Vehicle rearward driving warning method and device, electronic equipment and readable storage medium

Abstract

The application discloses a vehicle rearward driving warning method and device, electronic equipment and a readable storage medium, and relates to the technical field of vehicle control. The vehicle rearward driving warning method comprises the following steps: judging whether a current environment meets a first preset scene; when the current environment meets the first preset scene, estimating driving states of a target vehicle and a rear vehicle to obtain a driving state of the vehicle and a driving state of the rear vehicle; if the current environment meets the first preset scene and a second preset scene at the same time, determining a rear vehicle risk value according to the driving state of the vehicle and the driving state of the rear vehicle; and if the rear vehicle risk value exceeds a warning threshold, issuing a warning prompt to the rear vehicle. The application solves the technical problem that the existing overtaking risk prompt method is highly dependent on the subjective judgment of the driver.

Description

Technical Field

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

[0002] In high-speed driving scenarios, numerous safety accidents occur during overtaking and passing maneuvers. Analysis of these accidents reveals several contributing factors, including blind spots (failure to detect oncoming vehicles or obstacles in the target lane) and excessive speed. Overtaking maneuvers under these conditions are more likely to result in accidents. Further analysis of successful overtaking or passing incidents shows that canceling some overtaking maneuvers reduces the likelihood of accidents. If the driver of the vehicle being overtaken can promptly recognize the overtaking intention of the vehicle behind them and assess the potential risks of the overtaking maneuver in light of their lights, they can avoid accidents caused by overtaking. However, successfully recognizing the intention of the vehicle behind, assessing the risks based on the current driving environment, and alerting the driver requires extensive driving experience and relies heavily on the driver's subjective judgment, making it difficult to apply universally in practice. Summary of the Invention

[0003] The main purpose of this application is to provide a vehicle rear driving warning method, which aims to solve the technical problem that existing overtaking risk warning methods rely heavily on the driver's subjective judgment.

[0004] To achieve the above objectives, in a first aspect, this application provides a vehicle rear-view warning method, the vehicle rear-view warning method comprising:

[0005] Identify the current environment of the target vehicle and determine whether the current environment matches a first preset scenario;

[0006] When the current environment matches the first preset scenario, the driving status of the target vehicle and the vehicle behind is estimated to obtain the driving status of the vehicle and the driving status of the vehicle behind.

[0007] If the current environment simultaneously meets the first preset scenario and the second preset scenario, then the risk value of the following vehicle is determined based on the driving status of the current vehicle and the driving status of the following vehicle, wherein the risk level of the second preset scenario is greater than the risk level of the first preset scenario;

[0008] If the risk value of the following vehicle exceeds the warning threshold, a warning message will be issued to the following vehicle.

[0009] According to the first aspect, the step of identifying the current environment of the target vehicle and determining whether the current environment conforms to the first preset scenario includes:

[0010] Identify the road type, lane type, and road conditions of the target vehicle;

[0011] If the target vehicle is located on a road of a preset type, in a non-overtaking lane, and there are obstacles or vehicles ahead, then it is determined that the first preset scenario is met.

[0012] According to the first aspect, the driving state of the vehicle includes the driving trajectory of the vehicle and the driver's state, and the driving state of the following vehicle includes the lateral behavior boundary and the longitudinal behavior boundary;

[0013] The step of estimating the driving states of the target vehicle and the vehicles behind to obtain the driving states of the vehicle itself and the vehicles behind includes:

[0014] The driving trajectory of the target vehicle is estimated to obtain the driving trajectory of the current vehicle;

[0015] Monitor the driver's status based on the action information fed back to the target vehicle by the driver;

[0016] A motion model is established based on the motion state of the vehicle behind, and the lateral and longitudinal behavioral boundaries of the vehicle behind are determined based on the motion model.

[0017] According to the first aspect, or any implementation of the first aspect above, the step of establishing a motion model based on the motion state of the rear vehicle, and determining the lateral and longitudinal behavioral boundaries of the rear vehicle based on the motion model, includes:

[0018] Identify the vehicle type, yaw rate, lateral acceleration, and motion state of the vehicle behind;

[0019] Based on the motion state of the vehicle behind, establish a motion model of the vehicle behind;

[0020] Based on the motion model, the lateral behavior boundary of the following vehicle is determined according to the vehicle type, yaw rate, and lateral acceleration of the following vehicle.

[0021] Based on the motion model, the longitudinal behavior boundary of the following vehicle is determined according to the longitudinal acceleration model of the following vehicle and the maximum acceleration, maximum impact, minimum acceleration and minimum impact corresponding to the vehicle type.

[0022] According to the first aspect, or any implementation of the first aspect above, the following vehicle risk value includes a lateral request value and a longitudinal request value, and the step of determining the following vehicle risk value based on the driving state of the current vehicle and the driving state of the following vehicle includes:

[0023] Based on the driving status of the target vehicle and the driving status of the vehicle behind it, a common coordinate system is established for the target vehicle and the vehicle behind it.

[0024] Based on the common coordinate system, the lateral request value is calculated according to the vehicle's driving state, the lateral behavior boundary, and the preset lateral obstacle avoidance objective function.

[0025] Based on the common coordinate system, the longitudinal request value is calculated according to the vehicle's driving state, the longitudinal behavior boundary, and the preset longitudinal obstacle avoidance objective function.

[0026] According to the first aspect, or any implementation of the first aspect above, before the step of determining the risk value of the following vehicle based on the driving state of the current vehicle and the driving state of the following vehicle if the current environment simultaneously meets the first preset scenario and the second preset scenario, the method further includes:

[0027] The scene in which the target vehicle is located is identified to determine whether the target vehicle is in a first warning scene, a second warning scene, or an intervention and protection scene. In the first warning scene, there is a vehicle traveling in the same direction ahead in the overtaking lane or a vehicle approaching in both lanes and a vehicle behind intends to overtake. In the second warning scene, in addition to the first warning scene, there is a vehicle ahead in the lane in which the target vehicle is located. In the intervention and protection scene, in addition to the first warning scene, there is no vehicle ahead in the lane in which the target vehicle is located.

[0028] If the target vehicle is in one or more of the first warning scenario, the second warning scenario, and the intervention protection scenario, then it is determined that the environment in which the target vehicle is located conforms to the second preset scenario.

[0029] According to the first aspect, or any implementation of the first aspect above, the step of issuing a warning to the following vehicle if the risk value of the following vehicle exceeds the warning threshold includes:

[0030] When the lateral request value or the longitudinal request value is higher than its respective warning threshold, a warning signal is issued to the vehicle behind via lights.

[0031] If the target vehicle is in the intervention protection scenario, the intervention torque of the target vehicle is calculated based on the lateral request value and the longitudinal request value;

[0032] The target vehicle is controlled based on the intervention torque.

[0033] Secondly, this application provides a vehicle rear-view warning device, the vehicle rear-view warning device comprising:

[0034] The scene recognition module is used to identify the current environment of the target vehicle and determine whether the current environment matches the first preset scene.

[0035] The state estimation module is used to estimate the driving state of the target vehicle and the vehicle behind when the current environment matches the first preset scenario, so as to obtain the driving state of the vehicle itself and the driving state of the vehicle behind.

[0036] The risk calculation module is used to determine the risk value of the following vehicle based on the driving status of the current vehicle and the driving status of the following vehicle if the current environment simultaneously meets the first preset scenario and the second preset scenario.

[0037] The early warning module is used to issue an early warning to the following vehicle if the risk value of the following vehicle exceeds the early warning threshold.

[0038] According to the second aspect, the scene recognition module is also used for:

[0039] Identify the road type, lane type, and road conditions of the target vehicle;

[0040] If the target vehicle is located on a road of a preset type, in a non-overtaking lane, and there are obstacles or vehicles ahead, then it is determined that the first preset scenario is met.

[0041] According to the second aspect, the vehicle's driving state includes the vehicle's driving trajectory and the driver's state, and the following vehicle's driving state includes lateral behavior boundaries and longitudinal behavior boundaries. The state estimation module is further used for:

[0042] The driving trajectory of the target vehicle is estimated to obtain the driving trajectory of the current vehicle;

[0043] Monitor the driver's status based on the action information fed back to the target vehicle by the driver;

[0044] A motion model is established based on the motion state of the vehicle behind, and the lateral and longitudinal behavioral boundaries of the vehicle behind are determined based on the motion model.

[0045] According to the second aspect, or any implementation of the second aspect above, the state estimation module is also used for:

[0046] Identify the vehicle type, yaw rate, lateral acceleration, and motion state of the vehicle behind;

[0047] Based on the motion state of the vehicle behind, establish a motion model of the vehicle behind;

[0048] Based on the motion model, the lateral behavior boundary of the following vehicle is determined according to the vehicle type, yaw rate, and lateral acceleration of the following vehicle.

[0049] Based on the motion model, the longitudinal behavior boundary of the following vehicle is determined according to the longitudinal acceleration model of the following vehicle and the maximum acceleration, maximum impact, minimum acceleration and minimum impact corresponding to the vehicle type.

[0050] According to the second aspect, or any implementation of the second aspect above, the risk calculation module is also used for:

[0051] Based on the driving status of the target vehicle and the driving status of the vehicle behind it, a common coordinate system is established for the target vehicle and the vehicle behind it.

[0052] Based on the common coordinate system, the lateral request value is calculated according to the vehicle's driving state, the lateral behavior boundary, and the preset lateral obstacle avoidance objective function.

[0053] Based on the common coordinate system, the longitudinal request value is calculated according to the vehicle's driving state, the longitudinal behavior boundary, and the preset longitudinal obstacle avoidance objective function.

[0054] According to the second aspect, or any implementation of the second aspect above, the risk calculation module is also used for:

[0055] The scene in which the target vehicle is located is identified to determine whether the target vehicle is in a first warning scene, a second warning scene, or an intervention and protection scene. In the first warning scene, there is a vehicle traveling in the same direction ahead in the overtaking lane or a vehicle approaching in both lanes and a vehicle behind intends to overtake. In the second warning scene, in addition to the first warning scene, there is a vehicle ahead in the lane in which the target vehicle is located. In the intervention and protection scene, in addition to the first warning scene, there is no vehicle ahead in the lane in which the target vehicle is located.

[0056] If the target vehicle is in one or more of the first warning scenario, the second warning scenario, and the intervention protection scenario, then it is determined that the environment in which the target vehicle is located conforms to the second preset scenario.

[0057] According to the second aspect, or any implementation of the second aspect above, the early warning module is also used for:

[0058] When the lateral request value or the longitudinal request value is higher than its respective warning threshold, a warning signal is issued to the vehicle behind via lights.

[0059] If the target vehicle is in the intervention protection scenario, the intervention torque of the target vehicle is calculated based on the lateral request value and the longitudinal request value;

[0060] The target vehicle is controlled based on the intervention torque.

[0061] Thirdly, this application provides a vehicle rear-end collision warning device, which includes a memory and a processor. The memory stores a computer program that can run on the processor, and the computer program is configured to implement the steps of the vehicle rear-end collision warning method as described above.

[0062] The third aspect and any implementation thereof correspond to the first aspect and any implementation thereof, respectively. The technical effects of the third aspect and any implementation thereof are similar to those of the first aspect and any implementation thereof, and will not be repeated here.

[0063] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the vehicle rear-end collision warning method as described in any one of the first aspects or possible implementations of the first aspect.

[0064] The fourth aspect and any implementation thereof correspond to the first aspect and any implementation thereof, respectively. The technical effects of the fourth aspect and any implementation thereof are similar to those of the first aspect and any implementation thereof, and will not be repeated here.

[0065] Fifthly, embodiments of this application provide a computer program including instructions for executing the vehicle rear-end traffic warning method in the first aspect and any possible implementation thereof.

[0066] The fifth aspect and any implementation thereof correspond to the first aspect and any implementation thereof, respectively. The technical effects of the fifth aspect and any implementation thereof are similar to those of the first aspect and any implementation thereof, and will not be repeated here.

[0067] This application proposes a vehicle rear-view warning method, device, equipment, and readable storage medium. First, the current environment of the target vehicle is identified, and it is determined whether the current environment conforms to a first preset scenario. When the current environment conforms to the first preset scenario, the driving states of the target vehicle and the vehicles behind it are estimated to obtain the driving states of the target vehicle and the vehicles behind it. If the current environment conforms to both the first and second preset scenarios, a rear-view risk value is determined based on the driving states of the target vehicle and the vehicles behind it. The risk level of the second preset scenario is greater than the risk level of the first preset scenario. If the rear-view risk value exceeds a warning threshold... If the risk value is reached, a warning is issued to the vehicle behind. The technical solution of this application further executes the warning by identifying the environment and calculating the risk value of the following vehicle. This allows the system to automatically issue a warning to the driver of the following vehicle who intends to overtake, even when the target vehicle has reached the preset warning threshold risk level, even if the driver does not have extensive driving experience. This improves the automation of warnings in driving scenarios and solves the technical problem that existing overtaking risk warning methods rely heavily on the driver's subjective judgment. This makes the rearward driving warning method in this technical solution widely applicable to various vehicles, especially heavy vehicles, and has the beneficial effect of improving driving safety. Attached Figure Description

[0068] Figure 1 This is a flowchart illustrating the first embodiment of the vehicle rear-end collision warning method of this application;

[0069] Figure 2 This is a schematic diagram of the motion model of a rear vehicle in an embodiment of this application;

[0070] Figure 3 This is a statistical graph showing the relationship between time and steering wheel angle for a driver steering behavior constraint in an embodiment of this application.

[0071] Figure 4 This is a statistical graph of vehicle longitudinal behavior constraints with respect to time and longitudinal acceleration, as shown in an embodiment of this application.

[0072] Figure 5 This is a schematic diagram of the common coordinate system of the target vehicle and the vehicles behind it in the embodiments of this application;

[0073] Figure 6 This is a schematic diagram of the geometric modeling of the rear vehicle in the embodiment of this application;

[0074] Figure 7 This is a flowchart illustrating the inventive concept structure of one embodiment of the present application;

[0075] Figure 8 These are schematic diagrams of various scenarios in the embodiments of this application;

[0076] Figure 9 This is a schematic diagram of the rear-view warning device for the vehicle in this application.

[0077] Figure 10 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application.

[0078] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0079] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0080] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0081] The terms "first" and "second," etc., used in the specification and claims of this application are used to distinguish different objects, not to describe a specific order of objects. For example, "first target object" and "second target object," etc., are used to distinguish different target objects, not to describe a specific order of target objects.

[0082] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0083] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0084] In one embodiment of this application, the current environment of the target vehicle is first identified, and it is determined whether the current environment conforms to a first preset scenario. When the current environment conforms to the first preset scenario, the driving states of the target vehicle and the following vehicle are estimated to obtain the driving state of the target vehicle and the driving state of the following vehicle. If the current environment conforms to both the first and second preset scenarios, the risk value of the following vehicle is determined based on the driving state of the target vehicle and the driving state of the following vehicle. The risk level of the second preset scenario is greater than that of the first preset scenario. If the risk value of the following vehicle exceeds a warning threshold, a warning is issued to the following vehicle. The technical solution of this application further executes the warning by identifying the environment and calculating the risk value of the following vehicle. This allows the target vehicle to automatically issue a warning to the driver of the following vehicle intending to overtake when the target vehicle reaches the preset warning threshold risk level, even if the driver does not have extensive driving experience. This improves the automation of warnings in driving scenarios, solves the technical problem that existing overtaking risk warning methods rely heavily on the driver's subjective judgment, and improves driving safety.

[0085] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the vehicle rear-view warning method of this application. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0086] The first embodiment of this application provides a vehicle rear-view warning method, which includes the following steps:

[0087] Step S100: Identify the current environment of the target vehicle and determine whether the current environment conforms to the first preset scenario;

[0088] In this embodiment, it should be noted that the target vehicle is the vehicle itself. The target vehicle is equipped with a road recognition module. The road recognition module can collect image information of the current environment through cameras installed in various directions and analyze it to determine whether it meets the preset scenario. The first preset scenario is a manually preset scenario, which belongs to a driving scenario with certain driving risks. Therefore, it is necessary to further estimate the driving status of the vehicle and the following vehicles. In a feasible embodiment, the first preset scenario may include scenarios such as the target vehicle driving at a speed of 60 kph or higher in suburban areas (i.e., highways), in a non-overtaking lane (there is a need to identify whether the following vehicle intends to overtake), and whether there are obstacles or other vehicles ahead. It can be customized according to the target vehicle's common driving scenarios.

[0089] In one feasible embodiment, since heavy vehicles have a high chassis and good visibility, they can see traffic conditions more clearly beyond a visual distance of 200m. Therefore, they can accurately assess the current overtaking risk by combining road condition information over a wider range. Thus, the target vehicle can be a heavy vehicle. Compared with other vehicles, applying the technical solution of this application embodiment to a heavy vehicle can achieve a better early warning effect and further improve the safety of following vehicles when they are overtaking in driving scenarios.

[0090] The step of identifying the current environment of the target vehicle and determining whether the current environment matches the first preset scenario may include:

[0091] Step S110: Identify the road type, lane type, and road conditions of the road where the target vehicle is located;

[0092] Step S120: If the target vehicle is located on a road of a preset type, in a lane that is a non-overtaking lane, and there are obstacles or vehicles in front of it, then it is determined that the first preset scenario is met.

[0093] In this embodiment, it should be noted that the road type, lane type, and obstacles ahead of the target vehicle need to be identified and judged separately to determine whether the first preset scenario is met. That is, this vehicle rear-view warning method only works in the first preset scenario. In other relatively safe driving scenarios, the road recognition system corresponding to the vehicle rear-view warning method does not work to save unnecessary energy consumption. Specifically, the road type can be suburban or highway sections with a speed limit of 60 kph or higher, the lane type is a non-overtaking lane, and whether there are obstacles or vehicles ahead can include identifying obstacles, low-speed, stationary vehicles, or oncoming vehicles in the left lane of the vehicle, as well as identifying whether there are vehicles in front of the vehicle. Only when multiple preset conditions are met simultaneously can it be determined that the current environment of the target vehicle meets the first preset scenario.

[0094] Step S200: When the current environment matches the first preset scenario, the driving status of the target vehicle and the vehicle behind is estimated to obtain the driving status of the vehicle and the driving status of the vehicle behind.

[0095] In this embodiment, it is understood that once it is determined that the current environment of the target vehicle conforms to the first preset environment, the driving status of the target vehicle and the vehicles behind it can be estimated to further estimate the overtaking risk. The vehicles behind are those in the same lane as the target vehicle. Due to the obstruction of the target vehicle, the vehicles behind may have difficulty seeing the road conditions ahead (especially when the target vehicle is a heavy vehicle), making them prone to dangerous overtaking maneuvers. Therefore, it is necessary to combine the analyzed driving status of the vehicles in front and behind, and to provide certain early warning prompts through the target vehicle to avoid traffic risks. Specifically, the driving status includes the vehicle's trajectory, used to estimate the probability of a collision or other safety accident between the vehicle and the vehicle behind, in order to take appropriate countermeasures.

[0096] For example, when estimating the driving status of the target vehicle and the vehicles behind it, motion data of the target vehicle and the vehicles behind it can be collected by sensors installed on the target vehicle, and corresponding motion models can be constructed to further predict their motion trajectories.

[0097] The vehicle driving status mentioned in step S200 includes the vehicle driving trajectory and driver status, and the following vehicle driving status includes lateral behavior boundaries and longitudinal behavior boundaries.

[0098] The step of estimating the driving states of the target vehicle and the vehicles behind to obtain the driving states of the vehicle itself and the vehicles behind includes:

[0099] Step S210: Estimate the driving trajectory of the target vehicle to obtain the driving trajectory of the vehicle itself;

[0100] Step S220: Monitor the driver's status based on the action information fed back to the target vehicle by the driver;

[0101] Step S230: Establish a motion model based on the motion state of the rear vehicle, and determine the lateral and longitudinal behavior boundaries of the rear vehicle based on the motion model.

[0102] In this embodiment, it should be noted that the above embodiment mainly uses the vehicle's trajectory and driver status to characterize the vehicle's driving state, and uses lateral and longitudinal behavioral boundaries to characterize the driving state of the following vehicle. This is because the vehicle's motion data is easier to obtain than the following vehicle's motion data, making it easier to predict the vehicle's trajectory and control the vehicle to stay within its lane. However, predicting the driving state of the following vehicle is more difficult, so it is necessary to establish a corresponding motion model to further assess the possibility of a collision between the following vehicle and the vehicle based on the maximum lateral and longitudinal boundaries that the following vehicle may reach.

[0103] Specifically, sensors can detect whether the vehicle is currently within its lane and its current speed, thereby predicting its trajectory. Generally, when there is no need to overtake, the vehicle will continue driving in a straight line along the lane, resulting in a relatively simple trajectory. Furthermore, driver feedback received from inside the cab, such as steering wheel movements, headlight adjustments, gearshift manipulation, and clutch, accelerator, and brake control actions, can be used to detect driver inattention. Certain detection conditions can be set based on experience; for example, if the driver does not perform any driving actions within 30 seconds, it can be considered that the driver is not focused. This lack of focus can also serve as an enabling condition for a second preset scenario, triggering the next step of calculating the risk value. In a risky situation, the system will alert both the driver of the following vehicle and the driver of this vehicle.

[0104] Further, in step S230, the step of establishing a motion model based on the motion state of the rear vehicle, and determining the lateral and longitudinal behavioral boundaries of the rear vehicle based on the motion model, includes:

[0105] Step S231: Identify the vehicle type, yaw rate, lateral acceleration, and motion state of the vehicle behind.

[0106] Step S232: Based on the motion state of the vehicle behind, establish a motion model of the vehicle behind;

[0107] Step S233: Based on the motion model, determine the lateral behavior boundary of the following vehicle according to the vehicle type, yaw rate and lateral acceleration of the following vehicle.

[0108] Step S234: Based on the motion model, determine the longitudinal behavior boundary of the rear vehicle according to the longitudinal acceleration model of the rear vehicle and the maximum acceleration, maximum impact, minimum acceleration and minimum impact corresponding to the vehicle type.

[0109] In this embodiment, the vehicle type, yaw rate, lateral acceleration, and motion state of the following vehicle are mainly identified by a perception system installed on the target vehicle. The motion state includes motion speed and other motion parameters. The vehicle type is used to determine the corresponding maximum acceleration, maximum impact, minimum acceleration, and minimum impact. Because different vehicle types have different weights, their specific driving parameters, such as acceleration and deceleration capabilities, are different. Each vehicle type has a fixed maximum acceleration, maximum impact, minimum acceleration, and minimum impact. The corresponding parameter values ​​can be directly determined after obtaining the vehicle type of the following vehicle.

[0110] In one feasible embodiment, the lateral behavior boundary of the rear vehicle can be determined by the lateral steering behavior constraint of the rear vehicle. The steering wheel angle can reach different values ​​at different times, thereby calculating the farthest lateral behavior boundary that the rear vehicle can reach.

[0111] The target vehicle can calculate the estimated position of the following vehicle within time t during the acceleration process in real time. The purpose is to prevent the following vehicle from changing its intention after discovering an obstacle or an oncoming vehicle. However, since the current speed has been increased, in order to provide a larger margin for the following vehicle to avoid a collision, it is necessary to find an objective function to avoid collision during this process.

[0112] Since the vehicle cannot control the running state of the vehicle behind it, but can change the distance between the vehicles in front and behind by changing the running state of the vehicle itself, the purpose of this system is to prevent the vehicle behind from overtaking and colliding with objects in the target lane. The proposed objective function is to act on the reference frame of the vehicle behind and the vehicle itself, that is, to study the physical behavior of the vehicle and the vehicle behind to avoid collision.

[0113] Specifically, during the process of establishing a motion model based on the motion state of the following vehicles, sensors can be used to identify the type of the following vehicle, its yaw rate, and lateral acceleration. (Refer to...) Figure 2 The motion model of the rear vehicle includes:

[0114] Tire steering angle :

[0115] (2.1)

[0116] It refers to the vehicle's wheelbase. ;

[0117] Additionally, refer to Figure 2 , The distance between the center of gravity and the front axle. Distance from rear axle This is the distance between the rear axle and the front bumper. For vehicle length, For vehicle width, Let the radius of the center of mass be the turning radius. The rear axle turning radius. For the overall vehicle quality, For the front wheel lateral stiffness, For the stiffness of the rear wheel side plates, For vehicle speed;

[0118] Vehicle curvature :

[0119] (2.2)

[0120] Center of mass slip angle :

[0121] (2.3)

[0122] Rear wheel slip angle :

[0123] By reducing the coefficients of the constant term, we get:

[0124] (2.4)

[0125] Front wheel slip angle : (2.5)

[0126] Further calculations were performed to determine the relationship between the steering angle and curvature:

[0127] Substituting (2.4) and (2.5) into (2.1), we get:

[0128] The constant term coefficients are obtained as follows:

[0129] (2.6)

[0130] in ;

[0131] vertical distance between steering center and rear axle :

[0132] Due to the rear wheel slip angle in actual vehicles Very small, approximation processing has ,so:

[0133] Substituting (2.2) and (2.4) into the equation, we get:

[0134] (2.7)

[0135] Once the expressions for each parameter in the motion model are determined, the type of following vehicle and the vehicle's yaw rate can be determined through the target vehicle's perception system. and lateral angular velocity ,therefore,

[0136] curvature (2.8)

[0137] And based on the mathematical model of the driver's steering wheel during a turn:

[0138] (2.9)

[0139] in, It is the initial angle of the steering wheel when the driver turns. It means the driver turns at a constant turning speed. It is after time The rear steering wheel angle; Constraints , The time can be calibrated, and can be set to 2 seconds.

[0140] Steering wheel angle With steering angle The relationship between them: (2.10)

[0141] Furthermore, the mathematical model for vehicle curvature change is derived based on (2.6), (2.9), and (2.10), resulting in the final lateral target constraint model (lateral behavior boundary):

[0142] (2.11)

[0143] in, For the initial curvature, To describe the rate of curvature change of the vehicle's steering behavior, the curvature and rate of curvature change constraints are determined by (2.8) through the vehicle's lateral constraints as follows:

[0144] (2.12)

[0145] (2.13)

[0146] The constraint time during turning is calculated using the above formula:

[0147] (2.14)

[0148] Therefore, in one feasible embodiment, the driver steering behavior constraint, i.e., the correspondence between time and steering wheel angle, can be as follows: Figure 3 As shown.

[0149] On the other hand, the longitudinal acceleration model for the vehicle behind is:

[0150] (2.15)

[0151] Constraints , The time can be calibrated, and can be set to 2 seconds; the maximum acceleration when driven by a passenger vehicle. Drive maximum impact Minimum acceleration during braking Drive maximum impact .

[0152] From (2.15), the constraint time at the minimum longitudinal acceleration is obtained:

[0153] (2.16)

[0154] Constraint time at maximum longitudinal acceleration:

[0155] (2.17)

[0156] Therefore, in one feasible embodiment, the vehicle longitudinal behavior constraint, i.e., the correspondence between time and longitudinal acceleration, can be as follows: Figure 4 As shown. The vertical behavior boundary can be determined by combining (2.15), (2.16) and (2.17).

[0157] Step S300: If the current environment simultaneously meets the first preset scenario and the second preset scenario, then determine the risk value of the following vehicle based on the driving status of the current vehicle and the driving status of the following vehicle, wherein the risk level of the second preset scenario is greater than the risk level of the first preset scenario.

[0158] In this embodiment, it should be noted that step S300 is only enabled under certain conditions, and only then is the step of determining the risk value of the following vehicle based on the driving status of the current vehicle and the driving status of the following vehicle executed. That is, after determining the current driving status and the driving status of the following vehicle, it is necessary to determine whether the current scenario of the target vehicle is a second preset scenario through road recognition. Specifically, in the second preset scenario, it can be identified that the following vehicle has the intention to overtake, and there are vehicles traveling in the same direction or two lanes in front of the overtaking lane. That is, in the second preset scenario, the overtaking behavior of the following vehicle may cause a traffic safety accident. Therefore, it is necessary to determine the risk value of the following vehicle. Such judgment can avoid continuously calculating the risk value when there is no safety risk, thus avoiding wasting computing resources.

[0159] Additionally, the following vehicle risk value mentioned in step S300 includes a lateral request value and a longitudinal request value. The step of determining the following vehicle risk value based on the driving status of the current vehicle and the driving status of the following vehicle includes:

[0160] Step S310: Based on the driving status of the vehicle and the driving status of the vehicle behind, establish a common coordinate system corresponding to the target vehicle and the vehicle behind.

[0161] Step S320: Based on the common coordinate system, calculate the lateral request value according to the vehicle's driving state, the lateral behavior boundary, and the preset lateral obstacle avoidance objective function;

[0162] Step S330: Based on the common coordinate system, calculate the longitudinal request value according to the vehicle's driving state, the longitudinal behavior boundary, and the preset longitudinal obstacle avoidance objective function.

[0163] In this embodiment of the application, it is first necessary to establish a common coordinate system for the target vehicle and the vehicle behind it. Specifically, referring to... Figure 5 Since the center of the rear axle of the vehicle is taken as the origin of the common coordinate system, therefore, =0;(2.18), where 1 represents the target vehicle and 2 represents the vehicle behind. Additionally, the frontal angle is defined as Ψ, and the length of the vehicle behind is... Rear wheelbase The coordinates of the rear vehicle The preset lateral obstacle avoidance objective function can be set according to the lateral collision avoidance process, which is the process by which the driver of the following vehicle avoids a collision by steering when they detect a potential hazard. The lateral physical boundaries of the following vehicle have already been constrained in the system boundary constraints. Geometric modeling of the following vehicle is performed as follows: Figure 6 As shown. Therefore, the lateral obstacle avoidance objective function based on lateral constraints can be obtained by... Figure 6 The geometric model of the rear vehicle is analyzed and derived to obtain the objective function for collision avoidance by steering, which requires the rate of change of curvature of the rear vehicle to satisfy the following:

[0164] (2.19)

[0165] in, The rate of change of curvature of the rear vehicle. It is a scalar derived after coordinate transformation. , yes The pace is long.

[0166] Based on the above derivation method of the lateral obstacle avoidance objective function, the longitudinal obstacle avoidance objective function of the following vehicle is derived as follows:

[0167] (2.20)

[0168] in, It is the minimum distance from the car behind. , yes The pace is long.

[0169] Furthermore, the objective function values, namely the lateral and longitudinal request values, can be obtained based on model prediction methods. Specifically, data statistics can be collected through lane change conditions, and the prediction time domain can be set through calibration, for example, a 2-second time domain. The prediction step size is determined by the system controller scheduling time, which is currently set to 10ms. At each sampling time, the lateral and longitudinal objective functions for the 2-second time are solved, and the extreme values ​​of the solved functions in these two dimensions are used as the estimated request values ​​for calculating the hazard to following vehicles.

[0170] In summary, based on the optimal value obtained and (2.11), the horizontal request value is obtained as follows:

[0171] (2.21)

[0172] Based on the optimal value obtained from the solution and (2.15), the vertical request value is obtained:

[0173] (2.22)

[0174] in, For lateral request values, This is the value requested vertically.

[0175] Additionally, it should be noted that before executing step S300, it is necessary to determine whether the current environment meets both the first and second preset scenarios in order to trigger system enable, i.e., to execute the step of determining the risk value of the following vehicle. Therefore, before the step in step S300 where, if the current environment simultaneously meets the first and second preset scenarios, the risk value of the following vehicle is determined based on the driving status of the current vehicle and the driving status of the following vehicle, the method further includes:

[0176] The scene in which the target vehicle is located is identified to determine whether the target vehicle is in a first warning scene, a second warning scene, or an intervention and protection scene. In the first warning scene, there is a vehicle traveling in the same direction ahead in the overtaking lane or a vehicle approaching in both lanes and a vehicle behind intends to overtake. In the second warning scene, in addition to the first warning scene, there is a vehicle ahead in the lane in which the target vehicle is located. In the intervention and protection scene, in addition to the first warning scene, there is no vehicle ahead in the lane in which the target vehicle is located.

[0177] If the target vehicle is in one or more of the first warning scenario, the second warning scenario, and the intervention protection scenario, then it is determined that the environment in which the target vehicle is located conforms to the second preset scenario.

[0178] In this embodiment, it should be noted that, referring to Figure 8Based on the aforementioned criteria for classifying various scenarios, this vehicle rear-view warning method is primarily applied to conventional scenarios with traffic risks. The second preset scenario is further divided into three different types. In the first and second warning scenarios, the target vehicle needs to send a warning to vehicles behind it. In the intervention and protection scenario, intervention torque needs to be input to the target vehicle to change its operating state and the distance between the vehicle in front and behind, preventing collisions with the target vehicle, other vehicles in the lane ahead, or obstacles caused by overtaking from behind. Here, 1 represents the target vehicle, 2 represents the vehicle behind, and 3 represents the vehicle ahead. In this embodiment, the current road condition scenario can be identified through a road recognition module, and triggering is enabled when any of the following scenarios are met.

[0179] 1) WarnScen1 (first warning scenario) == true;

[0180] 2) WarnScen2 (second warning scenario) == true;

[0181] 3) Intervention Scen = true.

[0182] At the same time, the trajectory positions of the vehicle and the following vehicles in the relative coordinate system are determined based on the state estimation of the vehicle itself, and the overlap of trajectories within time t is estimated. The scene is then classified based on the trajectories of the vehicle and the following vehicles.

[0183] It should be noted that, during the overtaking process, the behavior of the vehicle overtaking can be specifically categorized based on the actions of the vehicle behind:

[0184] 1) Aggressive lane changing and overtaking: Accelerate in the current lane and continue to accelerate to the target lane during the lane change process;

[0185] 2) Normal lane change and overtaking: Accelerate in the current lane, release the accelerator to a certain degree during the lane change and maintain it until the target lane is reached;

[0186] 3) Smooth lane change and overtaking: Change lanes in this lane using the current throttle.

[0187] It should also be noted that the second warning scenario includes the first warning scenario, and the interference protection scenario also includes the first warning scenario. The difference is that in the second warning scenario, there are vehicles in front of the target vehicle in its current lane, so the target vehicle's movement cannot be adjusted (such as accelerating to increase the distance from vehicles behind), so only a warning can be issued; while in the interference protection scenario, there are no vehicles in front of the target vehicle in its current lane, so the distance from vehicles behind can be increased by accelerating, etc., so that the drivers of the vehicles behind can have a wider field of vision, and also to avoid collisions with the vehicles behind.

[0188] This embodiment sets up different specific scenarios to enable appropriate risk avoidance behaviors in different scenarios, thereby maximizing the driving safety of the target vehicle and the vehicles behind it.

[0189] Step S400: If the risk value of the following vehicle exceeds the warning threshold, a warning prompt is issued to the following vehicle.

[0190] In this embodiment of the application, it should be noted that the basis for determining whether the risk value of the following vehicle exceeds the warning threshold is the warning boundary MAP (Figure) used for hazard arbitration. That is, the warning boundary MAP is preset in the system, which includes the warning threshold. When the obtained lateral request value and / or longitudinal request value is greater than the warning threshold, a warning prompt can be triggered. That is, by controlling the flashing of the rear lights of the target vehicle, the driver of the following vehicle is prompted that there is a certain risk ahead and to overtake with caution.

[0191] Further, in step S400, the step of issuing a warning to the following vehicle if the risk value of the following vehicle exceeds the warning threshold includes:

[0192] Step S410: When the lateral request value or the longitudinal request value is higher than its respective warning threshold, a warning is issued to the vehicle behind by means of lights.

[0193] Step S420: If the target vehicle is in the intervention protection scenario, calculate the intervention torque of the target vehicle based on the lateral request value and the longitudinal request value;

[0194] Step S430: Control the target vehicle according to the intervention torque.

[0195] In this embodiment, it should be noted that when the risk value of the following vehicle is higher than the warning threshold in the warning boundary MAP, in addition to issuing a warning to the following vehicle, it is also possible to determine whether the motion state of the target vehicle can be changed by intervention torque based on the current specific scenario to avoid collision with the following vehicle and further improve driving safety. Specifically, based on the scene recognition results obtained before step S300, it is determined whether the current situation is an intervention protection scenario, i.e., there are no other vehicles in front of the current lane. If so, the intervention torque required for the target vehicle is determined according to the lateral request value and the longitudinal request value. The intervention torque is used to change the motion state of the target vehicle. The intervention torque is calculated so that after changing the running state of the target vehicle by intervention torque, the corresponding lateral request value and longitudinal request value will change to below the warning threshold. That is, after controlling the target vehicle to change its motion state by intervention torque, the predicted trajectory positions of the target vehicle and the following vehicle will not overlap, thereby reserving a safety space to prevent collision.

[0196] Based on the above embodiments, the overall structure and flow of this vehicle rear-view warning method can be obtained as follows: Figure 7 As shown, the driving status of the target vehicle and the vehicle behind is first estimated under the first preset scenario. Then, based on the first preset scenario and when it meets the second preset scenario, the hazard calculation is enabled to determine the risk value of the vehicle behind. When it exceeds the warning threshold, a warning prompt is given according to the current scenario and torque intervention is used to control the current operating status of the target vehicle. The first warning scenario and the intervention protection scenario can be met at the same time, so the warning prompt and torque intervention can be performed at the same time under the intervention protection scenario.

[0197] Once the value of the intervention torque is determined, the control system of the target vehicle can be interfered with by the intervention torque to automatically adjust the motion state of the target vehicle (e.g., accelerate forward, increase the distance between the vehicle and the vehicle behind to leave a safe overtaking space). This enables the automatic execution of the intervention protection action based on the vehicle's rear driving warning, without relying on the driver to manually adjust the vehicle's operating state. It automatically adjusts the distance when there is a safety risk to ensure overtaking safety.

[0198] In the first embodiment of this application, the current environment of the target vehicle is first identified, and it is determined whether the current environment conforms to a first preset scenario. When the current environment conforms to the first preset scenario, the driving states of the target vehicle and the following vehicle are estimated to obtain the driving state of the target vehicle and the driving state of the following vehicle. If the current environment conforms to both the first and second preset scenarios, the risk value of the following vehicle is determined based on the driving state of the target vehicle and the driving state of the following vehicle. The risk level of the second preset scenario is greater than that of the first preset scenario. If the risk value of the following vehicle exceeds a warning threshold, a warning is issued to the following vehicle. The technical solution of this application further executes the warning by identifying the environment and calculating the risk value of the following vehicle. This allows the target vehicle to automatically issue a warning to the driver of the following vehicle intending to overtake when the target vehicle reaches the preset warning threshold risk level, even if the driver does not have extensive driving experience. This improves the automation of warnings in driving scenarios, solves the technical problem of high dependence on the driver's subjective judgment in existing overtaking risk warning methods, and improves driving safety.

[0199] Reference Figure 9 , Figure 9 This is a schematic diagram of the rear-view warning device for vehicles in this application.

[0200] This application also provides a vehicle rear-view warning device, the vehicle rear-view warning device comprising:

[0201] The scene recognition module 10 is used to identify the current environment of the target vehicle and determine whether the current environment conforms to the first preset scene.

[0202] The state estimation module 20 is used to estimate the driving state of the target vehicle and the vehicle behind when the current environment matches the first preset scenario, so as to obtain the driving state of the vehicle itself and the driving state of the vehicle behind.

[0203] The risk calculation module 30 is used to determine the risk value of the following vehicle based on the driving status of the current vehicle and the driving status of the following vehicle if the current environment simultaneously meets the first preset scenario and the second preset scenario.

[0204] The early warning module 40 is used to issue an early warning to the following vehicle if the risk value of the following vehicle exceeds the early warning threshold.

[0205] Optionally, the scene recognition module 10 is further configured to: identify the road type, lane type, and road conditions of the road where the target vehicle is located; if the road type where the target vehicle is located is a preset road type, the lane type is a non-overtaking lane, and there are obstacles or vehicles in front, then it is determined that it conforms to the first preset scene.

[0206] Optionally, the scene recognition module 10 is further configured to: identify the scene in which the target vehicle is located, to determine whether the target vehicle is in a first warning scene, a second warning scene, or an intervention protection scene, wherein, in the first warning scene, there is a vehicle traveling in the same direction ahead in the overtaking lane or a vehicle approaching in both lanes and a vehicle behind intends to overtake; in the second warning scene, in addition to the first warning scene, there is a vehicle ahead in the lane in which the target vehicle is located; and in the intervention protection scene, in addition to the first warning scene, there is no vehicle ahead in the lane in which the target vehicle is located; if the target vehicle is in one or more of the first warning scene, the second warning scene, and the intervention protection scene, then it is determined that the environment in which the target vehicle is located conforms to a second preset scene.

[0207] like Figure 10 As shown, Figure 10 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application.

[0208] Specifically, the vehicle rear-view warning device can be a VCU (Vehicle Control Unit), PC (Personal Computer), tablet computer, portable computer, or server, etc.

[0209] like Figure 10As shown, the vehicle rear-view warning device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0210] Those skilled in the art will understand that Figure 10 The device structure shown does not constitute a limitation on the vehicle rear-view warning device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0211] like Figure 10 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a vehicle rear-view warning application.

[0212] exist Figure 10 In the device shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the client and communicate data with the client; and the processor 1001 can be used to call the vehicle rear driving warning program stored in the memory 1005 to implement the operation in the vehicle rear driving warning method provided in the above embodiment.

[0213] Furthermore, this application also proposes a vehicle that includes the aforementioned rear-view warning device. It is understood that the vehicle also includes energy storage devices, drive systems, and other devices that ensure the normal operation of the vehicle.

[0214] Furthermore, this application also proposes a computer storage medium storing a computer program. When the computer program is executed by a processor, it implements the operations in the vehicle rear-end collision warning method provided in the above embodiments. The specific steps will not be described in detail here.

[0215] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity / operation / object from another, and do not necessarily require or imply any such actual relationship or order between these entities / operations / objects; the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0216] For the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and relevant details can be found in the description of the method embodiments. The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separate. Some or all of the modules can be selected according to actual needs to achieve the purpose of this application. Those skilled in the art can understand and implement this without creative effort.

[0217] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0218] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, vehicle, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0219] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for vehicle rear-view warning, characterized in that, The vehicle rear driving warning method includes: Identify the current environment of the target vehicle and determine whether the current environment matches a first preset scenario; When the current environment matches the first preset scenario, the driving status of the target vehicle and the vehicle behind is estimated to obtain the driving status of the vehicle and the driving status of the vehicle behind. If the current environment simultaneously meets the first preset scenario and the second preset scenario, then the risk value of the following vehicle is determined based on the driving status of the current vehicle and the driving status of the following vehicle, wherein the risk level of the second preset scenario is greater than the risk level of the first preset scenario; If the risk value of the following vehicle exceeds the warning threshold, a warning message will be issued to the following vehicle. The step of identifying the current environment of the target vehicle and determining whether the current environment matches the first preset scenario includes: Identify the road type, lane type, and road conditions of the target vehicle; If the target vehicle is located on a road of a preset type, in a non-overtaking lane, and there are obstacles or vehicles ahead, then it is determined that the first preset scenario is met. Before the step of determining the risk value of the following vehicle based on the driving status of the current vehicle and the driving status of the following vehicle if the current environment simultaneously meets the first preset scenario and the second preset scenario, the method further includes: The scene in which the target vehicle is located is identified to determine whether the target vehicle is in a first warning scene, a second warning scene, or an intervention and protection scene. In the first warning scene, there is a vehicle traveling in the same direction ahead in the overtaking lane or a vehicle approaching in both lanes and a vehicle behind intends to overtake. In the second warning scene, in addition to the first warning scene, there is a vehicle ahead in the lane in which the target vehicle is located. In the intervention and protection scene, in addition to the first warning scene, there is no vehicle ahead in the lane in which the target vehicle is located. If the target vehicle is in one or more of the first warning scenario, the second warning scenario, and the intervention protection scenario, then it is determined that the environment in which the target vehicle is located conforms to the second preset scenario.

2. The vehicle rearward driving warning method as described in claim 1, characterized in that, The vehicle's driving status includes its driving trajectory and driver status, while the following vehicle's driving status includes lateral and longitudinal behavioral boundaries. The step of estimating the driving states of the target vehicle and the vehicles behind to obtain the driving states of the vehicle itself and the vehicles behind includes: The driving trajectory of the target vehicle is estimated to obtain the driving trajectory of the current vehicle; Monitor the driver's status based on the action information fed back to the target vehicle by the driver; A motion model is established based on the motion state of the vehicle behind, and the lateral and longitudinal behavioral boundaries of the vehicle behind are determined based on the motion model.

3. The vehicle rearward driving warning method as described in claim 2, characterized in that, The step of establishing a motion model based on the motion state of the following vehicle, and determining the lateral and longitudinal behavioral boundaries of the following vehicle based on the motion model, includes: Identify the vehicle type, yaw rate, lateral acceleration, and motion state of the vehicle behind; Based on the motion state of the vehicle behind, establish a motion model of the vehicle behind; Based on the motion model, the lateral behavior boundary of the following vehicle is determined according to the vehicle type, yaw rate, and lateral acceleration of the following vehicle. Based on the motion model, the longitudinal behavior boundary of the following vehicle is determined according to the longitudinal acceleration model of the following vehicle and the maximum acceleration, maximum impact, minimum acceleration and minimum impact corresponding to the vehicle type.

4. The vehicle rearward driving warning method as described in claim 2, characterized in that, The following vehicle risk value includes a lateral request value and a longitudinal request value. The step of determining the following vehicle risk value based on the driving status of the current vehicle and the driving status of the following vehicle includes: Based on the driving status of the target vehicle and the driving status of the vehicle behind it, a common coordinate system is established for the target vehicle and the vehicle behind it. Based on the common coordinate system, the lateral request value is calculated according to the vehicle's driving state, the lateral behavior boundary, and the preset lateral obstacle avoidance objective function. Based on the common coordinate system, the longitudinal request value is calculated according to the vehicle's driving state, the longitudinal behavior boundary, and the preset longitudinal obstacle avoidance objective function.

5. The vehicle rearward driving warning method as described in claim 4, characterized in that, The step of issuing a warning to the following vehicle if the risk value of the following vehicle exceeds the warning threshold includes: When the lateral request value or the longitudinal request value is higher than its respective warning threshold, a warning signal is issued to the vehicle behind via lights. If the target vehicle is in the intervention protection scenario, the intervention torque of the target vehicle is calculated based on the lateral request value and the longitudinal request value; The target vehicle is controlled based on the intervention torque.

6. A vehicle rear-view warning device, characterized in that, The vehicle rear driving warning device includes: The scene recognition module is used to identify the current environment of the target vehicle and determine whether the current environment matches the first preset scene. The state estimation module is used to estimate the driving state of the target vehicle and the vehicle behind when the current environment matches the first preset scenario, so as to obtain the driving state of the vehicle itself and the driving state of the vehicle behind. The risk calculation module is used to determine the risk value of the following vehicle based on the driving status of the current vehicle and the driving status of the following vehicle if the current environment simultaneously meets the first preset scenario and the second preset scenario. The early warning module is used to issue an early warning to the following vehicle if the risk value of the following vehicle exceeds the early warning threshold. The scene recognition module is also used to: identify the road type, lane type and road conditions of the road where the target vehicle is located; if the road type where the target vehicle is located is a preset road type, the lane type is a non-overtaking lane and there are obstacles or vehicles in front, then it is determined that it conforms to the first preset scene; The scene recognition module is further configured to: identify the scene in which the target vehicle is located, to determine whether the target vehicle is in a first warning scene, a second warning scene, or an intervention protection scene, wherein, in the first warning scene, there is a vehicle traveling in the same direction ahead in the overtaking lane or a vehicle approaching in both lanes and a vehicle behind intends to overtake; in the second warning scene, in addition to the first warning scene, there is a vehicle ahead in the lane in which the target vehicle is located; and in the intervention protection scene, in addition to the first warning scene, there is no vehicle ahead in the lane in which the target vehicle is located; if the target vehicle is in one or more of the first warning scene, the second warning scene, and the intervention protection scene, then it is determined that the environment in which the target vehicle is located conforms to a second preset scene.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; A memory that is communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the steps of the vehicle rear-end collision warning method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for implementing a vehicle rear-end collision warning method, the program for implementing the vehicle rear-end collision warning method being executed by a processor to implement the steps of the vehicle rear-end collision warning method as described in any one of claims 1 to 5.

Images