Vehicle braking control method and system, vehicle-mounted equipment and vehicle

Abstract

The invention provides a vehicle braking control method and system, vehicle-mounted equipment and a vehicle, and the method comprises the steps that driving state information is obtained and comprises speed information of a target vehicle, speed information of a front vehicle and speed information of a rear vehicle and distance information between the target vehicle and the front vehicle and distance information between the rear vehicle and the target vehicle; determining a first risk level of collision between the target vehicle and the front vehicle and a second risk level of collision between the rear vehicle and the target vehicle according to the speed information and the distance information; comparing the risk levels of the first risk level and the second risk level, and determining the target deceleration of the target vehicle according to the comparison result; and controlling the target vehicle to brake according to the target deceleration. Through the states of the front vehicle, the own vehicle and the rear vehicle and the distance between the vehicles, the collision risk levels of the own vehicle and the front vehicle as well as the rear vehicle and the own vehicle are determined, and the braking deceleration is determined by integrating the risk levels of the front and rear collisions, so that the risk of rear-end collision caused by the rear vehicle due to the fact that only the collision with the front vehicle is concerned is avoided.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle braking control method, system, on-board equipment, and vehicle. Background Technology

[0002] With the rapid development of intelligent driving technology, AEB (Autonomous Emergency Braking) has become an important component for improving the active safety performance of vehicles. AEB systems typically use sensors to monitor obstacles in front of the vehicle in real time. A microcontroller processes the collected obstacle information to determine if there is a risk of collision between the vehicle and the obstacle. If a potential collision is detected, an emergency braking command is immediately triggered, and the braking actuator applies a significant deceleration to avoid or mitigate the consequences of a collision.

[0003] In related technologies, AEB systems primarily focus on avoiding forward collision risks, generally neglecting other collision problems that may be caused by the emergency braking action itself, especially rear-end collisions caused by vehicles failing to brake in time. If a vehicle suddenly brakes at high speed and there are other road users following closely behind, the latter may not be able to slow down in time due to insufficient reaction time or limited braking capacity, resulting in a rear-end collision. Therefore, the overall safety benefits of AEB systems are still insufficient, making it difficult to reduce the risk of rear-end collisions while avoiding forward collision risks. Summary of the Invention

[0004] This application discloses a vehicle braking control method, system, on-board equipment, and vehicle, which solves the technical problem of reducing the risk of rear-end collisions while avoiding the risk of frontal collisions during vehicle braking.

[0005] This application provides a vehicle braking control method, the method comprising: acquiring driving state information, the driving state information including speed information of a target vehicle, a vehicle in front, and a vehicle behind, as well as distance information between the target vehicle and the vehicle in front, and between the vehicle behind and the target vehicle; determining a first risk level of a collision between the target vehicle and the vehicle in front, and determining a second risk level of a collision between the target vehicle and the vehicle behind, based on the speed information and the distance information; comparing the risk levels of the first risk level and the second risk level, and determining a target deceleration of the target vehicle based on the comparison result; and controlling the target vehicle to brake based on the target deceleration.

[0006] In one embodiment of this application, the determination of the first risk level and the second risk level includes: determining a first collision prediction time between the target vehicle and the vehicle in front based on a first speed of the target vehicle, a second speed of the vehicle in front, and a first distance between the target vehicle and the vehicle in front; determining a second collision prediction time between the rear vehicle and the target vehicle based on the second speed, a third speed of the vehicle behind, and a second distance between the rear vehicle and the target vehicle; determining the first risk level based on the first collision prediction time and a preset mapping relationship; and determining the second risk level based on the second collision time and the mapping relationship; wherein the speed information includes the first speed, the second speed, and the third speed; the distance information includes the first distance and the second distance; and the mapping relationship characterizes the correspondence between the collision prediction time and the risk level.

[0007] In one embodiment of this application, before determining the second risk level based on the second collision time and the mapping relationship, the method further includes: obtaining the braking delay time of the following vehicle, wherein the braking delay time includes the driver's reaction time, the driver's braking operation time, and the vehicle's braking response time; calculating the difference between the second collision prediction time and the braking delay time, and using the difference as the final second collision prediction time, so as to determine the second risk level based on the final second collision prediction time.

[0008] In one embodiment of this application, determining the target deceleration of a target vehicle based on a comparison result includes: if the comparison result satisfies a preset first condition, then determining the target deceleration based on a first speed of the target vehicle, a second speed of the vehicle in front, and a first distance between the target vehicle and the vehicle in front; if the comparison result satisfies a preset second condition, then obtaining a first collision prediction time between the target vehicle and the vehicle in front, and determining the target deceleration based on the first collision prediction time, the first speed, a third speed of the vehicle behind, and the extreme deceleration value of the vehicle behind; if the comparison result satisfies a preset third condition, then determining the target deceleration based on the first speed, the second speed, the third speed, the first distance, a second distance between the vehicle behind and the target vehicle, a first acceleration of the vehicle in front, and a second acceleration of the vehicle behind; wherein, the first condition includes a first risk level higher than a second risk level, the second condition includes a first risk level lower than a second risk level, the third condition includes a first risk level and a second risk level being the same, and the speed information further includes the extreme deceleration value, the first acceleration, and the second acceleration.

[0009] In one embodiment of this application, the second condition further includes the first risk level being a medium risk level; the third condition further includes both the first risk level and the second risk level being high risk levels; after determining the first risk level, the method further includes: if the first risk level is a low risk level, then setting the target deceleration to a preset deceleration threshold; determining the target deceleration of the target vehicle based on the comparison result further includes: if both the first risk level and the second risk level are medium risk levels, then determining the target deceleration based on the first speed, the second speed, and the first distance.

[0010] In one embodiment of this application, if the comparison result satisfies a preset third condition, the method for determining the target deceleration includes: determining a first deceleration of the target vehicle based on the first speed, the second speed, the first distance, and the first acceleration, wherein the first deceleration represents the minimum deceleration required by the target vehicle to avoid colliding with the vehicle in front; determining a second deceleration of the target vehicle based on the first speed, the third speed, the second distance, and the second acceleration, wherein the second deceleration represents the maximum deceleration required by the target vehicle to avoid colliding with the vehicle behind; if there is a safe deceleration range between the first deceleration and the second deceleration, then the target deceleration is determined within the safe deceleration range; if there is no safe deceleration range between the first deceleration and the second deceleration, then a collision cost function is constructed based on the first relative speed when the target vehicle collides with the vehicle in front and the second relative speed when the vehicle behind collides with the target vehicle, and the target deceleration is solved with the goal of minimizing the collision cost.

[0011] In one embodiment of this application, the method for obtaining the speed information and the distance information includes: acquiring environmental data of the target vehicle, the environmental data including a first environmental image in front of the target vehicle and a second environmental image behind the target vehicle; inputting the first environmental image and the second environmental image into a pre-constructed target detection model to obtain a first distance between the target vehicle and the vehicle in front, and a second distance between the vehicle behind and the target vehicle, thereby obtaining the distance information, wherein the target detection model is trained by environmental image samples collected under various driving environments, containing various vehicles and labeled with corresponding position and distance labels; determining the second speed and first acceleration of the vehicle in front based on the acquisition time interval of consecutive first environmental images and the change value of the first distance in consecutive first environmental images, and determining the third speed and second acceleration of the vehicle behind based on the acquisition time interval of consecutive second environmental images and the change value of the second distance in consecutive second environmental images, thereby obtaining the speed information.

[0012] This application also provides a vehicle braking control system, the system comprising: a data acquisition module for acquiring driving status information, the driving status information including speed information of the target vehicle, the vehicle in front and the vehicle behind, and distance information between the target vehicle and the vehicle in front, and between the vehicle behind and the target vehicle; a risk level determination module for determining a first risk level of a collision between the target vehicle and the vehicle in front, and a second risk level of a collision between the target vehicle and the vehicle behind, based on the speed information and the distance information; a deceleration calculation module for comparing the risk levels of the first risk level and the second risk level, and determining a target deceleration of the target vehicle based on the comparison result; and a braking control module for controlling the target vehicle to brake based on the target deceleration.

[0013] This application also provides an on-board device that uses the vehicle braking control method as described above, or includes the vehicle braking control system as described above.

[0014] This application also provides a vehicle including a vehicle braking control system as described above, or including on-board equipment as described above.

[0015] The beneficial effects of this application are as follows: The vehicle braking control method, system, on-board equipment, and vehicle provided in this application first acquire driving status information, including the speed information of the target vehicle, the vehicle in front, and the vehicle behind, as well as the distance information between the target vehicle and the vehicle in front, and between the vehicle behind and the target vehicle. Then, based on the speed information and distance information, a first risk level of collision between the target vehicle and the vehicle in front is determined, and a second risk level of collision between the target vehicle and the vehicle behind is determined. Then, the risk levels of the first risk level and the second risk level are compared, and a target deceleration of the target vehicle is determined based on the comparison result. Finally, the target vehicle is controlled to brake based on the target deceleration. By considering the states of the vehicle in front, the vehicle itself, and the vehicle behind, as well as the distance between the vehicles, and simultaneously judging the collision risk levels between the vehicle itself and the vehicle in front, and between the vehicle behind and the vehicle itself, the risk levels of front and rear collisions are comprehensively considered, and the braking deceleration of the vehicle itself is adaptively determined and braked based on this. This avoids the risk of being rear-ended by the vehicle behind by only focusing on the collision with the vehicle in front, thus improving driving safety. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0017] In the attached diagram: Figure 1This is a schematic diagram illustrating an implementation environment of a vehicle braking control system, as shown in an exemplary embodiment of this application. Figure 2 This is a flowchart illustrating a vehicle braking control method as shown in an exemplary embodiment of this application; Figure 3 This is a schematic diagram illustrating the structure of a front / rear view camera, as shown in an exemplary embodiment of this application; Figure 4 This is a flowchart illustrating an exemplary embodiment of the present application for acquiring environmental images; Figure 5 This is a flowchart illustrating a specific vehicle braking control method as shown in an exemplary embodiment of this application; Figure 6 This is a flowchart illustrating another specific vehicle braking control method as shown in an exemplary embodiment of this application; Figure 7 This is a block diagram illustrating a vehicle braking control system as an exemplary embodiment of this application; Figure 8 This is a schematic diagram of the structure of an in-vehicle device provided in one embodiment of this application. Detailed Implementation

[0018] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0019] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. The drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the shape, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0020] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the present application. However, it will be apparent to those skilled in the art that embodiments of the present application may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the present application.

[0021] The emergency braking function of the AEB system can effectively avoid collisions or significantly reduce the severity of collisions when complete avoidance is not possible. However, the inventors of this application have found that AEB systems primarily focus on avoiding forward collision risks, generally neglecting other collision problems that may be caused by the emergency braking action itself, especially rear-end collisions caused by vehicles failing to brake in time. If a vehicle suddenly applies emergency braking while traveling at high speed, and there are other road users following closely behind, the latter may not be able to slow down in time due to insufficient reaction time or limited braking capacity, resulting in a rear-end collision. Therefore, the overall safety benefits of the AEB system are still insufficient, making it difficult to reduce the risk of rear-end collisions while avoiding forward collision risks.

[0022] Therefore, please see Figure 1 , Figure 1 This is a schematic diagram illustrating an implementation environment of a vehicle braking control system, as shown in an exemplary embodiment of this application. Figure 1 As shown, the implementation environment includes a vehicle 110 and a vehicle braking control system 120. The vehicle braking control system 120 is embedded in the vehicle 110 and is used to realize the braking control of the vehicle 110. The vehicle braking control system 120 includes, but is not limited to, the vehicle infotainment system, the vehicle computer, the automatic emergency braking system, etc. By considering the state of the vehicle in front, the vehicle itself, and the vehicle behind, as well as the distance between the vehicles, it simultaneously judges the collision risk level between the vehicle itself and the vehicle in front, and between the vehicle behind and the vehicle itself. In this way, it comprehensively considers the risk level of front and rear collisions, adaptively determines the braking deceleration of the vehicle itself, and performs braking based on this. This avoids the risk of being rear-ended by the vehicle behind by only focusing on the collision with the vehicle in front, thus improving driving safety.

[0023] Please see Figure 2 , Figure 2 This is a flowchart illustrating a vehicle braking control method as shown in an exemplary embodiment of this application. This method can be applied to... Figure 1 The implementation environment is shown, and is specifically executed by the vehicle braking control system 120 in that implementation environment. It should be understood that the method can also be applied to other exemplary implementation environments and executed by devices in other implementation environments. This embodiment does not limit the implementation environment to which the method is applicable.

[0024] like Figure 2 As shown, in an exemplary embodiment, the vehicle braking control method includes at least steps S210 to S240, which are described in detail below: Step S210: Obtain driving status information, which includes the speed information of the target vehicle, the vehicle in front and the vehicle behind, as well as the distance information between the target vehicle and the vehicle in front, and between the vehicle behind and the target vehicle.

[0025] Among them, the target vehicle is the braking vehicle to be controlled; the vehicle in front refers to the vehicle in front of the target vehicle, in the same lane and closest to it; the vehicle behind refers to the vehicle behind the target vehicle, in the same lane and closest to it; speed information refers to the current speed information of the target vehicle, the vehicle in front and the vehicle behind; distance information refers to the current distance information between the target vehicle and the vehicle in front, and between the vehicle behind and the target vehicle.

[0026] In addition, the speed information of the target vehicle can be obtained by acquiring onboard sensors. The speed information of the vehicle in front, the speed information of the vehicle behind, the distance information between the target vehicle and the vehicle in front, and the distance information between the vehicle behind and the target vehicle can be obtained by monitoring the position information of the vehicles in front and the vehicles behind to obtain position change information.

[0027] Step S220: Based on the speed and distance information, determine the first risk level of a collision between the target vehicle and the vehicle in front, and determine the second risk level of a collision between the vehicle behind and the target vehicle.

[0028] The first risk level represents the likelihood of a collision between the target vehicle and the vehicle in front, while the second risk level represents the likelihood of a collision between the vehicle behind and the target vehicle. The higher the risk level, the greater the likelihood of a collision.

[0029] Step S230: Compare the risk levels of the first risk level and the second risk level, and determine the target deceleration of the target vehicle based on the comparison results.

[0030] The comparison result refers to the relative risk levels of the first and second risk levels; the target deceleration refers to the braking deceleration of the target vehicle determined by a comprehensive consideration of the first and second risk levels.

[0031] Step S240: Control the target vehicle to brake based on the target deceleration.

[0032] Specifically, the vehicle is controlled to brake based on the target deceleration. This involves generating a deceleration command based on the target deceleration and sending the command to the execution system. The execution system then responds to the deceleration command and performs the vehicle deceleration operation to complete the vehicle braking and deceleration.

[0033] In this embodiment, by considering the states of the vehicle in front, the vehicle itself, and the vehicles behind, as well as the distance between the vehicles, the collision risk levels between the vehicle itself and the vehicle in front, and between the vehicle behind and the vehicle itself are determined simultaneously. Thus, by comprehensively considering the risk levels of front and rear collisions, the braking deceleration of the vehicle itself is adaptively determined, and braking is performed based on this. This avoids the risk of being rear-ended by the vehicle behind due to focusing only on the collision with the vehicle in front, thereby improving driving safety.

[0034] For example, the speed information includes the first speed of the target vehicle, the second speed of the vehicle in front, the third speed of the vehicle behind, the first acceleration of the vehicle in front, the second acceleration of the vehicle behind, and the extreme value of the deceleration of the vehicle behind; the distance information includes the first distance between the target vehicle and the vehicle in front, and the second distance between the vehicle behind and the target vehicle.

[0035] For example, risk levels include low risk, medium risk, and high risk.

[0036] In this exemplary embodiment, there are no restrictions on the specific method of risk level classification or the number of risk levels.

[0037] In one possible embodiment, after obtaining the target deceleration, considering that the actual deceleration of the target vehicle may deviate from the target deceleration due to factors such as road surface, load, and braking system response, it is necessary to eliminate this deviation. Therefore, a PID controller (proportional-integral-derivative controller) is used to ensure that the actual deceleration generated by the target vehicle reaches the target deceleration as quickly, smoothly, and accurately as possible. Its output formula is: Equation (1) in, This indicates the magnitude of the braking force applied to the braking system; Indicates proportional gain; Indicates integral gain; Represents differential gain; This indicates the proportional term, which provides an immediate response to the current error between the actual deceleration and the target deceleration. This represents the integral term, used to eliminate the cumulative error between the actual deceleration and the target deceleration; This represents the differential term, used to eliminate the prediction error between the actual deceleration and the target deceleration. By adjusting... , , This can optimize the vehicle's deceleration process.

[0038] In one embodiment, the determination of the first risk level and the second risk level includes: determining a first collision prediction time between the target vehicle and the vehicle in front based on a first speed of the target vehicle, a second speed of the vehicle in front, and a first distance between the target vehicle and the vehicle in front; determining a second collision prediction time between the rear vehicle and the target vehicle based on the second speed, a third speed of the vehicle behind, and a second distance between the rear vehicle and the target vehicle; determining a first risk level based on the first collision prediction time and a preset mapping relationship; and determining a second risk level based on the second collision time and the mapping relationship; wherein the mapping relationship represents the correspondence between the collision prediction time and the risk level.

[0039] The first collision prediction time refers to the time required for the target vehicle to collide with the vehicle in front under the current driving conditions; the second collision prediction time refers to the time required for the vehicle to brake suddenly due to the risk of collision between the target vehicle and the vehicle in front, thus affecting the vehicles behind, i.e., the time required for the vehicles behind to collide with the target vehicle. In other words, the second collision prediction time is the collision prediction time determined based on the risk of collision between the target vehicle and the vehicle in front, and the impact of the target vehicle's braking on the vehicles behind.

[0040] Furthermore, the calculation of the second collision prediction time actually involves calculating the third relative speed between the rear vehicle and the target vehicle, and the second distance between the rear vehicle and the target vehicle when the target vehicle collides with the vehicle in front. This yields the second collision prediction time, specifically the ratio of the second distance to the third relative speed. The corresponding calculation formula is as follows: Equation (2) in, Indicates the second collision prediction time; This indicates the second distance between the vehicle behind and the target vehicle. This indicates the third relative speed between the vehicle behind and the target vehicle when the target vehicle collides with the vehicle in front. The formula for calculating the third relative velocity is: Equation (3) in, Indicates the third relative velocity; Indicates the third speed of the vehicle behind; Indicates the first speed of the target vehicle; Indicates the first collision prediction time; This represents the expected deceleration of the target vehicle, which is just enough to avoid a collision between the target vehicle and the vehicle in front. In other words, the target vehicle can reduce its first speed to the same as the second speed of the vehicle in front within the first collision prediction time according to the expected deceleration. The expected deceleration value is negative. therefore The result is the second speed of the vehicle in front. Therefore, the second collision prediction time between the vehicle behind and the target vehicle can be calculated directly based on the second speed of the vehicle in front, the third speed of the vehicle behind, and the second distance between the vehicle behind and the target vehicle.

[0041] In this embodiment, by calculating the collision prediction time between the target vehicle and the vehicle in front, and between the vehicle behind and the target vehicle, and combining the preset collision prediction time with the risk level mapping relationship, the risk levels of forward and rear collisions are determined respectively, thereby realizing real-time and quantitative assessment of the risk of front and rear collisions. In this way, through front and rear TTC (Time To Collision) modeling and risk mapping, reliable support is provided for the subsequent determination of braking strategies for overall protection capabilities.

[0042] For example, determining the first collision prediction time between the target vehicle and the vehicle in front based on the first speed of the target vehicle, the second speed of the vehicle in front, and the first distance between the target vehicle and the vehicle in front includes: calculating the difference between the first speed and the second speed to obtain a fourth relative speed; and calculating the ratio of the first distance to the fourth relative speed to obtain the first collision prediction time.

[0043] The fourth relative speed refers to the current relative speed between the target vehicle and the vehicle in front.

[0044] In this exemplary embodiment, the formula for calculating the first collision prediction time is: Equation (4) in, Indicates the first collision prediction time; This indicates the initial distance between the target vehicle and the vehicle in front. Indicates the first speed of the target vehicle; Indicates the second speed of the vehicle ahead; This represents the fourth relative velocity.

[0045] For example, determining the second collision prediction time between the rear vehicle and the target vehicle based on the second speed, the third speed of the rear vehicle, and the second distance between the rear vehicle and the target vehicle includes: calculating the difference between the third speed and the second speed to obtain a fifth relative speed; and calculating the ratio of the second distance to the fifth relative speed to obtain the second collision prediction time.

[0046] The fifth relative speed refers to the current relative speed between the vehicle behind and the vehicle in front.

[0047] In this exemplary embodiment, the formula for calculating the second collision prediction time is: Equation (5) in, Indicates the second collision prediction time; This indicates the second distance between the vehicle behind and the target vehicle. Indicates the third speed of the vehicle behind; Indicates the second speed of the vehicle ahead; This represents the fifth relative velocity.

[0048] In one possible embodiment, in the mapping relationship, if the collision prediction time is greater than a first time threshold, the corresponding risk level is low risk; if the collision prediction time is less than or equal to the first time threshold and greater than or equal to a second time threshold, the corresponding risk level is medium risk; and if the collision prediction time is less than the second time threshold, the corresponding risk level is high risk.

[0049] The first time threshold and the second time threshold can be obtained through experimental calibration. This application does not restrict the specific values ​​of the first time threshold and the second time threshold.

[0050] For example, the first time threshold is set to 5 seconds, and the second time threshold is set to 3 seconds. That is, if the collision prediction time is greater than 5 seconds, the corresponding risk level is low risk; if the collision prediction time is less than or equal to 5 seconds but greater than or equal to 3 seconds, the corresponding risk level is medium risk; and if the collision prediction time is less than 3 seconds, the corresponding risk level is high risk.

[0051] As one possible implementation, a low-risk level indicates that the probability of a collision between vehicles is low and the AEB system will not be triggered to perform emergency braking. A medium-risk level indicates that there is a certain probability of a collision between vehicles, and the AEB system needs to perform emergency braking based on a certain deceleration to avoid the collision. A high-risk level indicates that a collision between vehicles is inevitable, and the AEB system needs to perform emergency braking based on a certain deceleration to avoid the collision or reduce the damage from the collision.

[0052] In one embodiment, before determining the second risk level based on the second collision time and mapping relationship, the method further includes: obtaining the braking delay time of the following vehicle, wherein the braking delay time includes the driver's reaction time, the driver's braking operation time, and the vehicle's braking response time; calculating the difference between the second collision prediction time and the braking delay time, and using the difference as the final second collision prediction time, so as to determine the second risk level based on the final second collision prediction time.

[0053] Among them, the braking delay time is preset and is calibrated based on the driver's usual reaction characteristics and the vehicle's own braking performance, serving as the braking delay time for the following vehicle; the driver's reaction time refers to the time required for the driver of the following vehicle to perceive the target vehicle's deceleration and begin to make a braking intention; the driver's braking operation time refers to the time from when the driver of the following vehicle generates a braking intention to when the driver actually presses the brake pedal; and the vehicle braking response time refers to the delay time from when the driver of the following vehicle presses the brake pedal to when the vehicle actually generates effective braking force.

[0054] In this embodiment, considering the braking delay between the perception of danger and the actual generation of braking force by the vehicle behind, the calculated second collision prediction time is subtracted from the braking delay time before determining the second risk level, so as to obtain a second collision prediction time that is closer to the real situation, thereby improving the accuracy of the assessment of the risk of being rear-ended.

[0055] For example, the formula for calculating the final second collision prediction time is as follows: Equation (6) in, This indicates the final predicted time for the second collision; Indicates the third speed of the vehicle behind; This indicates the third relative speed between the vehicle behind and the target vehicle when the target vehicle collides with the vehicle in front. Indicates the driver's reaction time; Indicates the driver's braking operation time; This indicates the vehicle's braking response time.

[0056] In one embodiment, determining the target deceleration of the target vehicle based on the comparison result includes: if the comparison result meets a preset first condition, then determining the target deceleration based on the first speed of the target vehicle, the second speed of the vehicle in front, and the first distance between the target vehicle and the vehicle in front; if the comparison result meets a preset second condition, then obtaining the first collision prediction time between the target vehicle and the vehicle in front, and determining the target deceleration based on the first collision prediction time, the first speed, the third speed of the vehicle behind, and the extreme value of the deceleration of the vehicle behind; if the comparison result meets a preset third condition, then determining the target deceleration based on the first speed, the second speed, the third speed, the first distance, the second distance between the vehicle behind and the target vehicle, the first acceleration of the vehicle in front, and the second acceleration of the vehicle behind; wherein the first condition includes a first risk level higher than a second risk level, the second condition includes a first risk level lower than a second risk level, and the third condition includes a first risk level and a second risk level being the same.

[0057] Among them, the extreme deceleration value of the vehicle behind represents the maximum braking capacity of the vehicle behind.

[0058] In this embodiment, the comparison results include three scenarios: the first risk level is higher than the second risk level, the first risk level is lower than the second risk level, and the first risk level and the second risk level are the same. Considering that when the first risk level is higher than the second risk level, the probability of a collision in front is greater than that in the rear, priority is given to ensuring collision avoidance in front. Therefore, the target deceleration is determined directly based on the relative state between the vehicle in front and the vehicle itself. When the first risk level is lower than the second risk level, it indicates that the vehicle behind is more likely to rear-end the vehicle. In this case, sudden braking would increase the risk of being hit. Therefore, the extreme deceleration value of the vehicle behind and the first collision prediction time are introduced. Combined with the relative state between the vehicle behind and the vehicle itself, the target deceleration is determined to avoid the risk of being hit by the vehicle behind while trying to avoid the vehicle in front. When the first risk level is equal to the second risk level, it indicates that the probability of a collision in front and behind is equal. Therefore, comprehensive state information, namely the speed, distance, and acceleration of the vehicles in front and behind, is used to perform multi-vehicle cooperative kinematics modeling to find a target deceleration that can avoid a forward collision without causing a rear-end collision.

[0059] In this way, based on the comparison results of forward and backward risks, three different strategies are dynamically selected to determine the target deceleration of the target vehicle, breaking through the traditional braking logic that only faces the vehicle in front and improving the overall safety benefits of the AEB system.

[0060] For example, if the risk levels include low risk, medium risk, and high risk, then the first risk level and the second risk level satisfying the first condition include three cases: the first risk level is medium risk and the second risk level is low risk; the first risk level is high risk and the second risk level is low risk; the first risk level is high risk and the second risk level is medium risk. The first risk level and the second risk level satisfying the second condition include three cases: the first risk level is low risk and the second risk level is medium risk; the first risk level is low risk and the second risk level is high risk; the first risk level is medium risk and the second risk level is high risk. The first risk level and the second risk level satisfying the third condition include three cases: the first risk level and the second risk level are simultaneously low risk, medium risk, or high risk.

[0061] For example, determining the target deceleration based on the first speed of the target vehicle, the second speed of the vehicle in front, and the first distance between the target vehicle and the vehicle in front includes: calculating the difference between the first speed and the second speed to obtain a fourth relative speed; calculating the square of the fourth relative speed, and calculating the square value and the first distance to obtain the target deceleration.

[0062] In this exemplary embodiment, the formula for calculating the target deceleration is: Equation (7) in, This represents the target deceleration (also the expected deceleration mentioned above), and its value is negative. Indicates the second speed of the vehicle ahead; Indicates the first speed of the target vehicle; This indicates the initial distance between the target vehicle and the vehicle in front. This represents the fourth relative velocity.

[0063] Furthermore, regarding the situation of the target vehicle and the vehicle in front, it is assumed that the target vehicle needs to be within the first collision prediction time. As the vehicle decelerates until its relative velocity with the vehicle in front is zero, the first kinematic equation exists: Equation (8) in, This represents the relative final velocity between the target vehicle and the vehicle in front, which is 0. This indicates the initial relative velocity between the target vehicle and the vehicle in front. This represents the deceleration of the target vehicle, and is taken as a negative value. Indicates the distance between the target vehicle and the vehicle in front; Substituting the target vehicle's first speed, the vehicle in front's second speed, the target vehicle's target deceleration, and the first distance between the target vehicle and the vehicle in front, we can obtain: Equation (9) By transforming the above equation (9), we can obtain the above equation (7).

[0064] For example, determining the target deceleration based on the first collision prediction time, the first speed, the third speed of the following vehicle, and the deceleration extreme value of the following vehicle includes: constructing a second kinematic equation based on the first collision prediction time, the first speed, the third speed, and the deceleration extreme value; and solving for the target deceleration based on the second kinematic equation.

[0065] The second kinematic equation characterizes the target vehicle's deceleration to its speed at maximum braking capacity during the first collision prediction time, i.e., the time during which the target vehicle brakes and decelerates. The target deceleration of the target vehicle, calculated using this second kinematic equation, can prevent collisions between the target vehicle and vehicles behind it, while avoiding collisions between the target vehicle and the vehicle in front.

[0066] In this exemplary embodiment, the second kinematic equation is: Equation (10) in, Indicates the first speed of the target vehicle; This represents the target deceleration, and its value is negative. Indicates the first collision prediction time; Indicates the third speed of the vehicle behind; This represents the extreme value of the deceleration of the vehicle behind, and is taken as negative.

[0067] In one possible embodiment, considering the braking delay between the rear vehicle's perception of danger and the actual generation of braking force, the actual deceleration time of the rear vehicle needs to be reduced by the braking delay time of the rear vehicle based on the first collision prediction time to ensure the reliability of the obtained target deceleration. The final second kinematic equation is: Equation (11) in, Indicates the first speed of the target vehicle; This represents the target deceleration, and its value is negative. Indicates the first collision prediction time; Indicates the third speed of the vehicle behind; This represents the extreme value of the deceleration of the vehicle behind, and is taken as a negative value; Indicates the driver's reaction time; Indicates the driver's braking operation time; This indicates the vehicle's braking response time.

[0068] In one possible embodiment, when the following vehicle needs to avoid colliding with the target vehicle within the second collision prediction time, the target deceleration is determined based on the velocity and displacement relationship between the following vehicle and the target vehicle.

[0069] As one possible embodiment, the speed relationship is: Equation (12) in, Indicates the first speed of the target vehicle; This represents the target deceleration, and its value is negative. Indicates the second collision prediction time; Indicates the third speed of the vehicle behind; This represents the extreme value of the deceleration of the vehicle behind, and is taken as a negative value; Indicates the driver's reaction time; Indicates the driver's braking operation time; Indicates the vehicle's braking response time; The displacement relationship is as follows: Equation (13) in, This indicates the second distance between the vehicle behind and the target vehicle; Indicates the third speed of the vehicle behind; Indicates the braking delay time. ; This represents the extreme value of the deceleration of the vehicle behind, and is taken as a negative value; Indicates the second collision prediction time; Indicates the first speed of the target vehicle; This represents the target deceleration of the target vehicle; Combining equations (12) and (13) above, we can obtain the solution. .

[0070] In one embodiment, the second condition further includes a first risk level of medium risk; the third condition further includes both the first risk level and the second risk level being high risk; after determining the first risk level, the method further includes: if the first risk level is low risk, then setting the target deceleration to a preset deceleration threshold; determining the target deceleration of the target vehicle based on the comparison result further includes: if both the first risk level and the second risk level are medium risk, then determining the target deceleration based on the first speed, the second speed, and the first distance.

[0071] The preset deceleration threshold can be set through experimental calibration and is used for normal braking of the vehicle rather than emergency braking when the collision risk is within a controllable range.

[0072] In this embodiment, the second condition also includes that the first risk level is medium risk level. That is, the target deceleration is determined based on the first collision prediction time, the first speed, the third speed of the rear vehicle, and the extreme value of the deceleration of the rear vehicle only when the first risk level is medium risk level and the second risk level is high risk level. The third condition also includes that both the first risk level and the second risk level are high risk level. That is, the target deceleration is determined based on the first speed, the second speed, the third speed, the first distance, the second distance between the rear vehicle and the target vehicle, the first acceleration of the front vehicle, and the second acceleration of the rear vehicle only when both the first risk level and the second risk level are high risk level.

[0073] In addition, if the first risk level is low risk level, the target deceleration is set to a preset deceleration threshold. That is, when the first risk level is low risk level and the second risk level is one of low risk level, medium risk level and high risk level, the target vehicle is controlled to decelerate based on the deceleration threshold. When both the first risk level and the second risk level are medium risk level, the target deceleration is also determined based on the first speed, the second speed and the first distance. The calculation formula is the above formula (7).

[0074] In this embodiment, if the first risk level is low, it indicates that the collision risk is within a controllable range, and the target vehicle can decelerate using normal braking without the need for emergency braking. Therefore, the second condition does not include the two cases where the first risk level is low and the second risk level is medium or high. That is, only when the first risk level is medium and the second risk level is high is the extreme deceleration value of the following vehicle and the first collision prediction time introduced, combined with the relative state of the following vehicle and the vehicle itself, to determine the target deceleration, so as to avoid the risk of being hit by the following vehicle while trying to avoid the vehicle in front. The third condition does not include the case where both the first and second risk levels are low or medium. That is, only when both the first and second risk levels are high is multi-vehicle cooperative kinematic modeling performed based on comprehensive state information, namely the speed, distance, and acceleration of the vehicles in front and behind, to find a target deceleration that can avoid a forward collision without causing a rear-end collision. Considering that both the first and second risk levels are medium risk levels, there is still a certain risk of collision with the vehicle in front, requiring emergency braking to slow down, but the impact on vehicles behind is relatively small. Therefore, the target deceleration is determined directly based on the relative state between the vehicle in front and the vehicle itself.

[0075] In this way, by further refining the risk level combinations and corresponding control strategies, more precise braking decisions are achieved, thereby improving the overall safety benefits of the AEB system.

[0076] In one embodiment, if the comparison result satisfies a preset third condition, the method for determining the target deceleration includes: determining a first deceleration of the target vehicle based on a first speed, a second speed, a first distance, and a first acceleration, wherein the first deceleration represents the minimum deceleration required by the target vehicle to avoid colliding with the vehicle in front; determining a second deceleration of the target vehicle based on a first speed, a third speed, a second distance, and a second acceleration, wherein the second deceleration represents the maximum deceleration required by the target vehicle to avoid colliding with the vehicle behind; if there is a safe deceleration range between the first deceleration and the second deceleration, then the target deceleration is determined within the safe deceleration range; if there is no safe deceleration range between the first deceleration and the second deceleration, then a collision cost function is constructed based on the first relative speed when the target vehicle collides with the vehicle in front and the second relative speed when the vehicle behind collides with the target vehicle, and the target deceleration is solved with the goal of minimizing the collision cost.

[0077] In this embodiment, the target deceleration is denoted as... The first deceleration is The first deceleration is All values ​​are negative. The target vehicle can avoid colliding with the vehicle in front. This can prevent collisions between vehicles behind and the target vehicle; conversely, The target vehicle cannot avoid colliding with the vehicle in front. It is inevitable that a collision will occur between the vehicle behind and the target vehicle. Considering and The size of the case makes and There may be an overlap, meaning there exists a safe deceleration range. In this case, there exists... This ensures that the target vehicle will not collide with any vehicles in front or behind it, but if and There is no intersection, meaning there is no safe deceleration range. In this case, the target vehicle will collide with both the vehicles in front and behind it, and a safe deceleration range needs to be found. This minimizes the overall collision damage.

[0078] For example, -8 m / s² If the speed is -9 m / s², then it exists. Once the safe deceleration range is determined, a value can be set as the target deceleration within that range. -9 m / s² -8 m / s², that is Since the deceleration rate must be both less than -9 m / s² and greater than -8 m / s², there is no safe deceleration range. Therefore, a collision cost function is constructed, and the target deceleration is solved with the goal of minimizing the collision cost, so that the overall collision damage is reduced to the minimum.

[0079] In this way, by constructing a safe range between the minimum deceleration required for forward collision avoidance and the maximum deceleration allowed for rear-end collision prevention, a coordinated balance between front and rear risks is achieved. When the safe range does not exist, a collision cost function is further introduced to solve for the optimal deceleration with the goal of minimizing the overall collision loss. Thus, when there is an unavoidable risk of collision with the vehicle in front and behind, the collision damage is minimized by minimizing the collision speed.

[0080] For example, based on the first speed, the second speed, the first distance, and the first acceleration, the first deceleration of the target vehicle is determined, and the expression for the first deceleration is: Equation (14) in, Indicates the first deceleration; Indicates the first velocity; Indicates the second speed; Indicates the first distance; This indicates the first acceleration.

[0081] For example, based on the first speed, the third speed, the second distance, and the second acceleration, the second deceleration of the target vehicle is determined, and the expression for the second deceleration is: Equation (15) in, Indicates the second deceleration; Indicates the first velocity; Indicates the third speed; Indicates the second distance; This indicates the second acceleration.

[0082] For example, a collision cost function is constructed based on the first relative velocity when the target vehicle collides with the vehicle in front and the second relative velocity when the vehicle behind collides with the target vehicle. The expression for the collision cost function is as follows: Equation (16) in, Indicates the target vehicle is decelerating. The cost of collision at that time; This indicates the initial relative velocity of the target vehicle when it collides with the vehicle in front. This indicates the second relative velocity when the vehicle behind collides with the target vehicle.

[0083] In this exemplary embodiment, to minimize the collision cost and solve for the target deceleration, it is first necessary to determine the search interval for the target deceleration, that is, to determine the conditions for a preceding vehicle collision based on the relative kinematics model: Equation (17) in, Indicates the second speed; Indicates the first velocity; Indicates the first acceleration; Indicates the first deceleration; Indicates the first distance; The deformation yields: Equation (18) Conditions for determining the possibility of a rear-end collision: Equation (19) in, Indicates the first velocity; Indicates the third speed; Indicates the second deceleration; Indicates the second acceleration; Indicates the second distance; The deformation yields: Equation (20) Therefore, the deceleration range where collisions can occur from both the front and rear, i.e., the search range for the target deceleration, is: Equation (21) Then, based on the relative kinematics model, the collision time function is determined. The collision time function between the target vehicle and the vehicle in front is: Equation (22) The collision time function between the rear vehicle and the target vehicle is: Equation (23) Next, the collision cost function can be further expressed as: Equation (24) Finally, the golden section method (a one-dimensional deterministic search algorithm that does not require derivatives) is used to find a solution within the aforementioned search interval that satisfies... smallest The target deceleration is determined, that is, the left side of the search interval is defined as... Define the right side as And calculate the two midpoints according to the golden ratio. , Then calculate and ,if Then update , Recalculate Otherwise, let , Recalculate ,until (e.g., 0.01 m / s²), then the optimal value is obtained. Thus, the target deceleration is obtained.

[0084] In one embodiment, the method for obtaining speed and distance information includes: acquiring environmental data of the target vehicle, the environmental data including a first environmental image in front of the target vehicle and a second environmental image behind the target vehicle; inputting the first environmental image and the second environmental image into a pre-constructed target detection model to obtain a first distance between the target vehicle and the vehicle in front, and a second distance between the vehicle behind and the target vehicle, thereby obtaining distance information, wherein the target detection model is trained by environmental image samples collected under various driving environments, containing various vehicles and labeled with corresponding position and distance labels; determining the second speed and first acceleration of the vehicle in front based on the acquisition time interval of consecutive first environmental images and the change value of the first distance in consecutive first environmental images, and determining the third speed and second acceleration of the vehicle behind based on the acquisition time interval of consecutive second environmental images and the change value of the second distance in consecutive second environmental images, thereby obtaining speed information.

[0085] The first environmental image can be obtained through a front-view camera, and the second environmental image can be obtained through a rear-view camera.

[0086] In this embodiment, the distance between vehicles is obtained in real time from the images of the surrounding environment based on a vision-based target detection model. The speed and acceleration of the vehicles in front and behind are calculated by combining the distance changes and time intervals between consecutive frames. This achieves accurate perception of the vehicles in front and behind as well as the driving status information, providing reliable input for collision risk assessment and adaptive braking decision-making.

[0087] Please see Figure 3 , Figure 3 This is a schematic diagram illustrating the structure of a front / rear view camera, as shown in an exemplary embodiment of this application. Figure 3 As shown, the front / rear-view camera includes a lens, a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor, an image signal processor, a serializer, a power supply, and a memory. Its working principle is as follows: Light reflected from the surface of an object (such as a vehicle) is focused by the lens, passes through a filter, and enters the CMOS image sensor. The CMOS image sensor converts the received light signal into an electrical signal and transmits it to the image processor. The image processor performs image filtering and enhancement on the electrical signal, and the serializer serializes the processed image information before transmission. The power supply powers the internal components of the camera, and the memory stores the camera's intrinsic parameter data and executable code.

[0088] Please see Figure 4 , Figure 4 This is a flowchart illustrating an exemplary embodiment of this application, showing the acquisition of environmental images. For example... Figure 4 As shown, the steps for acquiring environmental images include: first, powering on the camera; after powering on the camera, initializing the camera; after initialization, focusing the light reflected from objects; then converting the light signal into an electrical signal; next, performing image filtering and enhancement on the electrical signal; and finally, serializing the processed image information to obtain the environmental image.

[0089] For example, while CNN (Convolutional Neural Network) has powerful feature extraction capabilities and can extract rich feature information from images, its ability to model sequential data is limited. RNN (Recurrent Neural Network), on the other hand, has certain sequence modeling capabilities but suffers from problems such as gradient vanishing and gradient exploding. Therefore, the object detection model adopts the Transformer network, which has powerful sequence modeling capabilities and a global receptive field, overcoming the shortcomings of CNN and RNN, thereby ensuring accurate perception of vehicles in front and behind as well as driving status information.

[0090] In this exemplary embodiment, the Transformer network mainly consists of an encoder and a decoder. The encoder is used to extract feature information from the image, and the decoder is used to determine the positions of vehicles ahead and behind and the distance to the target vehicle based on the encoder's output. The encoder is composed of multiple identical layers stacked together, each layer including two sub-layers: a multi-head self-attention mechanism and a feedforward neural network. The decoder is also composed of multiple identical layers stacked together, each layer including three sub-layers: a multi-head self-attention mechanism, an encoder-decoder attention mechanism, and a feedforward neural network.

[0091] In this exemplary embodiment, for training the object detection model, a large number of environmental image samples from the front / rear-view cameras of automobiles are first collected and labeled, i.e., the positions and distances of various vehicles are labeled. Then, the labeled dataset is divided into training, validation, and test sets to train the object detection model. The environmental image samples include images containing various vehicles collected under various driving environments, including urban roads, highways, rural roads, and environments under different weather and lighting conditions, such as sunny, cloudy, rainy, snowy, daytime, and nighttime. Additionally, the labeled targets in the images may include common obstacles such as traffic signs and traffic lights for obstacle recognition, ensuring the accuracy of vehicle identification. Furthermore, data augmentation can be performed on the environmental image samples, such as geometric transformations, color transformations, and noise addition, thereby improving the robustness, generalization ability, and noise resistance of the object detection model, and making the object detection model more adaptable to changes in lighting, reducing the impact of lighting on vehicle detection.

[0092] For example, the encoder's input layer takes sample images as input and normalizes them to ensure the consistency and standardization of the input data; the encoder's multi-head self-attention layer, as the core of the Transformer network, captures and learns global feature information from the sample images; the encoder's feedforward neural network layer consists of two linear transformations and an activation function, assuming the input is... Then the calculation formula for the feedforward neural network is: ,in , It is a weight matrix. , It is a bias term. It is the activation function; in the encoder's residual connections and layer normalization, the output of the residual connection is... Let the input be The formula for calculating layer normalization is: ,in , These are the mean and standard deviation of the input, respectively. It is a small constant used to prevent the denominator from being zero.

[0093] For example, the decoder's input layer takes the encoder's output as input, and its output is a feature vector containing global feature information of the input image. Let the encoder's output be... ,in It is the sequence length. This is the feature dimension. Appropriate processing of the encoder's output, such as adding positional encoding, ensures that the decoder can correctly utilize the encoder's output information. The formula for calculating positional encoding is: , ,in It is a position index. It is a dimension index; the multi-head self-attention layer of the decoder is similar to the multi-head self-attention layer in the encoder, but the multi-head self-attention layer in the decoder not only considers the relationship between the current position and other positions, but also the relationship between the current position and the corresponding position of the encoder output, so as to better utilize the feature information extracted by the encoder and provide the accuracy of prediction of the position and distance of vehicles in front and behind; the output layer of the decoder is a fully connected layer to convert the final output of the decoder into the prediction results of the position and distance of vehicles in front and behind.

[0094] For example, for training an object detection model, the cross-entropy loss function and A combination of loss functions is used as the loss function; let the cross-entropy loss be... ,in, The sample belongs to the category specified in the true label. The probability, The model predicts the category to which the sample belongs. The probability of; The loss function includes location loss and distance loss. Let the location loss function be... For the coordinates of the prediction box coordinates of the real bounding box , Let the distance loss function be... For predicted distance and the actual distance , The combined loss function is: ),in, , Cross-entropy loss and The weighting coefficients of the loss.

[0095] For example, stochastic gradient descent is used to optimize the parameters of a Transformer network. This is achieved by calculating the gradient of the loss function with respect to the network parameters, and then updating the parameters in the reverse direction of the gradient to minimize the loss function for the network parameters. In each iteration, its update formula is: ,in, It's the learning rate. It is a loss function For parameters The gradient.

[0096] Please see Figure 5 , Figure 5 This is a flowchart illustrating a specific vehicle braking control method as shown in an exemplary embodiment of this application. Figure 5 As shown, this specific vehicle braking control method is executed by an automatic emergency braking system. The working logic of this automatic emergency braking system includes three parts: sensing, control, and execution. In the sensing logic part, environmental information in front of and behind the vehicle is collected by the front and rear cameras and sent to the control logic part. In the control logic part, the system first senses the vehicles in front and behind based on the environmental information to obtain their status information. At the same time, it detects the vehicle's operating status. Then, based on the status information of the vehicles in front and behind and the vehicle's operating status, it assesses the collision risk and, combined with the assessment result and the vehicle's operating status, performs deceleration control. Finally, it sends the deceleration control request to the execution logic part. In the execution logic part, the system controls the deceleration actuator to perform the deceleration operation according to the deceleration control request, thereby achieving vehicle deceleration.

[0097] Please see Figure 6 , Figure 6 This is a flowchart illustrating another specific vehicle braking control method as shown in an exemplary embodiment of this application. Figure 6As shown, the specific vehicle braking control method includes: first, powering on the controller, and then initializing the controller after powering on. After initialization, receiving data from the front / rear view cameras and simultaneously collecting the vehicle's operating status; then, determining the status information of the vehicles in front and behind based on the data from the front / rear view cameras, and combining the status information of the vehicles in front and behind with the operating status of the vehicle to determine the collision risk. If there is a collision risk, generating a vehicle deceleration request based on the target deceleration, and finally executing the deceleration request to achieve vehicle deceleration.

[0098] The aforementioned vehicle braking control method first acquires driving status information, including the speed information of the target vehicle, the vehicle in front, and the vehicle behind, as well as the distance information between the target vehicle and the vehicle in front, and between the vehicle behind and the target vehicle. Then, based on the speed and distance information, it determines the first risk level of a collision between the target vehicle and the vehicle in front, and the second risk level of a collision between the target vehicle and the vehicle behind. Next, it compares the risk levels of the first and second risk levels and determines the target deceleration of the target vehicle based on the comparison result. Finally, it controls the target vehicle to brake based on the target deceleration. By considering the states of the vehicle in front, the vehicle itself, and the vehicles behind, as well as the distances between the vehicles, and simultaneously judging the collision risk levels between the vehicle itself and the vehicle in front, and between the vehicle behind and the vehicle itself, it comprehensively considers the risk levels of front and rear collisions, adaptively determines the braking deceleration of the vehicle itself, and brakes accordingly. This avoids the risk of being rear-ended by the vehicle behind by only focusing on the collision with the vehicle in front, thus improving driving safety.

[0099] Please see Figure 7 , Figure 7 This is a block diagram illustrating a vehicle braking control system as an exemplary embodiment of this application. The system can be applied to... Figure 1 The implementation environment shown is intended to illustrate the system, but it should be understood that the system can also be applied to other exemplary implementation environments. This embodiment does not limit the implementation environment to which the system is applicable.

[0100] like Figure 7 As shown, in an exemplary embodiment, the vehicle braking control system 700 includes at least a data acquisition module 710, a level determination module 720, a deceleration calculation module 730, and a braking control module 740, which are described in detail below: The data acquisition module 710 is used to acquire driving status information, which includes the speed information of the target vehicle, the vehicle in front and the vehicle behind, as well as the distance information between the target vehicle and the vehicle in front, and between the vehicle behind and the target vehicle. The risk level determination module 720 is used to determine the first risk level of a collision between the target vehicle and the vehicle in front, and the second risk level of a collision between the vehicle behind and the target vehicle, based on speed and distance information. The deceleration calculation module 730 is used to compare the risk levels of the first risk level and the second risk level, and determine the target deceleration of the target vehicle based on the comparison result. The braking control module 740 is used to control the target vehicle to brake based on the target deceleration.

[0101] It should be noted that the vehicle braking control system provided in the above embodiments and the vehicle braking control method provided in the above embodiments belong to the same concept. The content of the operation performed by each module has been described in detail in the method embodiments, and will not be repeated here.

[0102] This application also provides an on-board device that uses the vehicle braking control method as described above, or includes the vehicle braking control system as described above.

[0103] This application also provides a vehicle including a vehicle braking control system as described above, or including on-board equipment as described above.

[0104] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of an in-vehicle device provided in one embodiment of this application. Figure 8 A schematic diagram of a computer system suitable for implementing the vehicle-mounted device of the embodiments of this application is shown. It should be noted that... Figure 8 The computer system 800 of the vehicle-mounted device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0105] like Figure 8 As shown, the computer system 800 includes a Central Processing Unit (CPU) 801, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on programs stored in Read-Only Memory (ROM) 802 or programs loaded from storage portion 808 into Random Access Memory (RAM) 803. The RAM 803 also stores various programs and data required for system operation. The CPU 801, ROM 802, and RAM 803 are interconnected via a bus 804. An Input / Output (I / O) interface 805 is also connected to the bus 804.

[0106] The following components are connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 810 as needed so that computer programs read from it can be installed into storage section 808 as needed.

[0107] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by central processing unit (CPU) 801, it performs various functions defined in the system of this application.

[0108] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A vehicle brake control method characterized by, The method comprises: obtaining driving state information, the driving state information comprising speed information of a target vehicle, a front vehicle and a rear vehicle, and distance information between the target vehicle and the front vehicle and between the rear vehicle and the target vehicle; determining a first risk level of a collision between the target vehicle and the front vehicle and a second risk level of a collision between the rear vehicle and the target vehicle according to the speed information and the distance information; comparing the risk levels of the first risk level and the second risk level, and determining a target deceleration of the target vehicle according to a comparison result; controlling the target vehicle to brake according to the target deceleration.

2. The vehicle brake control method according to claim 1, characterized by, The determination of the first risk level and the second risk level comprises: determining a first collision prediction time of the target vehicle and the front vehicle according to a first speed of the target vehicle, a second speed of the front vehicle and a first distance between the target vehicle and the front vehicle, and determining a second collision prediction time of the rear vehicle and the target vehicle according to the second speed, a third speed of the rear vehicle and a second distance between the rear vehicle and the target vehicle; determining the first risk level according to the first collision prediction time and a preset mapping relationship, and determining the second risk level according to the second collision time and the mapping relationship; wherein the speed information comprises the first speed, the second speed and the third speed, the distance information comprises the first distance and the second distance, and the mapping relationship represents a corresponding relationship between a collision prediction time and a risk level.

3. The vehicle brake control method according to claim 2, characterized by, Before determining the second risk level according to the second collision time and the mapping relationship, the method further comprises: obtaining a brake delay time of the rear vehicle, wherein the brake delay time comprises a driver reaction time, a driver brake operation time and a vehicle brake response time; calculating a difference between the second collision prediction time and the brake delay time, and taking the difference as a final second collision prediction time, so as to determine the second risk level according to the final second collision prediction time.

4. The vehicle brake control method according to claim 1, characterized by Determining the target deceleration of the target vehicle according to the comparison result comprises: if the comparison result satisfies a preset first condition, determining the target deceleration according to the first speed of the target vehicle, the second speed of the front vehicle and the first distance between the target vehicle and the front vehicle; if the comparison result satisfies a preset second condition, obtaining a first collision prediction time of the target vehicle and the front vehicle, and determining the target deceleration according to the first collision prediction time, the first speed, the third speed of the rear vehicle and a deceleration extreme value of the rear vehicle; if the comparison result satisfies a preset third condition, determining the target deceleration according to the first speed, the second speed, the third speed, the first distance, a second distance between the rear vehicle and the target vehicle, a first acceleration of the front vehicle and a second acceleration of the rear vehicle. The first condition comprises that the first risk level is higher than the second risk level, the second condition comprises that the first risk level is lower than the second risk level, and the third condition comprises that the first risk level is the same as the second risk level. The speed information further comprises the deceleration extreme value, the first acceleration and the second acceleration.

5. The vehicle brake control method according to claim 4, characterized by The second condition further comprises that the first risk level is a medium risk level. The third condition further comprises that the first risk level and the second risk level are both high risk levels. After determining the first risk level, if the first risk level is a low risk level, the target deceleration is set as a preset deceleration threshold. According to the comparison result, the target deceleration of the target vehicle is determined, and the determination further comprises that if the first risk level and the second risk level are both medium risk levels, the target deceleration is determined according to the first speed, the second speed and the first distance.

6. The vehicle brake control method according to claim 4 or 5, characterized by If the comparison result satisfies a preset third condition, the target deceleration is determined in the following manner: According to the first speed, the second speed, the first distance and the first acceleration, a first deceleration of the target vehicle is determined, wherein the first deceleration represents a minimum deceleration required by the target vehicle to avoid a collision with the front vehicle; According to the first speed, the third speed, the second distance and the second acceleration, a second deceleration of the target vehicle is determined, wherein the second deceleration represents a maximum deceleration required by the target vehicle to avoid a collision with the rear vehicle; If there is a safe deceleration interval between the first deceleration and the second deceleration, the target deceleration is determined in the safe deceleration interval; If there is no safe deceleration interval between the first deceleration and the second deceleration, a collision cost function is constructed according to a first relative speed when the front vehicle collides with the target vehicle and a second relative speed when the rear vehicle collides with the target vehicle, and the target deceleration is solved by minimizing the collision cost.

7. The vehicle brake control method according to any one of claims 1 to 5, characterized by The speed information and the distance information are obtained in the following manner: environmental data of the target vehicle is acquired, wherein the environmental data comprises a first environmental image in front of the target vehicle and a second environmental image behind the target vehicle; the first environmental image and the second environmental image are input into a pre-constructed target detection model to obtain a first distance between the target vehicle and the front vehicle and a second distance between the target vehicle and the rear vehicle, thereby obtaining the distance information, wherein the target detection model is trained by environmental image samples collected in various driving environments, containing various vehicles and labeled with corresponding position labels and distance labels; according to a sampling time interval of consecutive first environmental images and a change value of the first distance in consecutive first environmental images, a second speed and a first acceleration of the front vehicle are determined, and according to a sampling time interval of consecutive second environmental images and a change value of the second distance in consecutive second environmental images, a third speed and a second acceleration of the rear vehicle are determined, thereby obtaining the speed information.

8. A vehicle brake control system characterized by comprising: The system comprises: a data acquisition module configured to acquire driving state information, the driving state information comprising speed information of a target vehicle, a front vehicle and a rear vehicle, and distance information between the target vehicle and the front vehicle and between the rear vehicle and the target vehicle; a level determination module configured to determine a first risk level of a collision between the target vehicle and the front vehicle and a second risk level of a collision between the rear vehicle and the target vehicle according to the speed information and the distance information; a deceleration calculation module configured to compare the risk levels of the first risk level and the second risk level, and determine a target deceleration of the target vehicle according to a comparison result; a brake control module configured to control the target vehicle to brake according to the target deceleration.

9. An in-vehicle device characterized by comprising: The vehicle brake control method according to any one of claims 1 to 7, or the vehicle brake control system according to claim 8.

10. A vehicle characterized by comprising: The vehicle brake control system according to claim 8, or the vehicle-mounted device according to claim 9.

Images