Vehicle braking decision method and device, electronic equipment and storage medium

Abstract

This application discloses a vehicle braking decision-making method, device, electronic equipment, and storage medium, comprising: establishing a style index model of the target vehicle based on the target vehicle's index prediction results; determining the target vehicle's payoff function based on the target vehicle's style index model, and determining the self-vehicle's payoff function based on the collision probability relationship; determining a collision probability coefficient based on the target vehicle's payoff function and the self-vehicle's payoff function; and triggering vehicle braking when the collision probability coefficient meets the conditions. Based on asymmetric game theory and Nash equilibrium theory, this application determines the collision probability coefficient by constructing a target vehicle style index model and payoff function, enabling the AEB system to make accurate and efficient braking decisions to avoid hazards in emergency situations, effectively improving driving comfort while meeting vehicle driving safety requirements.

Description

Technical Field

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

[0002] In emergency situations where a collision is imminent, delayed driver reaction often leads to collisions or rear-end collisions with surrounding vehicles. In such cases, the AEB (Autonomous Emergency Braking) system is crucial for identifying collision risks in advance and making the correct braking decision. Currently, the basis for braking decisions in AEB systems is not entirely consistent; traditional decision-making models in existing technologies typically use collision time or safe collision distance as the basis for control decisions.

[0003] However, under complex operating conditions, traditional decision-making models cannot achieve dynamic evaluation and precise adjustment of braking decisions, resulting in inaccurate judgments from the system. This leads to slow response speeds for the vehicle, making it prone to braking or releasing too early or too late, which seriously affects the driver's comfort experience and further increases the risk of collisions between the vehicle and other vehicles. Summary of the Invention

[0004] This application provides a vehicle braking decision-making method, device, electronic device, and storage medium to achieve the technical effect of meeting vehicle safe driving requirements and enabling the AEB system to accurately and efficiently control and execute emergency braking decisions.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] According to one aspect of this application, a vehicle braking decision method is provided, the method comprising:

[0007] Based on the target vehicle's index prediction results, a style index model for the target vehicle is established.

[0008] Based on the style index model of the target vehicle, determine the revenue function of the target vehicle, and based on the collision probability relationship of the vehicle, determine the revenue function of the vehicle.

[0009] The collision probability coefficient is determined based on the target vehicle's payoff function and the autonomous vehicle's payoff function.

[0010] When the collision probability coefficient meets the conditions, the vehicle braking is triggered.

[0011] Furthermore, the step of establishing a style index model for the target vehicle based on the target vehicle's index prediction results also includes:

[0012] Based on the target vehicle's current indicator prediction results and the target vehicle's style index model from the previous moment, a style index model for the target vehicle at the current moment is established. The indicator prediction results include at least one of the following: the target vehicle's safety indicator, the target vehicle's comfort indicator, and the target vehicle's efficiency indicator.

[0013] Further, determining the revenue function of the target vehicle based on the style index model of the target vehicle includes:

[0014] Based on the style index in the style index model of the target vehicle, the revenue function of the target vehicle is determined. The revenue function of the target vehicle includes a first factor, a second factor, and a third factor. The first factor is related to the safety index in the target vehicle's index prediction results, the second factor is related to the comfort index in the target vehicle's index prediction results, and the third factor is related to the efficiency index in the target vehicle's index prediction results.

[0015] Furthermore, determining the vehicle's revenue function based on the vehicle's collision probability relationship includes:

[0016] Based on the collision probability relationship of the vehicle, the benefit function of the vehicle is determined. The benefit function of the vehicle includes a fourth factor, a fifth factor, and a sixth factor. The fourth factor is related to the collision probability relationship. The fifth factor is related to the collision probability relationship and the comfort index in the target vehicle's index prediction results. The sixth factor is related to the collision probability relationship and the efficiency index in the target vehicle's index prediction results.

[0017] Further, based on the payoff function of the target vehicle and the payoff function of the self-vehicle, the collision probability coefficient is determined, including:

[0018] Based on the profit function of the target vehicle and the profit function of the self-vehicle, construct the optimal profit objective function;

[0019] The collision probability coefficient is determined based on the optimal profit objective function.

[0020] Furthermore, determining the collision probability coefficient based on the target vehicle's payoff function and the vehicle's payoff function also includes:

[0021] When a collision occurs, the collision probability coefficient is 1; when no collision occurs, the collision probability coefficient is 0.

[0022] Furthermore, triggering vehicle braking when the collision probability coefficient meets the condition includes:

[0023] When the collision probability coefficient is not less than 0.8, the vehicle braking is triggered;

[0024] When the collision probability coefficient is less than 0.5, the vehicle braking is canceled.

[0025] According to a second aspect of this application, a vehicle braking decision device is provided, the device comprising:

[0026] A module is established to build a style index model for the target vehicle based on the indicator prediction results of the target vehicle.

[0027] The first determining module is used to determine the benefit function of the target vehicle based on the style index model of the target vehicle, and to determine the benefit function of the self-vehicle based on the collision probability relationship of the self-vehicle.

[0028] The second determining module is used to determine the collision probability coefficient based on the revenue function of the target vehicle and the revenue function of the self vehicle.

[0029] The triggering module is used to trigger vehicle braking when the collision probability coefficient meets the conditions.

[0030] According to a third aspect of this application, an electronic device is provided, comprising: a processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform a vehicle braking decision method as described in any of the preceding claims.

[0031] According to a fourth aspect of this application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores one or more programs that, when executed by a processor, implement the vehicle braking decision method as described in any of the preceding claims.

[0032] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects:

[0033] Based on the target vehicle's index prediction results, a style index model for the target vehicle is established. Based on the target vehicle's style index model, the target vehicle's payoff function is determined, and the self-vehicle's payoff function is determined based on the collision probability relationship. Based on the target vehicle's payoff function and the self-vehicle's payoff function, a collision probability coefficient is determined. When the collision probability coefficient meets a certain condition, vehicle braking is triggered. This application, based on asymmetric game theory and Nash equilibrium theory, solves for the collision probability coefficient by constructing a target vehicle style index model and payoff function. This enables the AEB system to make accurate and efficient braking decisions to avoid hazards in emergency situations, effectively improving driving comfort while meeting vehicle safety requirements. Attached Figure Description

[0034] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0035] Figure 1 This is a flowchart illustrating a vehicle braking decision method in one embodiment of this application;

[0036] Figure 2 This is a schematic diagram of the vehicle braking decision device in one embodiment of this application;

[0037] Figure 3 This is a schematic diagram of the structure of an electronic device in one embodiment of this application;

[0038] Figure 4 This is a schematic diagram of the structure of a computer-readable storage medium in one embodiment of this application. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0040] AEB systems typically use collision time or safe collision distance as the sole indicator for warning or emergency braking decisions. However, due to the limited accuracy and stability of the perception module, the calculation of collision time and distance often becomes inaccurate, leading to deviations in the timing of system warnings and braking, thus affecting vehicle safety and comfort.

[0041] Based on this, the embodiments of this application provide a vehicle braking decision method to achieve the technical effect of meeting the requirements of vehicle driving safety and enabling the AEB system to accurately and efficiently control and execute emergency braking decisions.

[0042] The technical concept of this application lies in constructing a target vehicle style model and an AEB system decision model based on the ideas of asymmetric information game theory and Nash equilibrium theory. Game theory and Nash equilibrium game theory belong to a branch of mathematics and are used to analyze the strategies of decision-makers in competitive environments.

[0043] Game theory is a theory that uses rigorous mathematical models to study optimal decision-making problems under conflict and adversarial conditions. The essence of game theory is to study how decision-makers, given a specific information structure, make decisions to maximize their own utility. Asymmetric information game theory studies the optimal contract design problem under asymmetric information conditions. If any player's chosen strategy is optimal given that the strategies of all other players are fixed, then this combination is defined as a Nash equilibrium.

[0044] This application establishes a model using game theory and Nash equilibrium theory, and solves for the collision probability coefficient to determine the collision risk between the target vehicle and the vehicle itself. Simultaneously, it obtains the optimal strategy by establishing an optimal objective through game theory, thereby enabling the AEB system to make and execute the correct braking decision. The technical solution of this application enables the AEB system to make accurate and efficient braking decisions to avoid hazards in emergency situations, effectively improving driving comfort while meeting vehicle safety requirements.

[0045] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0046] like Figure 1 As shown, the method includes the following steps S110 to S140:

[0047] Step S110: Based on the target vehicle's index prediction results, establish the target vehicle's style index model.

[0048] In this embodiment of the application, when establishing the style index model, it is necessary to first obtain an evaluation set including index information based on the real-time operating status information of the target vehicle. Specifically, the state variables such as real-time speed, historical speed, real-time position, historical position, real-time offset angle, and historical offset angle of the target vehicle are transformed to obtain the evaluation set of the target vehicle. The evaluation set includes the safety index, comfort index, and efficiency index of the target vehicle.

[0049] Based on the aforementioned indicator information of the target vehicle, a style index model for the target vehicle is established. The vehicle style index is used to represent the operational behavior characteristics of the driver of the target vehicle in controlling the vehicle operation under real vehicle operating conditions. In this embodiment, by analyzing the vehicle operating status data, the vehicle driving style can be dynamically identified. Specifically, the driving style can be divided into conservative, moderate, efficient, etc.

[0050] The calculation methods involved in the target vehicle style index model are as follows:

[0051]

[0052] In the formula, t represents the current time, t-1 represents the previous time, and δ sIndicates safety indicators, δ c Indicator of comfort, δ e The efficiency index is represented by ψ(t), which represents the style index of the target vehicle at time t, and ψ(t-1) represents the style index of the target vehicle at time t-1.

[0053] In the style index model described above, the driving style of the target vehicle can be determined by solving for the style index ψ. A result of 0 represents conservative driving, in which case the vehicle is relatively safe; a result of 1 represents efficient driving, in which case the vehicle is relatively efficient; and a result of 0.5 represents moderate driving, in which case the vehicle is relatively comfortable.

[0054] Step S120: Determine the revenue function of the target vehicle based on the style index model of the target vehicle, and determine the revenue function of the self-vehicle based on the collision probability relationship of the self-vehicle.

[0055] In this application, "self-vehicle" refers to the vehicle that will make emergency braking decisions using the AEB system, and "target vehicle" refers to surrounding vehicles moving relative to the self-vehicle. In assisted driving scenarios, the self-vehicle can predict the operating state of the target vehicle through the AEB system and use vehicle information obtained by the perception module to determine whether a collision will occur between the self-vehicle and the target vehicle and perform corresponding braking control.

[0056] In one embodiment of this application, determining the revenue function of the target vehicle based on the style index model of the target vehicle includes: determining the revenue function of the target vehicle based on the style index in the style index model of the target vehicle.

[0057] Specifically, the revenue function for the target vehicle is constructed as follows:

[0058]

[0059] In the formula, t represents the current time, and k represents the number of different sampling times recorded. The value of k ranges from 0 to N natural numbers. It can be understood that any time can be taken as the current time t, and k is taken starting from 0 at time t to achieve time integration of the terms in parentheses and to calculate the revenue function.

[0060] In this embodiment, the payoff function of the target vehicle includes a first factor J. os Second factor J oc And the third factor J oe J os J oc J oe The function expressions are as follows:

[0061] J os(t)=V[1](t)

[0062] Jo c (t)=1-[V[2](t)-V[2](t-1)] 2

[0063]

[0064] In the above expressions, V[1], V[2], and V[3] represent the target vehicle evaluation centralized safety index δ, respectively. s Comfort index δ c High efficiency index δ e The index prediction results are given, where φ(t) represents the collision probability relationship of the vehicle at time t.

[0065] In this embodiment of the application, based on the fuzzy state estimation model of the target vehicle, the obtained state variables such as real-time speed, historical speed, real-time position, historical position, real-time offset angle, and historical offset angle of the target vehicle are transformed through a fuzzy transformation matrix to obtain the evaluation set of the target vehicle. The evaluation set includes the target vehicle's safety indicators, comfort indicators, and efficiency indicators.

[0066] Therefore, based on the above functional expression, it can be understood that the first factor J os The safety index δ in the target vehicle's index prediction results s Correlation, the second factor J oc The comfort index δ in the target vehicle's index prediction results c Related, the third factor J oe The efficiency index δ in the target vehicle's index prediction results e It is related to the collision probability φ(t).

[0067] Furthermore, in this embodiment of the application, determining the vehicle's revenue function based on the vehicle's collision probability relationship includes: determining the vehicle's revenue function based on the vehicle's collision probability relationship.

[0068] The revenue function for the self-driving car is as follows:

[0069]

[0070] In the formula, t represents the current time, and k represents the number of different sampling times recorded. The value of k ranges from 0 to N natural numbers. It can be understood that any time can be taken as the current time t, and the value of k starts from 0 at time t, so as to perform time integration on the terms in parentheses above and calculate the revenue function.

[0071] In this embodiment, the vehicle's revenue function includes a fourth factor J.ms Factor J, the fifth factor mc And the sixth factor J me J ms J mc J me The expressions are as follows:

[0072]

[0073]

[0074]

[0075] In the above expressions, V[2] and V[3] represent the target vehicle evaluation centralized comfort index δ, respectively. c High efficiency index δ e The index prediction results are given, where φ(t) represents the collision probability relationship of the vehicle at time t.

[0076] Therefore, based on the above expression, it can be understood that the fourth factor J... ms The fifth factor J is related to the value of φ. mc The relationship between the collision probability φ(t) and the comfort index δ in the target vehicle's index prediction results. c Related, the sixth factor J me The efficiency index δ in the collision probability relationship φ(t) and the target vehicle's index prediction results. e Related.

[0077] Step S130: Determine the collision probability coefficient based on the revenue function of the target vehicle and the revenue function of the self vehicle.

[0078] In this embodiment, the collision probability coefficients can be calculated using the benefit functions of the target vehicle and the self-vehicle. As mentioned earlier, the benefit functions of the target vehicle and the self-vehicle include a collision probability relationship φ(t). It can be understood that the calculated result of φ(t) corresponds to different collision probability coefficients and represents the probability of different collision risks.

[0079] Step S140: When the collision probability coefficient meets the condition, vehicle braking is triggered.

[0080] In one embodiment of this application, by pre-setting judgment conditions based on the value of the collision probability coefficient, the AEB system can make and execute corresponding braking decisions. For example, it is set that vehicle braking is triggered when the collision probability coefficient φ ≥ 0.8. In this embodiment, a target vehicle style index model and a braking decision model are established based on asymmetric game theory and Nash equilibrium theory. Simultaneously, the collision probability coefficient calculated by the model represents the risk of a collision based on the game outcome. When the collision probability coefficient is not less than 0.8, it indicates a high probability of a collision, requiring emergency braking to avoid harm. This application can make emergency braking decisions more accurately and efficiently while ensuring safety, effectively improving driving comfort.

[0081] In one embodiment of this application, the step of establishing the style index model of the target vehicle based on the indicator prediction results of the target vehicle further includes: establishing the style index model of the target vehicle at the current moment based on the indicator prediction results of the target vehicle at the current moment and the style index model of the target vehicle at the previous moment, wherein the indicator prediction results include at least one of the following: the safety index of the target vehicle, the comfort index of the target vehicle, and the efficiency index of the target vehicle.

[0082] Specifically, when establishing a style index model for the target vehicle, it is necessary to extract safety, comfort, and efficiency indicators from the evaluation set input by the system. As mentioned earlier, in the model, δ s Indicates safety indicators, δ c This indicates comfort index, and δ e Indicators of high efficiency.

[0083] In a preferred embodiment of this application, determining the collision probability coefficient based on the revenue function of the target vehicle and the revenue function of the self-vehicle includes: constructing an optimal revenue objective function based on the revenue function of the target vehicle and the revenue function of the self-vehicle; and determining the collision probability coefficient based on the optimal revenue objective function.

[0084] Since the collision probability relationship and collision probability coefficient are only related to the vehicle itself and are not controlled by the target vehicle, the total payoff function is maximized within a certain range of the collision probability coefficient. Based on game theory strategies, from the initial time t0 to t... f Integrating the payoff function at time step 1, we construct the optimal payoff objective function as follows:

[0085]

[0086] In the formula, J m Let J represent the revenue function of the autonomous vehicle. o This represents the revenue function for the target vehicle.

[0087] In the optimal benefit objective function, the only variable is the collision probability coefficient φ. In this embodiment, when φ ≥ 0.8, the probability of a collision is considered extremely high, and at this time, the AEB system triggers emergency braking.

[0088] In one embodiment of this application, determining the collision probability coefficient based on the revenue function of the target vehicle and the revenue function of the self-vehicle further includes: when a collision occurs, the collision probability coefficient = 1, and when no collision occurs, the collision probability coefficient = 0.

[0089] Furthermore, in one embodiment of this application, triggering vehicle braking when the collision probability coefficient meets the condition includes: triggering vehicle braking when the collision probability coefficient is not less than 0.8; and canceling vehicle braking when the collision probability coefficient is less than 0.5.

[0090] This application also provides a vehicle braking decision device 200 in its embodiments, such as... Figure 2 As shown, the device includes:

[0091] Module 210 is used to establish a style index model for the target vehicle based on the indicator prediction results of the target vehicle.

[0092] In this embodiment of the application, when establishing the style index model, it is necessary to first obtain an evaluation set including index information based on the real-time operating status information of the target vehicle. Specifically, the state variables such as real-time speed, historical speed, real-time position, historical position, real-time offset angle, and historical offset angle of the target vehicle are transformed to obtain the evaluation set of the target vehicle. The evaluation set includes the safety index, comfort index, and efficiency index of the target vehicle.

[0093] Based on the aforementioned indicator information of the target vehicle, a style index model for the target vehicle is established. The vehicle style index is used to represent the operational behavior characteristics of the driver of the target vehicle in controlling the vehicle operation under real vehicle operating conditions. In this embodiment, by analyzing the vehicle operating status data, the vehicle driving style can be dynamically identified. Specifically, the driving style can be divided into conservative, moderate, efficient, etc.

[0094] The calculation methods involved in the target vehicle style index model are as follows:

[0095]

[0096] In the formula, t represents the current time, t-1 represents the previous time, and δ s Indicates safety indicators, δ c Indicator of comfort, δ eThe efficiency index is represented by ψ(t), which represents the style index of the target vehicle at time t, and ψ(t-1) represents the style index of the target vehicle at time t-1.

[0097] In the style index model described above, the driving style of the target vehicle can be determined by solving for the style index ψ. A result of 0 represents conservative driving, in which case the vehicle is relatively safe; a result of 1 represents efficient driving, in which case the vehicle is relatively efficient; and a result of 0.5 represents moderate driving, in which case the vehicle is relatively comfortable.

[0098] The first determining module 220 is used to determine the revenue function of the target vehicle based on the style index model of the target vehicle, and to determine the revenue function of the vehicle based on the collision probability relationship of the vehicle.

[0099] In this application, "self-vehicle" refers to the vehicle that will make emergency braking decisions using the AEB system, and "target vehicle" refers to surrounding vehicles moving relative to the self-vehicle. In assisted driving scenarios, the self-vehicle can predict the operating state of the target vehicle through the AEB system and use vehicle information obtained by the perception module to determine whether a collision will occur between the self-vehicle and the target vehicle and perform corresponding braking control.

[0100] In one embodiment of this application, determining the revenue function of the target vehicle based on the style index model of the target vehicle includes: determining the revenue function of the target vehicle based on the style index in the style index model of the target vehicle.

[0101] Specifically, the revenue function for the target vehicle is constructed as follows:

[0102]

[0103] In the formula, t represents the current time, and k represents the number of different sampling times recorded. The value of k ranges from 0 to N natural numbers. It can be understood that any time can be taken as the current time t, and k is taken starting from 0 at time t to achieve time integration of the terms in parentheses and to calculate the revenue function.

[0104] In this embodiment, the payoff function of the target vehicle includes a first factor J. OS Second factor J oc And the third factor J oe J os J oc J oe The function expressions are as follows:

[0105] J os (t)=V[1](t)

[0106] Joc (t)=1-[V[2](t)-V[2](t-1)] 2

[0107]

[0108] In the above expressions, V[1], V[2], and V[3] represent the target vehicle evaluation centralized safety index δ, respectively. s Comfort index δ c High efficiency index δ e The index prediction results are given, where φ(t) represents the collision probability relationship of the vehicle at time t.

[0109] In this embodiment of the application, based on the fuzzy state estimation model of the target vehicle, the obtained state variables such as real-time speed, historical speed, real-time position, historical position, real-time offset angle, and historical offset angle of the target vehicle are transformed through a fuzzy transformation matrix to obtain the evaluation set of the target vehicle. The evaluation set includes the target vehicle's safety indicators, comfort indicators, and efficiency indicators.

[0110] Therefore, based on the above functional expression, it can be understood that the first factor J os The safety index δ in the target vehicle's index prediction results s Correlation, the second factor J oc The comfort index δ in the target vehicle's index prediction results c Related, the third factor J oe The efficiency index δ in the target vehicle's index prediction results e It is related to the collision probability φ(t).

[0111] Furthermore, in this embodiment of the application, determining the vehicle's revenue function based on the vehicle's collision probability relationship includes: determining the vehicle's revenue function based on the vehicle's collision probability relationship.

[0112] The revenue function for the self-driving car is as follows:

[0113]

[0114] In the formula, t represents the current time, and k represents the number of different sampling times recorded. The value of k ranges from 0 to N natural numbers. It can be understood that any time can be taken as the current time t, and the value of k starts from 0 at time t, so as to perform time integration on the terms in parentheses above and calculate the revenue function.

[0115] In this embodiment, the vehicle's revenue function includes a fourth factor J. ms Factor J, the fifth factor mc And the sixth factor Jme J ms J mc J me The expressions are as follows:

[0116]

[0117]

[0118]

[0119] In the above expressions, V[2] and V[3] represent the target vehicle evaluation centralized comfort index δ, respectively. c High efficiency index δ e The index prediction results are given, where φ(t) represents the collision probability relationship of the vehicle at time t.

[0120] Therefore, based on the above expression, it can be understood that the fourth factor J... ms The fifth factor J is related to the value of φ. mc The relationship between the collision probability φ(t) and the comfort index δ in the target vehicle's index prediction results. c Related, the sixth factor J me The efficiency index δ in the collision probability relationship φ(t) and the target vehicle's index prediction results. e Related.

[0121] The second determining module 230 is used to determine the collision probability coefficient based on the revenue function of the target vehicle and the revenue function of the self vehicle.

[0122] In this embodiment, the collision probability coefficients can be calculated using the benefit functions of the target vehicle and the self-vehicle. As mentioned earlier, the benefit functions of the target vehicle and the self-vehicle include a collision probability relationship φ(t). It can be understood that the calculated result of φ(t) corresponds to different collision probability coefficients and represents the probability of different collision risks.

[0123] Trigger module 240 is used to trigger vehicle braking when the collision probability coefficient meets the conditions.

[0124] In one embodiment of this application, by pre-setting judgment conditions based on the value of the collision probability coefficient, the AEB system can make and execute corresponding braking decisions. For example, it is set that vehicle braking is triggered when the collision probability coefficient φ ≥ 0.8. In this embodiment, a target vehicle style index model and a braking decision model are established based on asymmetric game theory and Nash equilibrium theory. Simultaneously, the collision probability coefficient calculated by the model represents the risk of a collision based on the game outcome. When the collision probability coefficient is not less than 0.8, it indicates a high probability of a collision, requiring emergency braking to avoid harm. This application can make emergency braking decisions more accurately and efficiently while ensuring safety, effectively improving driving comfort.

[0125] In one embodiment of this application, in the establishment module 210,

[0126] The step of establishing a style index model for the target vehicle based on the target vehicle's index prediction results further includes:

[0127] Based on the target vehicle's current indicator prediction results and the target vehicle's style index model from the previous moment, a style index model for the target vehicle at the current moment is established. The indicator prediction results include at least one of the following: the target vehicle's safety indicator, the target vehicle's comfort indicator, and the target vehicle's efficiency indicator.

[0128] In one embodiment of this application, in the first determining module 220,

[0129] The step of determining the revenue function of the target vehicle based on the style index model of the target vehicle includes:

[0130] Based on the style index in the style index model of the target vehicle, the revenue function of the target vehicle is determined. The revenue function of the target vehicle includes a first factor, a second factor, and a third factor. The first factor is related to the safety index in the target vehicle's index prediction results, the second factor is related to the comfort index in the target vehicle's index prediction results, and the third factor is related to the efficiency index in the target vehicle's index prediction results.

[0131] In one embodiment of this application, in the first determining module 220,

[0132] The step of determining the vehicle's revenue function based on the collision probability relationship includes:

[0133] Based on the collision probability relationship of the vehicle, the benefit function of the vehicle is determined. The benefit function of the vehicle includes a fourth factor, a fifth factor, and a sixth factor. The fourth factor is related to the collision probability relationship. The fifth factor is related to the collision probability relationship and the comfort index in the target vehicle's index prediction results. The sixth factor is related to the collision probability relationship and the efficiency index in the target vehicle's index prediction results.

[0134] In one embodiment of this application, in the second determining module 230,

[0135] Based on the payoff function of the target vehicle and the payoff function of the self-vehicle, the collision probability coefficient is determined, including:

[0136] Based on the profit function of the target vehicle and the profit function of the self-vehicle, construct the optimal profit objective function;

[0137] The collision probability coefficient is determined based on the optimal profit objective function.

[0138] In one embodiment of this application, in the second determining module 230,

[0139] Determining the collision probability coefficient based on the target vehicle's payoff function and the driver's payoff function further includes:

[0140] When a collision occurs, the collision probability coefficient is 1; when no collision occurs, the collision probability coefficient is 0.

[0141] In one embodiment of this application, in the triggering module 240, triggering vehicle braking when the collision probability coefficient meets the condition includes:

[0142] When the collision probability coefficient is not less than 0.8, the vehicle braking is triggered;

[0143] When the collision probability coefficient is less than 0.5, the vehicle braking is canceled.

[0144] It should be noted that the above-mentioned vehicle braking decision device can realize each step of the vehicle braking decision method provided in the foregoing embodiments. The relevant explanations of the vehicle braking decision method are applicable to the vehicle braking decision device, and will not be repeated here.

[0145] In summary, the technical solution of this application achieves at least the following technical effects: a style index model of the target vehicle is established based on the target vehicle's index prediction results; the payoff function of the target vehicle is determined based on the target vehicle's style index model, and the payoff function of the self-vehicle is determined based on the collision probability relationship; a collision probability coefficient is determined based on the target vehicle's payoff function and the self-vehicle's payoff function; and vehicle braking is triggered when the collision probability coefficient meets the conditions. Based on asymmetric game theory and Nash equilibrium theory, this application solves for the collision probability coefficient by constructing a target vehicle style index model and payoff function, enabling the AEB system to make accurate and efficient braking decisions to avoid hazards in emergency situations, effectively improving driving comfort while meeting vehicle driving safety requirements.

[0146] It should be noted that:

[0147] The algorithms and displays provided herein are not inherently related to any particular computer, virtual device, or other equipment. Various general-purpose devices can also be used in conjunction with the teachings herein. The required structure for constructing such devices is apparent from the above description. Furthermore, this application is not directed to any particular programming language. It should be understood that the content of this application described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of this application.

[0148] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0149] Similarly, it should be understood that, in order to simplify this application and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of this application, various features of this application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this application.

[0150] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0151] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0152] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the vehicle braking decision device according to the embodiments of this application. This application can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such a program implementing this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0153] For example, Figure 3A schematic diagram of an electronic device according to an embodiment of this application is shown. The electronic device 300 includes a processor 310 and a memory 320 arranged to store computer-executable instructions (computer-readable program code). The memory 320 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. The memory 320 has a storage space 330 for storing computer-readable program code 331 for performing any of the method steps described above. For example, the storage space 330 for storing computer-readable program code may include various computer-readable program codes 331 respectively for implementing the various steps in the methods described above. The computer-readable program code 331 can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, CDs, memory cards, or floppy disks. Such computer program products are typically, for example... Figure 4 The computer-readable storage medium shown.

[0154] Figure 4 A schematic diagram of a computer-readable storage medium according to an embodiment of this application is shown. The computer-readable storage medium 400 stores computer-readable program code 331 for performing the method steps according to this application, which can be read by the processor 310 of an electronic device 300. When the computer-readable program code 331 is executed by the electronic device 300, it causes the electronic device 300 to perform the various steps of the method described above. Specifically, the computer-readable program code 331 stored in the computer-readable storage medium can perform the methods shown in any of the above embodiments. The computer-readable program code 331 can be compressed in a suitable form.

[0155] It should be noted that the above embodiments are illustrative of this application and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

Claims

1. A vehicle braking decision method, wherein, The method comprises: According to the index prediction result of the target vehicle, a style index model of the target vehicle is established, and the index prediction result at least comprises a safety index of the target vehicle, a comfort index of the target vehicle, and an efficiency index of the target vehicle; According to the style index model of the target vehicle, a benefit function of the target vehicle is determined, and a benefit function of the ego vehicle is determined according to a collision probability relationship of the ego vehicle; The determination of the benefit function of the target vehicle according to the style index model of the target vehicle comprises: According to the style index in the style index model of the target vehicle, the benefit function of the target vehicle is determined, wherein the benefit function of the target vehicle comprises a first factor, a second factor and a third factor, the first factor is related to the safety index in the index prediction result of the target vehicle, the second factor is related to the comfort index in the index prediction result of the target vehicle, and the third factor is related to the efficiency index in the index prediction result of the target vehicle; The determination of the benefit function of the ego vehicle according to the collision probability relationship of the ego vehicle comprises: According to the collision probability relationship of the ego vehicle, the benefit function of the ego vehicle is determined, wherein the benefit function of the ego vehicle comprises a fourth factor, a fifth factor and a sixth factor, the fourth factor is related to the collision probability relationship, the fifth factor is related to the collision probability relationship and the comfort index in the index prediction result of the target vehicle, and the sixth factor is related to the collision probability relationship and the efficiency index in the index prediction result of the target vehicle, the calculation result of the collision probability relationship corresponds to different collision probability coefficients, and represents the probability of different collision risks; According to the benefit function of the target vehicle and the benefit function of the ego vehicle, a collision probability coefficient is determined; When the collision probability coefficient meets the condition, vehicle braking is triggered.

2. The method of claim 1, wherein, The establishment of the style index model of the target vehicle according to the index prediction result of the target vehicle further comprises: According to the index prediction result of the target vehicle at the current time and the style index model of the target vehicle at the last time, the style index model of the target vehicle at the current time is established.

3. The method of claim 1, wherein, The determination of the collision probability coefficient according to the benefit function of the target vehicle and the benefit function of the ego vehicle comprises: According to the benefit function of the target vehicle and the benefit function of the ego vehicle, an optimal benefit target function is constructed; According to the optimal benefit target function, the collision probability coefficient is determined.

4. The method of claim 3, wherein, The determination of the collision probability coefficient according to the benefit function of the target vehicle and the benefit function of the ego vehicle further comprises: When a collision occurs, the collision probability coefficient = 1, and when no collision occurs, the collision probability coefficient = 0.

5. The method of claim 4, wherein, The triggering of vehicle braking when the collision probability coefficient meets the condition comprises: When the collision probability coefficient is not less than 0.8, vehicle braking is triggered; When the collision probability coefficient is less than 0.5, vehicle braking is cancelled.

6. A vehicle braking decision device in which, The device comprises: The establishing module is configured to establish a style index model of the target vehicle according to an index prediction result of the target vehicle, the index prediction result at least including a safety index of the target vehicle, a comfort index of the target vehicle, and an efficiency index of the target vehicle. The first determining module is configured to determine a benefit function of the target vehicle according to the style index model of the target vehicle, and determine a benefit function of the ego vehicle according to a collision probability relationship of the ego vehicle. The determining of the benefit function of the target vehicle according to the style index model of the target vehicle includes: The benefit function of the target vehicle is determined according to a style index in the style index model of the target vehicle, wherein the benefit function of the target vehicle includes a first factor, a second factor, and a third factor, the first factor is related to the safety index in the index prediction result of the target vehicle, the second factor is related to the comfort index in the index prediction result of the target vehicle, and the third factor is related to the efficiency index in the index prediction result of the target vehicle. The determining of the benefit function of the ego vehicle according to the collision probability relationship of the ego vehicle includes: The benefit function of the ego vehicle is determined according to the collision probability relationship of the ego vehicle, wherein the benefit function of the ego vehicle includes a fourth factor, a fifth factor, and a sixth factor, the fourth factor is related to the collision probability relationship, the fifth factor is related to the collision probability relationship and the comfort index in the index prediction result of the target vehicle, and the sixth factor is related to the collision probability relationship and the efficiency index in the index prediction result of the target vehicle, a calculation result of the collision probability relationship corresponds to different collision probability coefficients and represents probabilities of different collision risks. The second determining module is configured to determine a collision probability coefficient according to the benefit function of the target vehicle and the benefit function of the ego vehicle. The triggering module is configured to trigger vehicle braking when the collision probability coefficient meets a condition. 7.An electronic device comprising: a processor; and a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the method of any one of claims 1-5. 8.A computer-readable storage medium storing one or more programs, the one or more programs, when executed by an electronic device including multiple applications, cause the electronic device to perform the method of any one of claims 1-5.

Images