Vehicle active safety warning system and method based on multi-information fusion of human, vehicle and road

Abstract

The application discloses a kind of based on human vehicle road multi-information fusion automobile active safety early warning system and method, the system includes mutually connected information perception module, state monitoring module, threshold adjustment module, safety early warning module and active control module;Firstly, real-time vehicle state information is obtained by information perception module, state monitoring module is monitored real-time vehicle state information obtained, and each state index value is calculated and processed according to the vehicle state information obtained;Threshold adjustment module determines the safety threshold of each state index based on fuzzy control model according to current lane type and driver characteristics;Safety early warning module determines early warning level and corresponding early warning mode according to each state index and its safety threshold;Active control module intervenes and carries out active front wheel steering control after triggering a level safety early warning.The application improves overall driving safety by fusing multi-source information, reduces the accident rate, and has significant significance for improving road traffic safety.

Description

TECHNICAL FIELD

[0001] The present application relates to a car safety warning system and method, in particular to a car active safety warning system and method based on human-vehicle-road multi-information fusion, belonging to the field of advanced auxiliary driving control technology in intelligent vehicle control. BACKGROUND

[0002] Intelligent transportation systems (ITS) effectively integrate human, vehicle, and road resources through the fusion of advanced technologies, aiming to alleviate traffic congestion, reduce environmental pollution, and achieve efficient transportation. Vehicle driving assistance systems (DAS), as a key part of ITS, use sensors to monitor the driving environment, assess safety risks, and take control measures when necessary to prevent accidents, thereby enhancing vehicle intelligence and active safety. Given that most traffic accidents are caused by driver errors such as fatigue or inattentive driving, developing DAS can significantly reduce such accidents. Current research focuses on collision avoidance systems, lane changing assistance, lane keeping, adaptive cruise control (ACC), and pedestrian detection, among others. These systems can identify and warn potential risks in real time, prompting drivers to take safety actions. However, current vehicle warning systems often only consider single information, failing to fully consider multi-source information of human, vehicle, and road. When designing DAS, driver personality and vehicle characteristics need to be considered to enhance the adaptability and intelligence of the system. These studies not only accelerate the realization of intelligent driving but also effectively improve driving safety and reduce accident rates, which has significant implications for improving road traffic safety. SUMMARY

[0003] To solve the above problems, the present application proposes a car active safety warning system and method based on human-vehicle-road multi-information fusion, which improves overall driving safety by fusing multi-source information.

[0004] To achieve the above purpose, the specific technical solutions of the present application are as follows: a car active safety warning system based on human-vehicle-road multi-information fusion, comprising an information perception module, a state monitoring module, a threshold adjustment module, a safety warning module, and an active control module that are interconnected;

[0005] The information perception module, state monitoring module, threshold adjustment module, safety warning module, and active control module are integrated and installed in the central control unit area of the vehicle;

[0006] The information perception module is in communication connection with the state monitoring module and threshold adjustment module, and is used to obtain vehicle state information in real time;

[0007] The state monitoring module is in communication connection with the information perception module and safety warning module, and performs calculation and processing on the vehicle state information obtained by the information perception module, including three sub-modules of driver manipulation state monitoring, vehicle stability state monitoring, and lane keeping monitoring.

[0008] The threshold adjustment module is connected with the information perception module and the safety warning module, and determines the safety threshold of abnormal steering wheel angle input based on the fuzzy control model according to the current lane type and the driver characteristics sm The safety threshold of lane deviation time T am

[0009] The safety warning module is connected with the state monitoring module and the threshold adjustment module, and determines the warning level and the corresponding warning mode according to the state indicators obtained by the state monitoring module and the safety threshold obtained by the threshold adjustment module.

[0010] The active control module is connected with the safety warning module, and determines whether to intervene according to the judgment result of the safety warning module, and performs active front wheel steering control of the vehicle according to the current vehicle state to calculate the additional front wheel steering angle.

[0011] A method of an automobile active safety warning system based on human-vehicle-road multi-information fusion, comprising the following steps:

[0012] Step 1, obtaining vehicle state information in real time through the information perception module;

[0013] Step 2, the state monitoring module monitors the vehicle state information obtained in step 1 in real time, and calculates and processes the state indicator values according to the obtained vehicle state information;

[0014] Step 3, the threshold adjustment module determines the safety threshold of each state indicator based on the fuzzy control model according to the current lane type and the driver characteristics;

[0015] Step 4, the safety warning module determines the warning level and the corresponding warning mode according to each state indicator and its safety threshold;

[0016] Step 5, the active control module intervenes in the active front wheel steering control after triggering the first level safety warning.

[0017] Further, in step 1, the vehicle state information at least includes steering wheel angle, steering wheel angle rate, vehicle yaw angle, yaw angle velocity, lateral position, lateral velocity, longitudinal velocity and lateral acceleration.

[0018] Further, in step 2, the following specific steps are included,

[0019] Step 2.1, calculating the driver steering wheel angle abnormal input through the driver steering state monitoring sub-module, and the calculation formula is as follows:

[0020]

[0021] Where, δ sa ​is the actual steering wheel angle, is the actual steering wheel angle rate, δ sd is the ideal steering wheel angle, t s is the preset driver reaction time;

[0022] Step 2.2, the vehicle stability state criterion rear wheel side slip angle estimation value is calculated by the vehicle stability state monitoring sub-module to judge the vehicle yaw stability state, the specific calculation formula is as follows:

[0023]

[0024] Where ω r is the yaw rate, v y is the lateral velocity;

[0025] Step 2.3, the lane deviation time is calculated by the lane keeping monitoring sub-module, which refers to the time for the vehicle to travel from the current position to the outside wheel to touch the lane boundary line under the current driving state, and the specific calculation formula is as follows:

[0026]

[0027] Where a y is the lateral acceleration, d y is the lateral distance of the vehicle relative to the lane boundary.

[0028] Further, in step 2.1, the ideal steering wheel angle is obtained according to the ideal driver direction control model based on trajectory prediction, and the specific calculation formula is as follows:

[0029]

[0030] Where i w is the angle transmission ratio of steering wheel angle and front wheel angle, m is the mass of the vehicle, C f , C r is the front and rear tire equivalent cornering stiffness, l f , l r is the distance from the mass center of the vehicle to the front and rear axle, said i w , m, C f , C r , l f , l r are all inherent parameters of the vehicle, which can be measured and known in advance; β is the mass center side slip angle, v x is the longitudinal velocity, t p is the preset preview time, d p is the lateral deviation of the preview point from the lane center line, said β, v x , d pThe information perception module can acquire the information.

[0031] Further, in the step 3, the fuzzy control model is a double-input double-output model; the inputs are respectively a driver type Dr and a lane type Ro; the driver type is selected by the driver according to the driving habit of the driver, a universe U1 = [0, 1], and a fuzzy set M1 = (N1, Z1, P1) representing respectively that the driver type is “cautious, normal, and aggressive”; the lane type is acquired by the information perception module, a universe U2 = [0, 1], and a fuzzy set M2 = (N2, Z2, P2) representing respectively that the lane type is “low, medium, and high”; and the membership functions are all in the form of Gaussian functions.

[0032] The output is a safety threshold value Δδ of an abnormal input of a steering wheel rotation angle sm A safety threshold value T of a lane deviation time am , a universe U3 = [0, 10] of Δδ sm , a fuzzy set M3 = (N3, Z3, P3) of Δδ am , a universe U4 = [0.7, 2] of T am , and a fuzzy set M4 = (N4, Z4, P4) of T am , and the membership functions are all in the form of Gaussian functions.

[0033] The fuzzy reasoning rules of the fuzzy control model are shown in the following table:

[0034]

[0035] The fuzzy reasoning rules can also be expressed as the following fuzzy logic statements:

[0036] Rule 1: If Dr is N1 and Ro is N2, then Δδ sm is N3, and T am is N4.

[0037] Rule 2: If Dr is N1 and Ro is Z2, then Δδ sm is P3, and T am is P4.

[0038] Rule 3: If Dr is N1 and Ro is P2, then Δδ sm is P3, and T am is P4.

[0039] Rule 4: If Dr is Z1 and Ro is N2, then Δδ sm is N3, and T am is N4.

[0040] Rule 5: If Dr is Z1 and Ro is Z2, then Δδ sm is Z3, and Tam is Z4;

[0041] Rule 6: if Dr is Z1 and Ro is P2, then Δδ sm is P3, T am is P4;

[0042] Rule 7: if Dr is P1 and Ro is N2, then Δδ sm is N3, T am is N4;

[0043] Rule 8: if Dr is P1 and Ro is Z2, then Δδ sm is N3, T am is N4;

[0044] Rule 9: if Dr is P1 and Ro is P2, then Δδ sm is Z3, T am is Z4.

[0045] Further, in the step 4, the safety warning module determines the warning level and the corresponding warning mode according to the abnormal steering wheel angle input Δδ s , the vehicle yaw stability state α r , the lane deviation time T a and the safety threshold of the abnormal steering wheel angle input Δδ sm , the safety threshold of the vehicle stability state criterion rear side slip angle α rm and the safety threshold of the lane deviation time T am , the specific warning rules are as follows:

[0046] If Δδ s < Δδ sm , α r < α rm and T a < T am , no safety warning is triggered, the safety warning indicator light is green, no safety warning prompt sound, and the driver drives normally.

[0047] If Δδ s >= Δδ sm , α r < α rm and T a < T am , a three-level safety warning is triggered, the safety warning indicator light is yellow, and no safety warning prompt sound is given.

[0048] If α rm <= α r < 1.2* α rm or T am <= Ta <1.2*T am , then a secondary safety warning is triggered, the safety warning indicator light is displayed as yellow, and the warning system emits a low-frequency safety warning prompt sound;

[0049] If 1.2*alpha rm <= alpha r or 1.2*T am <= T a , then a primary safety warning is triggered, the safety warning indicator light is displayed as red, and the warning system emits a high-frequency safety warning prompt sound, and the active control module intervenes in control.

[0050] Further, in step 5, when the warning level judgment result is after triggering the primary safety warning, the active control module intervenes in control, and vehicle active front wheel steering control is performed according to the current vehicle state to calculate an additional front wheel steering angle.

[0051] The additional front wheel steering angle is obtained by using an active front wheel steering control algorithm based on a sliding mode control, and the specific steps are as follows:

[0052] Step 5.1, a vehicle yaw dynamics model is established:

[0053]

[0054] Wherein I z is the yaw moment of inertia, d is a system unknown disturbance and |d|<D;

[0055] Step 5.2, an ideal yaw angular velocity is determined:

[0056]

[0057] Step 5.3, a non-singular integral terminal sliding mode surface is designed:

[0058]

[0059] Wherein e(t)=omega r -omega rref , controller parameters mu1>0, mu2>0, and 0<lambda<1;

[0060] Step 5.4, an additional front wheel steering angle control law is determined:

[0061]

[0062] Wherein controller parameter epsilon d >D.

[0063] Compared with the prior art, the present application has the following beneficial effects:

[0064] 1、By fusing multi-source information, the system can more accurately judge potential safety risks, and compared with the early warning system of a single information source, the false positive rate and the false negative rate are reduced. This accurate early warning can help the driver to react in time, so as to avoid or reduce the occurrence of accidents;

[0065] 2、The method can automatically adjust the early warning strategy according to the current driving situation, and improve the adaptability of the method. Through real-time analysis of comprehensive information, the algorithm can identify potential dangers earlier and issue early warnings to the driver, providing more reaction time for the driver;

[0066] 3、Long-term use of the active safety early warning system with human-vehicle-road multi-information fusion can help the driver to identify and correct unsafe driving habits, thereby improving the overall driving safety. BRIEF DESCRIPTION OF DRAWINGS

[0067] Figure 1 The flowchart of the present application.

[0068] Figure 2 The driver direction control model based on trajectory prediction of the present application.

[0069] Figure 3 The safety early warning module flowchart of the present application.

[0070] Figure 4 The active control module flowchart of the present application.

[0071] Figure 5 The module connection diagram of the present application. DETAILED DESCRIPTION

[0072] In order to make the personnel in the technical field better understand the scheme of the embodiments of the present application, the present application examples are further described in detail below in combination with the drawings and specific embodiments.

[0073] The present embodiment proposes an automobile active safety early warning system based on human-vehicle-road multi-information fusion, such as Figure 5As shown, including information perception module, state monitoring module, threshold adjustment module, safety warning module and active control module. The information perception module, state monitoring module, threshold adjustment module, safety warning module and active control module are integrated and installed in the central control unit area of the vehicle. Among them, the information perception module is in communication connection with the state monitoring module and the threshold adjustment module, and is used for acquiring vehicle state information in real time; the state monitoring module is in communication connection with the information perception module and the safety warning module, and calculates and processes the vehicle state information acquired by the information perception module, including three sub-modules of driver steering state monitoring, vehicle stability state monitoring and lane keeping monitoring. The threshold adjustment module is connected with the information perception module and the safety warning module, and determines the safety threshold Δδ sm of abnormal input of steering wheel angle based on the current lane type and the driver characteristics and the fuzzy control model am The safety warning module is connected with the state monitoring module and the threshold adjustment module, and determines the warning level and the corresponding warning mode according to the state indicators acquired by the state monitoring module and the safety threshold acquired by the threshold adjustment module. The active control module is connected with the safety warning module, determines whether to intervene according to the judgment result of the safety warning module, and performs active front wheel steering control of the vehicle according to the current vehicle state to calculate the additional front wheel angle.

[0074] The embodiment also proposes an early warning method of an automobile active safety warning system based on multi-information fusion of human-vehicle-road, and the specific steps are as follows Figure 1 As shown, including:

[0075] Step 1), the information perception module acquires vehicle state information including steering wheel angle, steering wheel angle rate, vehicle yaw angle, yaw angle velocity, lateral position, lateral velocity, longitudinal velocity and lateral acceleration in real time;

[0076] Step 2), the state monitoring module calculates and processes the vehicle state information acquired by the information perception module, including three sub-modules of driver steering state monitoring, vehicle stability state monitoring and lane keeping monitoring, and specifically includes the following steps:

[0077] Step 2.1), the driver steering state monitoring sub-module in the state monitoring module calculates the abnormal input of the driver steering wheel angle, and the calculation formula is as follows:

[0078]

[0079] Where δ sa is the actual steering wheel angle, is the actual steering wheel angle rate, δ sd is the ideal steering wheel angle, t sFor the preset driver reaction time, the ideal steering wheel angle is obtained according to an ideal driver steering control model based on trajectory prediction as shown in the formula below: Figure 2

[0080]

[0081] i w is an angle transmission ratio of the steering wheel angle and the front wheel angle, m is the mass of the vehicle, C f , C r are equivalent cornering stiffness of front and rear tires, l f , l r are distances from the mass center of the vehicle to front and rear axles, the i w , m, C f , C r , l f , l r are all inherent parameters of the vehicle and can be measured and obtained in advance; β is a mass center cornering angle, v x is a longitudinal speed, t p is a preset preview time, d p is a lateral deviation of the preview point from the center line of the lane, and the β, v x , d p can be obtained by an information sensing module.

[0082] Step 2.2) The vehicle stability state monitoring sub-module in the state monitoring module calculates a vehicle stability state criterion rear wheel cornering angle estimation value to judge the vehicle yaw stability state, and the specific calculation formula is as follows:

[0083]

[0084] where ω r is a yaw angular velocity, and v y is a lateral speed.

[0085] Step 2.3) The lane keeping monitoring sub-module in the state monitoring module calculates a lane deviation time, which is a time for the vehicle to travel from the current position to the outside wheel touching the lane boundary line under the current driving state, and the specific calculation formula is as follows:

[0086]

[0087] where a y is a lateral acceleration, and d y is a lateral distance of the vehicle relative to the lane boundary.

[0088] ​​Step 3): The threshold adjustment module determines the safety threshold Δδ for the abnormal steering wheel angle input in Step 2) based on the current lane type and driver characteristics, using the designed fuzzy control model. sm Safety threshold T for lane departure time am In step 2), the safety threshold α of the rear wheel sideslip angle is used as a criterion for determining vehicle stability. rm Set to a fixed value.

[0089] The fuzzy control model is a dual-input, dual-output model. The inputs are driver type Dr and lane type Ro. The driver type is selected by the driver based on their driving habits, with a design universe of discourse U1 = [0, 1] and a design fuzzy set M1 = (N, Z, P) representing the driver's driving type as "cautious," "normal," and "aggressive," respectively. The lane type is obtained by the information perception module, with a design universe of discourse U2 = [0, 1] and a design fuzzy set M2 = (N, Z, P) representing the lane level as "low," "medium," and "high," respectively. The membership functions are all in Gaussian form.

[0090] The fuzzy control model outputs the safety threshold for abnormal steering wheel angle input and the safety threshold for lane departure time T. am Design Δδ sm The universe of discourse U3 = [0, 10] is given, and a fuzzy set M3 = (N, Z, P) is designed to represent the abnormal input values ​​of "small", "medium", and "large" for the steering wheel angle, respectively; T is designed... am The universe of discourse U4 = [0.7, 2] is designed, and the fuzzy set M1 = (N, Z, P) is designed to represent the abnormal input of steering wheel angle as "small, medium, large" respectively; the membership function is Gaussian function.

[0091] The fuzzy inference rules of the fuzzy control model are shown in Table 1:

[0092]

[0093] Step 4), the safety early warning module calculates Δδ based on the value in step 2). s α r With T a And the Δδ calculated in step 3) sm α rm With T am Determine the warning level and corresponding warning method, such as Figure 3 As shown, the specific warning rules are as follows:

[0094] If Δδ s <Δδ sm And α r <α rm And T a <T amNo safety warning is triggered, the safety warning indicator light is green, and there is no safety warning prompt sound, and the driver drives normally.

[0095] If Δδ s >=Δδ sm and α r <α rm and T a <T am , a three-level safety warning is triggered, the safety warning indicator light is yellow, and there is no safety warning prompt sound.

[0096] If α rm <=α r <1.2*α rm or T am <=T a <1.2*T am , a two-level safety warning is triggered, the safety warning indicator light is yellow, and the warning system emits a low-frequency safety warning prompt sound.

[0097] If 1.2*α rm <=α r or 1.2*T am <=T a , a one-level safety warning is triggered, the safety warning indicator light is red, the warning system emits a high-frequency safety warning prompt sound, and the active control module intervenes in control.

[0098] Step 5), the active control module intervenes in control according to the warning level judgment result in step 4) after triggering a one-level safety warning, performs vehicle active front wheel steering control according to the current vehicle state, and calculates an additional front wheel steering angle.

[0099] The additional front wheel steering angle is obtained by using an active front wheel steering control algorithm based on a sliding mode control, as shown in FIG. 5, and the specific steps are as follows: Figure 4

[0100] Step 5.1), a vehicle yaw dynamics model is established:

[0101]

[0102] wherein I z is the yaw moment of inertia, and d is a system unknown disturbance and |d|<D.

[0103] Step 5.2), an ideal yaw angular velocity is determined:

[0104]

[0105] wherein δ sd is the ideal steering wheel steering angle determined in step 2.1).​

[0106] Step 5.3), design nonsingular integral terminal sliding mode surface:

[0107]

[0108] where e(t) = ω r -ω rref , controller parameters μ1>0, μ2>0, 0<λ<1.

[0109] Step 5.4), determine additional front wheel steering control law:

[0110]

[0111] where controller parameter ε d >D, it is easy to prove that the above control law can guarantee the stability of the closed-loop system.

[0112] Those skilled in the art should understand that the present application is not limited to the above specific embodiments, and various changes and improvements can be made to the present application, which all fall within the scope of the claimed present application.

Claims

1. A method for an active safety warning system for automobiles based on the fusion of human, vehicle, and road information, characterized by: The system includes interconnected information sensing modules, status monitoring modules, threshold adjustment modules, safety early warning modules, and active control modules; The information perception module, status monitoring module, threshold adjustment module, safety warning module, and active control module are integrated and installed in the central control unit area of ​​the vehicle. The information sensing module is communicatively connected to the status monitoring module and the threshold adjustment module to acquire vehicle status information in real time. The status monitoring module is communicatively connected to the information perception module and the safety warning module, and performs calculation and processing on the vehicle status information acquired by the information perception module. It includes three sub-modules: driver operation status monitoring, vehicle stability status monitoring, and lane keeping monitoring. The threshold adjustment module is connected to the information perception module and the safety warning module. Based on the current lane type and driver characteristics, it determines the safety threshold Δδ for abnormal steering wheel angle input using a fuzzy control model. sm Safety threshold T for lane departure time am ; The safety early warning module is connected to the status monitoring module and the threshold adjustment module. It determines the early warning level and the corresponding early warning method based on the status indicators obtained by the status monitoring module and the safety threshold obtained by the threshold adjustment module. The active control module is connected to the safety warning module. It decides whether to intervene based on the judgment result of the safety warning module, and performs active front wheel steering control of the vehicle based on the current vehicle status, and calculates and generates additional front wheel steering angle. The method includes the following steps: Step 1: Obtain vehicle status information in real time through the information sensing module; Step 2: The status monitoring module monitors the vehicle status information obtained in Step 1 in real time, and calculates and processes the values ​​of each status indicator based on the obtained vehicle status information. Step 2.1: The abnormal input of the driver's steering wheel angle is calculated by the driver operation status monitoring submodule. The calculation formula is as follows: Where, δ sa This refers to the actual steering wheel angle. δ is the actual steering wheel angular rate. sd For the ideal steering wheel angle, t s This is the preset driver reaction time; Step 2.2: The estimated value of the rear wheel slip angle, a criterion for determining vehicle stability, is calculated using the vehicle stability state monitoring submodule to determine the vehicle's yaw stability state. The specific calculation formula is as follows: Where ω r v is the yaw rate. y For lateral velocity; Step 2.3: Calculate the lane departure time using the lane keeping monitoring submodule. The lane departure time refers to the time from when the vehicle is traveling in its current driving state from its current position until the outer wheel touches the lane boundary line. The specific calculation formula is as follows: Where a y For lateral acceleration, d y This represents the lateral distance of the vehicle relative to the lane boundary. Step 3: The threshold adjustment module determines the safety thresholds for each state indicator based on the current lane type and driver characteristics using a fuzzy control model. The fuzzy control model is a dual-input, dual-output model. The inputs are the driver type Dr and the lane type Ro, respectively. The driver type is selected by the driver based on their driving habits, with a universe of discourse U1 = [0, 1] and a fuzzy set M1 = (N1, Z1, P1), representing the driver's driving type as "cautious," "normal," and "aggressive," respectively. The lane type is obtained by the information perception module, with a universe of discourse U2 = [0, 1] and a fuzzy set M2 = (N2, Z2, P2), representing the lane level as "low," "medium," and "high," respectively. The membership functions all adopt the Gaussian function form. The output is the safety threshold Δδ for abnormal steering wheel angle input. sm Safety threshold T for lane departure time am ,Δδ sm The universe of discourse U3 = [0, 10], and the fuzzy set M3 = (N3, Z3, P3) represent the abnormal input values ​​of "small", "medium", and "large" for the steering wheel angle, respectively; T am The universe of discourse U4 = [0.7, 2], and the fuzzy set M4 = (N4, Z4, P4) represent the abnormal input of steering wheel angle as "small, medium, large" respectively; the membership functions are all in Gaussian form. Step 4: The safety early warning module determines the early warning level and corresponding early warning method based on each status indicator and its safety threshold. Step 5: After triggering the Level 1 safety warning, the active control module intervenes to perform active front wheel steering control.

2. The vehicle active safety early warning method based on multi-information fusion of people, vehicles, and roads according to claim 1, characterized in that: In step 1, the vehicle status information includes at least the steering wheel angle, steering wheel angle rate, vehicle yaw angle, yaw rate, lateral position, lateral velocity, longitudinal velocity, and lateral acceleration.

3. The vehicle active safety early warning method based on the fusion of human, vehicle, and road information according to claim 1, characterized in that: In step 2.1, the ideal steering wheel angle is obtained based on the ideal driver direction control model based on trajectory prediction, and the specific calculation formula is as follows: in i w The angular ratio is the steering wheel angle and the front wheel angle, where m is the vehicle mass and C is the angular ratio. f C r For the equivalent lateral stiffness of the front and rear tires, l f l r The distance from the vehicle's center of gravity to the front and rear axles, i w m, C f C r l f l r These are all inherent parameters of the vehicle and can be measured and known in advance; β is the sideslip angle, v x Let t be the longitudinal velocity. p For the preset aiming time, d p The lateral deviation between the aiming point and the lane centerline, β, v x d p It can be obtained through the information sensing module.

4. The vehicle active safety early warning method based on multi-information fusion of people, vehicles, and roads according to claim 1, characterized in that: The fuzzy inference rules of the fuzzy control model are expressed as the following fuzzy logic statements: Rule 1: If Dr is N1 and Ro is N2, then Δδ sm For N3, T am It is N4; Rule 2: If Dr is N1 and Ro is Z2, then Δδ sm For P3, T am P4; Rule 3: If Dr is N1 and Ro is P2, then Δδ sm For P3, T am P4; Rule 4: If Dr is Z1 and Ro is N2, then Δδ sm For N3, T am It is N4; Rule 5: If Dr is Z1 and Ro is Z2, then Δδ sm For Z3, T am Z4; Rule 6: If Dr is Z1 and Ro is P2, then Δδ sm For P3, T am P4; Rule 7: If Dr is P1 and Ro is N2, then Δδ sm For N3, T am It is N4; Rule 8: If Dr is P1 and Ro is Z2, then Δδ sm For N3, T am It is N4; Rule 9: If Dr is P1 and Ro is P2, then Δδ sm For Z3, T am It is Z4.

5. The vehicle active safety early warning method based on multi-information fusion of people, vehicles, and roads according to claim 1, characterized in that: In step 4, the safety warning module inputs Δδ based on the abnormal steering wheel angle of the driver obtained in step 2. s Vehicle yaw stability state α r Lane departure time T a and the safety threshold Δδ obtained in step 3 for abnormal steering wheel angle input. sm Vehicle stability criterion: safety threshold α for rear wheel slip angle rm Safety threshold T for lane departure time am Determine the warning level and corresponding warning method, and use the safe threshold α of the rear wheel sideslip angle as the criterion for judging vehicle stability. rm Set as a fixed value, the specific early warning rules are as follows: If Δδ s <Δδ sm And α r <α rm And T a <T am If the safety warning is not triggered, the safety warning indicator light will be green, there will be no safety warning sound, and the driver can drive normally. If Δδ s >=Δδ sm And α r <α rm And T a <T am If this occurs, a Level 3 safety warning will be triggered, the safety warning indicator light will turn yellow, and there will be no safety warning sound. If α rm <= α r <1.2*α rm or T am <=T a <1.2*T am If this occurs, a level two safety warning will be triggered, the safety warning indicator light will turn yellow, and the warning system will emit a low-frequency safety warning sound. If 1.2*α rm <= α r Or 1.2*T am <=T a If the situation is triggered, a Level 1 safety warning will be activated, the safety warning indicator light will turn red, the warning system will emit a high-frequency safety warning sound, and the active control module will intervene.

6. The vehicle active safety early warning method based on multi-information fusion of people, vehicles, and roads according to claim 1, characterized in that: In step 5, when the warning level judgment result triggers a level 1 safety warning, the active control module intervenes and performs active front wheel steering control based on the current vehicle status, and calculates and generates an additional front wheel steering angle. The additional front wheel steering angle is obtained using an active front wheel steering control algorithm based on sliding mode control. The specific steps are as follows: Step 5.1, establish the vehicle yaw dynamics model: in I z Let be the yaw moment of inertia, d be an unknown disturbance of the system, and |d| <D; Step 5.2, determine the ideal yaw rate: Step 5.3, Design the non-singular integral terminal sliding surface: Where e(t) = ω r -ω rref The controller parameters are μ1 > 0, μ2 > 0, and 0 < λ < 1. Step 5.4, determine the additional front wheel steering angle control law: Where the controller parameter ε d >D.

Images