational acceleration.

[0048] Specifically, based on the real-time detected lateral acceleration of oncoming vehicles, the absolute value of the acceleration is taken to eliminate the influence of direction, thus obtaining the lateral acceleration amplitude.

[0049] Based on the road adhesion coefficient estimated in real time by the vehicle chassis system and the standard gravitational acceleration, the absolute value of the lateral acceleration is used as the numerator, and the product of the road adhesion coefficient and the standard gravitational acceleration is used as the denominator. The ratio of the two is then calculated to obtain the runaway acceleration risk term, as shown in Formula 2 below:

[0050] In the formula, This is to accelerate the risk of things getting out of control. For lateral acceleration, The road surface adhesion coefficient, g The standard gravitational acceleration is approximately 9.8 m / s², which is used as the reference unit.

[0051] The physical meaning of the runaway acceleration risk term is that the absolute value of the lateral acceleration represents the degree of change in the lateral motion state, and the product of the road adhesion coefficient and the standard gravitational acceleration represents the maximum theoretical lateral acceleration that the tire can provide under the current road conditions.

[0052] When the absolute value of lateral acceleration suddenly increases while the road surface adhesion coefficient is low, the ratio increases significantly, indicating that oncoming vehicles are changing their lateral motion at a rate close to the physical limits of the road surface, and the risk of loss of control increases sharply. Conversely, if the amplitude of lateral acceleration is small or the road surface adhesion conditions are good, the ratio is small, and the risk of loss of control is low.

[0053] In step S104 above, the drift-lateral risk term is determined based on the lateral velocity and heading angle deviation. Specifically, this includes the following steps S1041-S1043: S1041: Based on the absolute value of the lateral velocity and the preset lateral velocity limit value, obtain the first normalized value of the lateral velocity.

[0054] Specifically, this can be achieved by taking the absolute value of the lateral velocity of oncoming vehicles detected in real time to eliminate directional influence. The absolute value of the lateral velocity is then divided by a preset lateral velocity limit value to obtain a first normalized lateral velocity value.

[0055] The preset lateral velocity limit value is the same as the preset lateral velocity limit value used in step S1021 above, and is used to characterize the safety boundary of lateral velocity.

[0056] Through the above calculations, a first normalized value for lateral velocity is obtained, which ranges from 0 to 1. The closer this value is to 1, the more severe the lateral slippage of the oncoming vehicle.

[0057] S1042: Based on the absolute value of the orientation angle deviation and the preset orientation angle deviation limit value, obtain the normalized value of the orientation angle deviation.

[0058] Specifically, this can be achieved by taking the absolute value of the oncoming vehicle's heading angle deviation detected in real time to eliminate the directional influence of left or right deviation. The absolute value of the heading angle deviation is then divided by a preset heading angle deviation limit value to obtain a normalized heading angle deviation value.

[0059] The preset steering angle deviation limit can be set to an angle threshold between 30° and 45°. Exceeding this value usually means that the vehicle has experienced serious loss of steering control.

[0060] Through the above calculations, a normalized value for the orientation angle deviation is obtained, which ranges from 0 to 1. The closer the value is to 1, the more serious the deviation of the oncoming vehicle's front end from the normal driving direction.

[0061] S1043: Based on the first normalized value of lateral velocity and the normalized value of heading angle deviation, the tail-slip risk term is obtained.

[0062] Specifically, the first normalized lateral velocity value can be multiplied by the normalized azimuth angle deviation value to obtain the tail-slip risk term.

[0063] In this model, the normalized value of the first lateral velocity characterizes the severity of lateral slippage, and the normalized value of the heading angle deviation characterizes the degree of deviation in the vehicle's pointing direction. Both are non-negative values, so the absolute value of the product is determined by both. A large heading angle deviation alone may indicate that the vehicle is turning or slightly veering, while a large lateral velocity alone may indicate that the vehicle is making a smooth lane change. Neither alone necessarily indicates instability. However, when both are large simultaneously, i.e., when the fishtail-lateral slip risk term is large, it strongly suggests that the vehicle is in a state where the pointing direction and the lateral movement direction are significantly inconsistent. This is a typical instability characteristic of fishtailing or understeer accompanied by lateral slippage. This product calculation can effectively capture this complex instability mode, improving the accuracy of fishtail-lateral slip risk identification.

[0064] To facilitate understanding of this method by those skilled in the art, step S104 above will be explained more clearly based on a formula. The complete calculation method of step S104 is shown in Formula 3 below:

[0065] In the formula, For the fishtail-lateral shift risk item, For the orientation angle deviation, To preset the orientation angle deviation limit value, For lateral velocity, This is a preset lateral velocity limit value.

[0066] In step S105 above, the instability risk of the oncoming vehicle is determined based on the sideslip risk item, the runaway acceleration risk item, and the fishtail-lateral shift risk item. Specifically, this includes the following steps S1051-S1052: S1051: Determine the first weight value, second weight value, and third weight value corresponding to the sideslip risk item, the runaway acceleration risk item, and the tail-slip risk item, respectively.

[0067] Specifically, this can be achieved by pre-calibrating the first, second, and third weight values ​​for the sideslip risk item, the runaway acceleration risk item, and the fishtail-lateral shift risk item using a real-vehicle dataset. The real-vehicle dataset contains cornering data under various road conditions and different degrees of instability. The weight values ​​are determined based on the actual contribution of each risk item to the final instability risk; the greater the contribution, the higher the weight value for that risk item.

[0068] S1052: Based on the first weight value, the second weight value, and the third weight value, the sideslip risk term, the runaway acceleration risk term, and the fishtail-side shift risk term are weighted and summed to obtain the instability risk of the oncoming vehicle.

[0069] Specifically, the risk of instability of the oncoming vehicle can be obtained by multiplying the sideslip risk term by the first weight value, the runaway acceleration risk term by the second weight value, and the fishtail-lateral shift risk term by the third weight value, and then adding the three products together. This instability risk is a scalar value used to comprehensively quantify the degree of instability of the oncoming vehicle at the current moment; the larger the value, the higher the instability risk.

[0070] To facilitate understanding of this method by those skilled in the art, step S1052 above will be explained more clearly based on the formula. The complete calculation method of step S104 is shown in Formula 4 below:

[0071] In the formula, Risk To mitigate the risk of instability, This is a side-slip risk item. This is to accelerate the risk of things getting out of control. For the fishtail-lateral shift risk item, For the orientation angle deviation, For lateral acceleration, The road surface adhesion coefficient, For lateral velocity, The road surface adhesion coefficient, w 1. w 2 and w 3 represents the first weight value, the second weight value, and the third weight value, respectively.

[0072] In this embodiment of the application, after completing step S105 to determine the instability risk of the approaching vehicle, step S106 is further included, which determines a warning strategy based on the instability risk of the approaching vehicle, specifically including the following steps S1061-S1063: S1061: Based on the first weight value, the second weight value, and the third weight value, and the vehicle environmental parameters, determine the updated first weight value, the updated second weight value, and the updated third weight value. The vehicle environmental parameters include the road surface adhesion coefficient, the radius of curvature of the curve, the relative speed between oncoming vehicles and the vehicle, and the road slope. Specifically, this includes the following steps S10611-S10612: S10611: Based on the road surface adhesion coefficient, the radius of curvature of the curve, the relative speed, and the road slope, determine the road surface adhesion coefficient correction factor, the radius of curvature of the curve correction factor, the relative speed correction factor, and the slope correction factor, respectively.

[0073] Specifically, a road surface adhesion coefficient correction factor can be determined based on the real-time acquired road surface adhesion coefficient. The value of this correction factor is derived from a real-vehicle dataset (containing over 10,000 sets of cornering instability events). When the road surface adhesion coefficient is below 0.4, it indicates a low-adhesion road surface, such as icy or wet surfaces, where tire grip is severely reduced and the vehicle is highly prone to sideslip. In this case, the road surface adhesion coefficient correction factor is set to 0.6 to lower the risk threshold and improve system sensitivity. When the road surface adhesion coefficient is greater than or equal to 0.7, it indicates a high-adhesion road surface, such as dry asphalt, where tire grip is good. In this case, the road surface adhesion coefficient correction factor is set to 1.2 to adopt the basic risk threshold. When the road surface adhesion coefficient is between 0.4 and 0.7, it indicates a medium-adhesion road surface, such as wet asphalt or lightly worn surfaces. A linear interpolation method is used to determine the corresponding correction factor value.

[0074] A correction factor for the curvature radius is determined based on the curvature radius of the curve. The value of this correction factor is also derived from real-vehicle dataset experiments. When the curvature radius of the curve is less than 100 meters, it indicates a small curvature radius curve, i.e., a sharp curve. The centripetal force required for the vehicle to navigate the curve is large, significantly increasing the risk of lateral instability. In this case, the correction factor is set to 0.7 to proportionally reduce the risk threshold. When the curvature radius of the curve is greater than or equal to 200 meters, it indicates a large curvature radius curve, i.e., a gentle curve. The vehicle's movement is closer to straight-line travel. In this case, the correction factor is set to 1.0 to adopt the standard threshold. When the curvature radius of the curve is between 100 meters and 200 meters, it indicates a medium curvature radius curve, and the corresponding correction factor value is determined using linear interpolation.

[0075] A relative speed correction factor is determined based on the relative speed between the oncoming vehicle and the vehicle itself. The value of this correction factor is also derived from real-vehicle dataset experiments. When the relative speed is greater than 80 km / h, it indicates a high relative speed condition, shortening the Time to Collision (TTC) and requiring earlier warning action; in this case, the relative speed correction factor is 0.8. When the relative speed is less than or equal to 40 km / h, it indicates a low relative speed condition, where a standard threshold can be used for judgment, focusing on the continuity analysis of the motion pattern; in this case, the relative speed correction factor is 1.0. When the relative speed is between 40 km / h and 80 km / h, it indicates a medium relative speed condition, and the corresponding correction factor value is determined using linear interpolation.

[0076] Based on the road gradient, a gradient correction factor is determined. When there is a lateral gradient on a curve, the gradient provides some centripetal force, which helps vehicle stability; in this case, the risk threshold can be appropriately increased. When there is a longitudinal gradient on a curve (uphill or downhill), it affects vehicle load distribution and braking efficiency, requiring dynamic correction of the adhesion coefficient in conjunction with the gradient angle. The specific value of the gradient correction factor is obtained by looking up a preset mapping table between gradient angle and correction factor; this mapping relationship is based on experimental calibration using real vehicle datasets.

[0077] S10612: Based on the road surface adhesion coefficient correction factor, the curve curvature radius correction factor, the relative speed correction factor, and the slope correction factor, the first weight value, the second weight value, and the third weight value are corrected respectively to obtain the updated first weight value, the updated second weight value, and the updated third weight value.

[0078] Specifically, the first weight value can be obtained by multiplying the road surface adhesion coefficient correction factor, the curve curvature radius correction factor, the relative speed correction factor, and the slope correction factor.

[0079] The updated second weight value is obtained by multiplying the second weight value by the road surface adhesion coefficient correction factor, the curve curvature radius correction factor, the relative speed correction factor, and the slope correction factor.

[0080] The updated third weight value is obtained by multiplying the third weight value by the road surface adhesion coefficient correction factor, the curve curvature radius correction factor, the relative speed correction factor, and the slope correction factor.

[0081] The above correction process can be uniformly expressed using the following formula 5:

[0082] In the formula, To update the first weight value, update the second weight value, or update the third weight value, w It can be the first weight value, the second weight value, or the third weight value. This is the road surface adhesion coefficient correction factor. This is the correction factor for the radius of curvature of the curve. This is a relative velocity correction factor. This is the slope correction factor.

[0083] Through the above modifications, the weight values ​​can be dynamically adjusted according to vehicle environmental parameters such as current road surface adhesion conditions, the degree of curve sharpness, relative speed, and road slope, thereby adapting to the risk assessment needs in different scenarios.

[0084] S1062: Based on updating the first weight value, updating the second weight value, and updating the third weight value, the sideslip risk term, the runaway acceleration risk term, and the fishtail-side shift risk term are weighted and summed to obtain the dynamic instability risk of the oncoming vehicle.

[0085] Specifically, it can be done by multiplying the sideslip risk term with the updated first weight value, the runaway acceleration risk term with the updated second weight value, and the drift-lateral shift risk term with the updated third weight value, and then adding the three products together to obtain the dynamic instability risk of the oncoming vehicle.

[0086] The dynamic instability risk is calculated using the same weighted summation method as the instability risk obtained in step S1052 above. The difference lies in the weight values ​​used: S1052 uses basic weight values ​​pre-calibrated based on real vehicle datasets, while this step uses updated weight values ​​corrected by vehicle environmental parameters such as road adhesion coefficient, curve curvature radius, relative speed, and road slope.

[0087] Therefore, dynamic instability risk can reflect the impact of the current road environment and driving conditions on the instability risk assessment in real time. The larger the value, the higher the instability risk of oncoming vehicles in the current scenario.

[0088] S1063: Determine the early warning strategy based on the instability risk and dynamic instability risk. This specifically includes the following steps: S10631-S10634: S10631: Based on the dynamic instability risk, determine the first-level instability risk and the second-level instability risk. Among them, the first-level instability risk is less than the second-level instability risk, and the second-level instability risk is less than the dynamic instability risk.

[0089] Specifically, it can be done by determining the first-level instability risk and the second-level instability risk based on the magnitude of the dynamic instability risk. The first-level instability risk is taken as 70% of the dynamic instability risk, and the second-level instability risk is taken as 85% of the dynamic instability risk. The dynamic instability risk itself serves as the third-level trigger threshold.

[0090] S10632: If the risk of instability is greater than or equal to the first-level instability risk, control the vehicle's instrument panel to display a warning icon.

[0091] Specifically, if the risk of instability is greater than or equal to the first-level instability risk, a first-level warning will be triggered, and the vehicle's dashboard will display a yellow warning icon to alert the driver to the risk of instability from oncoming vehicles.

[0092] S10633: If the risk of instability is greater than or equal to the level 2 instability risk, control the vehicle to output a voice alarm signal to suggest that the driver make slight adjustments to the lane position or reduce speed.

[0093] Specifically, if the risk of instability is greater than or equal to the level 2 instability risk, a level 2 warning will be triggered, the vehicle will be controlled to output a voice alarm signal, and the driver will be prompted through the in-vehicle human-machine interface to slightly adjust the lane position or appropriately slow down in order to increase the safe distance from oncoming vehicles.

[0094] S10634: If the risk of instability is greater than or equal to the risk of dynamic instability, then control the vehicle to brake suddenly and control the vehicle to reverse or change lanes to avoid a collision.

[0095] Specifically, if the risk of instability is greater than or equal to the risk of dynamic instability, a level three warning is triggered, and the vehicle intelligent system automatically intervenes in vehicle control, controlling the vehicle to perform emergency braking to reduce its own speed. At the same time, based on the position and movement of oncoming vehicles, the system controls the vehicle to perform emergency reversing or emergency lane changing operations to actively avoid collisions with instable oncoming vehicles. Example 2 Based on the same inventive concept, embodiments of the present invention also provide a device for assessing the instability risk of oncoming vehicles, referring to... Figure 2 As shown, the device includes: The judgment module 101 is used to obtain the road surface adhesion coefficient and the lateral velocity, lateral acceleration and orientation angle deviation of the oncoming vehicle if the driving trajectories of the oncoming vehicle and the vehicle overlap in a spatial area within a preset time period in the future. The first risk module 102 is used to determine the sideslip risk item based on the lateral velocity and the road surface adhesion coefficient; The second risk module 103 is used to determine the runaway acceleration risk item based on the lateral acceleration and the road surface adhesion coefficient; The third risk module 104 is used to determine the tail-slip risk item based on the lateral velocity and the heading angle deviation; The determination module 105 is used to determine the instability risk of the oncoming vehicle based on the sideslip risk item, the runaway acceleration risk item, and the drift-lateral shift risk item.

[0096] Example 3 Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing a computer program / instructions thereon, which, when executed by a processor, implements the oncoming vehicle instability risk assessment method as described in Embodiment 1 above.

[0097] Example 4 Based on the same inventive concept, embodiments of the present invention also provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the oncoming vehicle instability risk assessment method as described in Embodiment 1 above.

[0098] Example 5 Based on the same inventive concept, embodiments of the present invention also provide a computer device, including a memory, a processor, and a computer program stored in the memory. When the processor executes the computer program, it implements the method for assessing the instability risk of oncoming vehicles as described in Embodiment 1 above.

[0099] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0100] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0101] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0102] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0103] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for assessing the instability risk of oncoming vehicles, characterized in that, The method includes: If the trajectories of oncoming vehicles and other vehicles overlap in a spatial area within a preset time period in the future, the road surface adhesion coefficient, as well as the lateral velocity, lateral acceleration, and orientation angle deviation of the oncoming vehicles, are obtained. Based on the lateral velocity and the road surface adhesion coefficient, the sideslip risk item is determined; Based on the lateral acceleration and the road surface adhesion coefficient, the risk of runaway acceleration is determined; Based on the lateral velocity and the heading angle deviation, a tail-flip risk item is determined; The instability risk of the oncoming vehicle is determined based on the sideslip risk item, the runaway acceleration risk item, and the fishtail-side shift risk item.

2. The method according to claim 1, characterized in that, The determination of the drift-lateral risk term based on the lateral velocity and the heading angle deviation includes: Based on the absolute value of the lateral velocity and the preset lateral velocity limit value, a first normalized value of the lateral velocity is obtained; Based on the absolute value of the orientation angle deviation and the preset orientation angle deviation limit value, the normalized value of the orientation angle deviation is obtained; Based on the first normalized lateral velocity value and the normalized azimuth angle deviation value, the tail-slip risk term is obtained.

3. The method according to claim 1, characterized in that, The determination of sideslip risk items based on the lateral velocity and the road surface adhesion coefficient includes: Based on the lateral velocity and the preset lateral velocity limit value, a second normalized lateral velocity value is obtained; Based on the road surface adhesion coefficient and the baseline value of the adhesion coefficient, the normalized value of road surface adhesion is obtained; The sideslip risk term is obtained based on the second normalized lateral velocity value and the normalized road surface adhesion value.

4. The method according to claim 1, characterized in that, The determination of runaway acceleration risk items based on the lateral acceleration and the road surface adhesion coefficient includes: The runaway acceleration risk term is obtained based on the absolute value of the lateral acceleration, the road surface adhesion coefficient, and the standard gravitational acceleration.

5. The method according to claim 1, characterized in that, The determination of the instability risk of the oncoming vehicle based on the sideslip risk item, the runaway acceleration risk item, and the fishtail-lateral shift risk item includes: Determine the first weight value, the second weight value, and the third weight value corresponding to the sideslip risk item, the runaway acceleration risk item, and the tail-side slip risk item, respectively; Based on the first weight value, the second weight value, and the third weight value, the sideslip risk item, the runaway acceleration risk item, and the fishtail-side shift risk item are weighted and summed to obtain the instability risk of the oncoming vehicle.

6. The method according to claim 5, characterized in that, After determining the instability risk of the oncoming vehicle based on the sideslip risk item, the runaway acceleration risk item, and the fishtail-lateral shift risk item, the method further includes: Based on the first weight value, the second weight value, the third weight value, and the vehicle environmental parameters, determine the update of the first weight value, the update of the second weight value, and the update of the third weight value; Based on the updated first weight value, updated second weight value, and updated third weight value, the sideslip risk item, the runaway acceleration risk item, and the fishtail-side slip risk item are weighted and summed to obtain the dynamic instability risk of the oncoming vehicle. Based on the aforementioned instability risk and the aforementioned dynamic instability risk, an early warning strategy is determined.

7. The method according to claim 6, characterized in that, The vehicle environmental parameters include road surface adhesion coefficient, curve radius of curvature, relative speed between the oncoming vehicle and the vehicle, and road slope. The step of determining, updating the first weight value, updating the second weight value, and updating the third weight value based on the first weight value, the second weight value, the third weight value, and the vehicle environmental parameters includes: Based on the road surface adhesion coefficient, the curve radius of curvature, the relative speed, and the road slope, respectively determine the road surface adhesion coefficient correction factor, the curve radius of curvature correction factor, the relative speed correction factor, and the slope correction factor; Based on the road surface adhesion coefficient correction factor, the curve curvature radius correction factor, the relative speed correction factor, and the slope correction factor, the first weight value, the second weight value, and the third weight value are corrected respectively to obtain the updated first weight value, the updated second weight value, and the updated third weight value.

8. The method according to claim 6, characterized in that, The step of determining the early warning strategy based on the instability risk and the dynamic instability risk includes: Based on the dynamic instability risk, a first-level instability risk and a second-level instability risk are determined; wherein, the first-level instability risk is less than the second-level instability risk, and the second-level instability risk is less than the dynamic instability risk; If the instability risk is greater than or equal to the first-level instability risk, the vehicle instrument panel will display a warning icon. If the instability risk is greater than or equal to the secondary instability risk, the vehicle is controlled to output a voice alarm signal to suggest that the driver make slight adjustments to the lane position or reduce speed. If the instability risk is greater than or equal to the dynamic instability risk, then the vehicle is controlled to brake suddenly and reverse or change lanes to avoid a collision.

9. A device for assessing the instability risk of oncoming vehicles, characterized in that, include: The judgment module is used to obtain the road surface adhesion coefficient, the lateral velocity, lateral acceleration and orientation angle deviation of the oncoming vehicle if the driving trajectories of the oncoming vehicle and the vehicle overlap in a spatial area within a preset time period in the future. The first risk module is used to determine the sideslip risk item based on the lateral velocity and the road surface adhesion coefficient; The second risk module is used to determine the runaway acceleration risk item based on the lateral acceleration and the road surface adhesion coefficient; The third risk module is used to determine the tail-slip risk item based on the lateral velocity and the heading angle deviation; The determination module is used to determine the instability risk of the oncoming vehicle based on the sideslip risk item, the runaway acceleration risk item, and the drift-lateral shift risk item.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory. Its features are, The processor executes the computer program to implement the method for assessing the instability risk of oncoming vehicles as described in any one of claims 1-8.

Images