Vehicle braking control method, device, electronic device, and storage medium

Abstract

This application discloses a vehicle braking control method, device, electronic device, and storage medium, including: establishing a vehicle state prediction model based on the real-time states of a target vehicle and a self-vehicle; predicting the target vehicle's state information at the next moment through the vehicle state prediction model; establishing a fuzzy state estimation model based on the target vehicle's state information at the next moment; predicting the target vehicle's vehicle index information at the next moment through the fuzzy state estimation model; establishing a decision model based on the target vehicle's vehicle index information at the next moment; predicting the self-vehicle's braking decision at the next moment through the decision model, and executing vehicle braking control. This application can accurately predict the target vehicle's operating state and effectively solve the problem of decision-making errors caused by a single evaluation index, allowing the AEB system to determine braking decisions more safely, accurately, and efficiently.

Description

Technical Field

[0001] The present application relates to the field of assisted driving technology, and in particular to a vehicle braking control method, device, electronic equipment, and storage medium. Background Art

[0002] AEB (Autonomous Emergency Braking) is an active automotive safety technology. The function of the AEB system is to completely avoid collisions or minimize the intensity of collisions as much as possible, thereby preventing the vehicle from rear-ending or colliding with pedestrians and other traffic participants. In emergency situations where a collision is imminent, due to the driver's delayed reaction, the vehicle often collides with or rear-ends surrounding vehicles. In such cases, the AEB system (Autonomous Emergency Braking) is needed to identify the vehicle's collision risk in advance and make the correct braking decision.

[0003] In existing technologies, the ego vehicle needs to predict the motion state of target vehicles in its surroundings in real time and adjust subsequent control modules based on the prediction results. This prediction task typically uses a machine learning model combined with historical motion trajectories to predict the target vehicle's trajectory and generate a probability distribution of the prediction results. Furthermore, in emergency braking scenarios, the system also uses the predicted vehicle trajectory to determine the collision time or safe collision distance between the ego vehicle and the target vehicle, thereby making the correct braking control decisions to achieve emergency avoidance.

[0004] However, existing technologies have limited accuracy and stability in sensing target vehicles. Traditional prediction models cannot meet safety requirements, and prediction results are subject to errors, leading to inaccurate calculations of TTC (time to collision) and safe collision distance. The singleness of the system's evaluation indicators and their errors directly lead to deviations in the timing of AEB system warnings and braking, resulting in a slow response speed for the vehicle and a high risk of premature or late braking or release, seriously affecting the driver's safety and comfort experience. Summary of the Invention

[0005] The embodiments of the present application provide a vehicle braking control method, device, electronic device, and storage medium to achieve the technical effect of real-time prediction of vehicle operating status, conversion of braking decision evaluation indicators, meeting vehicle safety driving requirements, and enabling the AEB system to accurately and efficiently control and execute emergency braking decisions.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] According to one aspect of the present application, a vehicle braking control method is provided, the method comprising:

[0008] According to the real-time status of the target vehicle and the real-time status of the ego vehicle at the current moment, a vehicle state prediction model is established;

[0009] Predicting the vehicle state information of the target vehicle at the next moment through the vehicle state prediction model;

[0010] Establishing a fuzzy state estimation model based on the vehicle state information of the target vehicle at the next moment;

[0011] Predicting the vehicle index information of the target vehicle at the next moment through the fuzzy state estimation model;

[0012] Establishing a decision model based on vehicle index information of the target vehicle at the next moment;

[0013] Predicting the braking decision of the vehicle at the next moment through the decision model;

[0014] Vehicle braking control is executed according to the braking decision of the own vehicle.

[0015] Optionally, the vehicle state prediction model predicts the vehicle state information of the target vehicle at the next moment based on a double-layer state prediction model;

[0016] The fuzzy state estimation model converts the vehicle state information of the target vehicle at the next moment into a safety index of the target vehicle, a comfort index of the target vehicle, and an efficiency index of the target vehicle through fuzzy state conversion;

[0017] The decision model determines the braking decision of the vehicle at the next moment according to the collision probability coefficient.

[0018] Optionally, feedback correction and / or rolling optimization are performed on the two-layer state prediction model in real time.

[0019] Optionally, the vehicle state information of the target vehicle at the next moment includes the real-time speed, historical speed, real-time position, historical position, real-time offset angle, and historical offset angle of the target vehicle.

[0020] Optionally, when the collision probability coefficient is not less than 0.8, emergency braking is performed on the vehicle.

[0021] Optionally, establishing a fuzzy state estimation model according to the vehicle state information of the target vehicle at the next moment includes:

[0022] A fuzzy state estimation model is established based on the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle in the vehicle state information of the target vehicle at the next moment, so as to predict the vehicle index information of the target vehicle at the next moment.

[0023] Optionally, the method further includes: acquiring environmental information through a perception module to obtain the historical state and the real-time state of the target vehicle at the current moment, as well as the historical state and the real-time state of the own vehicle at the current moment.

[0024] According to a second aspect of the present application, a vehicle brake control device is provided, the device comprising:

[0025] The first establishing module is used to establish a vehicle state prediction model according to the real-time state of the target vehicle and the real-time state of the own vehicle at the current moment;

[0026] A first prediction module is used to predict the vehicle state information of the target vehicle at the next moment through the vehicle state prediction model;

[0027] A second establishing module is used to establish a fuzzy state estimation model according to the vehicle state information of the target vehicle at the next moment;

[0028] A second prediction module is used to predict the vehicle index information of the target vehicle at the next moment through the fuzzy state estimation model;

[0029] A third establishing module is used to establish a decision model based on the vehicle index information of the target vehicle at the next moment;

[0030] A third prediction module is used to predict the braking decision of the vehicle at the next moment through the decision model;

[0031] The decision-making braking module is used to execute vehicle braking control according to the braking decision of the vehicle.

[0032] According to a third aspect of the present application, there is provided an electronic device, comprising:

[0033] A processor; and a memory arranged to store computer executable instructions, which, when executed, cause the processor to perform any of the methods described above.

[0034] According to the fourth aspect of the present application, a computer-readable storage medium is provided, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes any of the methods described above.

[0035] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0036] Based on the real-time status of the target vehicle at the current moment and the real-time status of the own vehicle at the current moment, a vehicle state prediction model is established; the vehicle state information of the target vehicle at the next moment is predicted through the vehicle state prediction model; based on the vehicle state information of the target vehicle at the next moment, a fuzzy state estimation model is established; based on the vehicle index information of the target vehicle at the next moment, the vehicle index information of the target vehicle at the next moment is predicted through the fuzzy state estimation model; based on the vehicle index information of the target vehicle at the next moment, a decision model is established; based on the decision model, the braking decision of the own vehicle at the next moment is predicted; and based on the braking decision of the own vehicle, vehicle braking control is executed. This application can accurately predict the operating state of the target vehicle at the next moment by establishing a vehicle state prediction model, a fuzzy state estimation model, and a decision model, and realizes the conversion of the target vehicle state information into multi-dimensional index information, effectively solving the problem of decision-making errors caused by a single evaluation index. At the same time, in an emergency, this application enables the AEB system to make braking decisions to avoid risks more safely, accurately, and efficiently, greatly improving driving comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0038] Figure 1 This is a flow chart of a vehicle braking control method in one embodiment of the present application;

[0039] Figure 2 This is a fuzzy state transition effect diagram of a vehicle braking control method in one embodiment of the present application;

[0040] Figure 3 Schematic diagram of the structure of each model in the vehicle braking control method in one embodiment of the present application;

[0041] Figure 4 This is a schematic structural diagram of a vehicle brake control device in one embodiment of the present application;

[0042] Figure 5 This is a schematic structural diagram of an electronic device in one embodiment of the present application;

[0043] Figure 6 This is a schematic diagram of the structure of a computer-readable storage medium in one embodiment of the present application. DETAILED DESCRIPTION

[0044] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0045] As previously mentioned, the AEB system primarily operates by using sensors or radar within the perception module to measure the distance between the vehicle and the preceding vehicle. The system then uses this information to determine the collision time between the vehicle and the target vehicle, and then implements braking control through the vehicle's braking system. This allows the AEB system to take evasive action even in emergency situations where the driver doesn't have time to apply the brakes. However, the safety models used in related technologies based on collision time or collision distance often have overly simplistic evaluation metrics. This leads to frequent braking decision errors caused by data drift, low calculation accuracy, and large errors, resulting in poor safety and comfort in the vehicle system.

[0046] Based on this, a vehicle braking control method is proposed in the embodiment of the present application to achieve the technical effect of real-time prediction of vehicle operating status, expanding the dimension of decision-making evaluation indicators, meeting vehicle safety driving requirements, and enabling the AEB system to accurately and efficiently control and execute emergency braking decisions.

[0047] The technical concept of this application is to predict the operating state of the target vehicle at the next moment by establishing a vehicle state prediction model; by establishing a fuzzy state estimation model, the state information of the target vehicle is converted into safety indicators, comfort indicators and efficiency indicators; by constructing a target style index model and decision model based on Nash equilibrium theory, the AEB system can determine the braking decision more safely, accurately and efficiently. This application can accurately predict the operating state of the target vehicle and effectively solve the problem of decision-making errors caused by a single evaluation index. At the same time, this application improves driving efficiency and comfort, and can escort the safe travel of vehicles and personnel in emergency situations.

[0048] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0049] like Figure 1 As shown, the method includes the following steps S110 to S170:

[0050] Step S110 , establishing a vehicle state prediction model based on the real-time state of the target vehicle and the real-time state of the own vehicle at the current moment.

[0051] In an embodiment of the present application, it is necessary to obtain environmental information through a perception module. This environmental information includes the real-time status and historical status of the own vehicle and the target vehicle. After identifying, processing and analyzing the environmental information, the historical status and real-time status of the target vehicle at the current moment, as well as the historical status and real-time status of the own vehicle at the current moment are obtained.

[0052] In one embodiment of the present application, the vehicle state prediction model includes predicting the vehicle state information of the target vehicle at the next moment based on a two-layer state prediction model. The two-layer state prediction model includes a control quantity prediction model and a state quantity prediction model. Since the current control quantity of the target vehicle is unavailable, in this embodiment, the control quantity of the target vehicle at the previous moment is obtained through the perception module of the vehicle, and a control quantity prediction model for the target vehicle is established based on the control quantity of the target vehicle at the previous moment.

[0053] In the control quantity prediction model, t k-1 represents the previous moment, t k represents the current time, t k+1 Indicates the next moment.

[0054] The preset target vehicle is at t k-1 The control quantity at time t is u(k-1), then the target vehicle is k The control quantity at time t is u(k), and the target vehicle is at t k+1 The control quantity at the moment is u(k+1), m(k) represents the relational expression related to the target vehicle's brake light signal information, n(k) represents the relational expression related to the target vehicle's turn signal information, and p(k) represents the relational expression related to the target vehicle's lane-changing probability. The control quantity prediction model for the target vehicle is established as follows:

[0055]

[0056] In the formula, u=[a o ],n=[ρ t ],m=[ρ b ],p=[δ l ];

[0057] The meanings of the parameters in the above model are as follows:

[0058] a o represents the real-time acceleration of the target vehicle, ρ b represents the target vehicle's brake light signal information, ρ t represents the target vehicle’s turn signal information, δ l represents the lane-changing probability of the target vehicle;

[0059] A dRepresents the first calculation factor, B du Represents the second calculation factor, B dv Represents the third calculation factor, C d Denotes the fourth calculation factor, D dv represents the fifth calculation factor, wherein the first calculation factor A d The second calculation factor B is related to the offset angle between the target vehicle and the vehicle, and the brake light signal information of the target vehicle. du The third calculation factor B is related to the maximum braking deceleration that the EPS system of the vehicle can provide. dv The fourth calculation factor C is related to the deceleration output by the ABS system when the vehicle turns. d is a constant, the fifth calculation factor D dv Related to the offset angle of the target vehicle.

[0060] Furthermore, in the state quantity prediction model, t k-1 represents the previous moment, t k represents the current time, t k+1 Indicates the next moment. The preset target vehicle is at t k The variable of the vehicle state information at the moment is x(k), and the state prediction model of the target vehicle is as follows:

[0061]

[0062] Where, the relationship expressions related to x(k), u(k), v(k), and y(k) are as follows:

[0063]

[0064] The meanings of the parameters in the above model are as follows:

[0065] x(k+1) is t k+1 The predicted values ​​of the state information variables of the target vehicle at time t are u(k), v(k), and y(k), respectively. k The control quantity of the target vehicle, the measurable input quantity of the ego vehicle, and the output quantity of the target vehicle in the model predictive control processor at the time instant;

[0066] d p Represents the real-time lateral distance of the target vehicle, d H Represents the real-time longitudinal distance of the target vehicle, V p Represents the real-time lateral speed of the target vehicle, V H represents the real-time longitudinal velocity of the target vehicle, Represents the real-time offset angle of the target vehicle; a o Represents the real-time acceleration of the target vehicle, v m represents the real-time speed of the vehicle, am represents the real-time acceleration of the vehicle, represents the real-time offset angle of the vehicle, represents the vehicle offset angle, TTC represents the time to collision of the target vehicle;

[0067] A represents the sixth calculation factor, B u Represents the seventh calculation factor, B v represents the eighth calculation factor, C represents the ninth calculation factor, and D v represents the tenth calculation factor, y(k-1) represents the output of the target vehicle at the previous moment, and y(k) represents the output of the target vehicle at the current moment. In one embodiment of the present application, the sixth calculation factor A is related to the acceleration of the vehicle, the real-time speed of the vehicle, and the offset angle between the vehicle and the target vehicle. The seventh calculation factor B u is a first matrix relationship established based on the vehicle offset angle, the eighth calculation factor B v Based on the second matrix relationship established by the vehicle offset angle, the ninth calculation factor C is related to the vehicle offset angle, the vehicle acceleration and the speed of the target vehicle, and the tenth calculation factor D v Related to the vehicle offset angle and the speed of the target vehicle.

[0068] Step S120: predicting the vehicle state information of the target vehicle at the next moment through the vehicle state prediction model.

[0069] In one embodiment of the present application, the variables of the vehicle state information of the target vehicle at the next moment include at least one of the following: real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle. In another embodiment of the present application, when predicting the vehicle state information using the vehicle state prediction model, the vehicle state information of the target vehicle at the next moment also includes: the target vehicle's real-time speed, historical speed, real-time position, historical position, real-time offset angle, and historical offset angle.

[0070] The above control quantity prediction model can be used to predict the control quantity u(k) of the target vehicle at the current moment. By substituting the control quantity u(k) into the state quantity prediction model of the target vehicle, the vehicle state information of the target vehicle at the next moment can be predicted.

[0071] In the embodiment of the present application, a control quantity prediction model of the target vehicle is established based on the control quantity u(k-1) of the target vehicle at the previous moment, and the control quantity u(k) of the target vehicle at the current moment is calculated; a state prediction model of the target vehicle is established based on the control quantity u(k) of the target vehicle at the current moment, the measurable input quantity v(k) of the vehicle at the current moment, and the output quantity y(k) of the target vehicle at the current moment; by constructing the above-mentioned two-level model of control quantity prediction and state quantity prediction, it is possible to predict the operating state quantity information of the target vehicle at the next moment, that is, to predict the target vehicle at t k+1 Prediction of the variable x(k+1) at the moment of operation.

[0072] In an embodiment of the present application, the method further includes: performing real-time feedback correction and / or rolling optimization on the two-layer state prediction model to ensure the accuracy and stability of the model output results. Thus, the embodiment of the present application adopts this two-layer state prediction model, combined with strategies such as feedback correction and rolling optimization, which can not only efficiently and stably predict the operating state of the target vehicle at the next moment, but also ensure the accuracy of the vehicle state prediction results; at the same time, it provides an accurate and effective basis for the braking control of the vehicle's AEB system, enabling the vehicle to make emergency braking decisions more accurately and efficiently while ensuring safety, effectively improving driving comfort.

[0073] Step S130: establishing a fuzzy state estimation model based on the vehicle state information of the target vehicle at the next moment.

[0074] In one embodiment of the present application, the fuzzy state estimation model is established based on the vehicle state information of the target vehicle at the next moment, including: establishing a fuzzy state estimation model based on the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle in the vehicle state information of the target vehicle at the next moment, for predicting the vehicle index information of the target vehicle at the next moment.

[0075] Specifically, the fuzzy state estimation model is used to convert the vehicle state information of the target vehicle at the next moment into a fuzzy state to obtain the safety index of the target vehicle, the comfort index of the target vehicle and the high efficiency index of the target vehicle, wherein the vehicle state information is the first reference index, and the safety index, comfort index and high efficiency index of the target vehicle are the second reference index.

[0076] In one embodiment of the present application, the method includes obtaining the lateral relative position, longitudinal relative position, lateral relative speed, longitudinal relative speed, and offset angle of a target vehicle in a first reference index of the target vehicle, and establishing a factor set. By constructing a fuzzy state estimation model, the vehicle state information such as the real-time speed, historical speed, real-time position, historical position, real-time offset angle, and historical offset angle contained in the obtained first reference index U of the target vehicle is fuzzily transformed using a preset fuzzy transformation matrix R to obtain a second reference index V of the target vehicle.

[0077] The implementation is as follows:

[0078] The factor set composed of the preset first reference index The evaluation set composed of the second reference index V={δ s ,δ c ,δ e},

[0079] Among them, d P represents the lateral relative position of the target vehicle, d H Indicates the longitudinal relative position of the target vehicle, v P represents the lateral relative velocity of the target vehicle, v H represents the longitudinal relative velocity of the target vehicle, represents the offset angle of the target vehicle; δ s represents the safety index of the target vehicle, δ c represents the comfort index of the target vehicle, δ e Represents the efficiency index of the target vehicle.

[0080] A fuzzy transformation matrix R is preset. The fuzzy transformation matrix R is composed of the fuzzy evaluation vector R i =(r i1 ,r i2 ,…,r im ), where r i1 -r im They represent the membership of each factor to the state in the evaluation set, reflecting a fuzzy relationship from the factor set to the evaluation set. The fuzzy evaluation vector R i The matrix relationship is specifically expressed as follows:

[0081]

[0082] It can be understood that the fuzzy state estimation model of the target vehicle is composed of the (U, V, R) triplet, and the conversion relationship in the fuzzy state estimation model of the target vehicle is: V = U × R,

[0083] Substituting the parameters in the above factor set and evaluation set, we get:

[0084]

[0085]

[0086] Based on the above model and its conversion relationship, the fuzzy state conversion of the target vehicle can be realized. By solving the model, the state conversion result of the preset fuzzy conversion matrix and the second reference index can be obtained.

[0087] Step S140: predicting the vehicle index information of the target vehicle at the next moment through the fuzzy state estimation model.

[0088] As previously described, based on the conversion relationship V = U × R in the target vehicle's fuzzy state estimation model, the target vehicle's vehicle index information at the next moment can be predicted. The target vehicle index information includes at least one of the following: a safety index of the target vehicle, a comfort index of the target vehicle, and an efficiency index of the target vehicle. Specifically, the safety index of the target vehicle is used to characterize the safe distance between the target vehicle and the ego vehicle and the time the safe distance is maintained. The comfort index of the target vehicle is used to characterize whether the acceleration of the target vehicle is smooth. The efficiency index of the target vehicle is used to characterize whether the target vehicle's speed is maintained and / or whether the target vehicle changes lanes.

[0089] In one embodiment of the present application, the above method also includes optimizing and compensating the model. In order to further solve the limitation problem of the fuzzy state estimation model, the model can be optimized by constructing a transition matrix performance optimization target; at the same time, the corresponding indicator obtained according to the preset weight distribution in the second reference indicator of the aforementioned target vehicle is used as the state conversion result of the target vehicle to achieve the purpose of compensating the output result of the fuzzy state estimation model of the target vehicle.

[0090] Specifically, in order to avoid the influence of the state at the previous moment on the state at the current moment, a more realistic state indicator can be obtained through rolling optimization. Therefore, the compensation fuzzy relationship model is constructed as follows:

[0091] V(t+1)=σ[V(t)-V(t-1)] 2 +τ(U×R)

[0092] Among them, σ represents the first weight, τ represents the second weight, V(t+1), V(t), and V(t-1) represent the second reference indicators of the target vehicle at time t+1, time t, and time t-1, respectively. It can be understood that time t in this application can be any time.

[0093] Since certain errors will occur in the calculation process of solving the second reference index by presetting the fuzzy transformation matrix, in order to further solve the limitations of the fuzzy state estimation model, a transformation matrix performance optimization target is constructed:

[0094]

[0095] The meaning of each parameter is as follows:

[0096] δ s Represents the safety index, used to characterize the safety distance and the safety distance maintenance time, Δδ s represents the difference between the safety index converted by the preset fuzzy conversion matrix and the real safety index, δ c Represents the comfort index, which is strongly correlated with acceleration smoothness, Δδ c represents the difference between the comfort index converted by the preset fuzzy conversion matrix and the real comfort index, δ e Represents the efficiency index, which is used to characterize whether the target vehicle maintains speed and / or changes lanes, Δδ e represents the difference between the efficiency index after conversion using the preset fuzzy conversion matrix and the true efficiency index; wherein the above-mentioned true safety index, true comfort index and true efficiency index are all obtained by expert experience scoring; t0 represents the initial sampling time of the solution, t f represents the end sampling time of the solution; α, β, and γ represent different performance optimization parameters.

[0097] At the same time, if Figure 2 As shown, simulations conducted in the present application demonstrate that the compensation fuzzy relationship model constructed in the aforementioned embodiment can meet driving needs and usage requirements when the target vehicle speed is 38-82 kph, and can accurately predict the numerical results of the evaluation set after the target vehicle is converted and the evaluation set under real conditions, with an accuracy rate exceeding 50%. In particular, it can achieve an accuracy rate exceeding 90% when the vehicle speed is 60 kph.

[0098] The above simulation results show that the state quantity of the target vehicle can be converted into safety indicators, comfort indicators and efficiency indicators through the fuzzy state estimation model and the compensating fuzzy relationship model. The present application achieves the technical effect of effectively and accurately predicting and evaluating the operating state of the target vehicle; at the same time, the state conversion result of the target vehicle determined in the present application can be used as an effective evaluation indicator for the emergency braking decision of the AEB system.

[0099] From the above, it can be seen that the present application constructs a fuzzy state estimation model, and based on the first reference indicator composed of the target vehicle state quantity information, it can solve the state conversion result of the preset fuzzy conversion matrix and the second reference indicator, thereby further achieving the purpose of evaluating the braking risk factors and braking risk probability of the target vehicle, and providing an accurate and effective basis for the subsequent emergency braking decision of the AEB system.

[0100] Step S150: establishing a decision model based on the vehicle index information of the target vehicle at the next moment.

[0101] In the embodiment of the present application, a target vehicle style model and an AEB system decision model are constructed based on the idea of ​​asymmetric information game theory and Nash equilibrium theory.

[0102] Game theory and Nash equilibrium are a branch of mathematics used to analyze the strategies of decision-makers in competitive environments. Game theory uses rigorous mathematical models to study optimal decision-making under conditions of conflict and confrontation. Its essence is the study of how decision-makers maximize their utility under given information structures. Asymmetric information game theory examines the optimal contract design under asymmetric information conditions. If any player's strategy is optimal given the strategies of all other players, this combination is defined as a Nash equilibrium.

[0103] Specifically, in the embodiment of the present application, when establishing a decision model, it is necessary to first establish a style index model of the target vehicle based on the aforementioned indicator prediction results of the target vehicle; then, based on the style index model of the target vehicle, determine the benefit function of the target vehicle, and determine the benefit function of the own vehicle based on the collision probability relationship of the own vehicle; finally, determine the collision probability coefficient based on the benefit function of the target vehicle and the benefit function of the own vehicle. In the embodiment of the present application, the collision probability coefficient can be calculated using the benefit functions of the target vehicle and the own vehicle. The collision probability relationship φ(t) is included in the benefit function of the target vehicle and the benefit function of the own vehicle. It can be understood that the calculation results of φ(t) correspond to different collision probability coefficients and represent the probability of different collision risks.

[0104] Step S160: predicting the braking decision of the vehicle at the next moment through the decision model.

[0105] The vehicle style index is used to represent the operational behavior characteristics of the target vehicle's driver in controlling the vehicle operation in the actual vehicle operating environment. 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.

[0106] The calculations involved in the target vehicle style index model are as follows:

[0107]

[0108] Where, δ s represents the safety index, δ c represents the comfort index, δ e represents the efficiency index, ψ(t) 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. It can be understood that time t can represent any time, t-1 represents the previous time before time t, and t+1 represents the next time after time t.

[0109] In the above-mentioned style index model, by solving the style index ψ of the target vehicle, the driving style of the target vehicle at the current moment can be determined. When the result is 0, it represents conservativeness, and the vehicle is safer at this time; when the result is 1, it represents efficiency, and the vehicle is more efficient at this time; when the result is 0.5, it represents moderateness, and the vehicle is more comfortable at this time.

[0110] Furthermore, the benefit function of the target vehicle is determined based on the style index model of the target vehicle, and the benefit function of the ego vehicle is determined based on the collision probability relationship of the ego vehicle.

[0111] In this embodiment of the present application, the ego vehicle represents the vehicle for which the AEB system is about to initiate an emergency braking decision, and the target vehicle represents the surrounding vehicles moving relative to the ego vehicle. In assisted driving scenarios, the ego vehicle uses the AEB system to predict the target vehicle's operating state, and uses vehicle information acquired by the perception module to determine whether the ego vehicle and the target vehicle are in collision, and to implement appropriate braking control.

[0112] In one embodiment of the present application, determining the benefit function of the target vehicle based on the style index model of the target vehicle includes: determining the benefit function of the target vehicle based on the style index in the style index model of the target vehicle.

[0113] Specifically, the profit function of building the target vehicle is as follows:

[0114]

[0115] Where t represents the current time, k represents the number of different sampling times recorded, and the value range of k includes natural numbers from 0 to N. It can be understood that any time can be used as the current time t, and the values ​​are taken starting from k = 0 at time t to realize the time integration of the above terms in the brackets and calculate the profit function.

[0116] In this embodiment, the target vehicle's profit function includes the first factor J os , the second factor J oc and the third factor J oe , the first factor J os and the safety index δ in the index prediction result of the target vehicle s Correlation, the second factor J oc and the comfort index δ in the index prediction result of the target vehicle c Correlation, the third factor J oe and the efficiency index δ in the index prediction result of the target vehicle e Related to the collision probability relation φ(t).

[0117] Furthermore, in an embodiment of the present application, determining the benefit function of the own vehicle based on the collision probability relationship of the own vehicle includes: determining the benefit function of the own vehicle based on the collision probability relationship of the own vehicle.

[0118] The revenue function for building your own car is as follows:

[0119]

[0120] Where t represents the current time, k represents the number of different sampling times recorded, and the value range of k includes natural numbers from 0 to N. It can be understood that any time can be used as the current time t, and the values ​​are taken starting from k = 0 at time t to perform time integration of the above terms in the brackets and calculate the profit function.

[0121] In this embodiment, the vehicle's profit function includes a fourth factor J ms , Factor V J mc and Factor VI J me , the fourth factor J ms Related to the value of φ, the fifth factor J mc The collision probability relationship φ(t) and the comfort index δ in the index prediction result of the target vehicle c Related, the sixth factor J me The collision probability relationship φ(t) and the efficiency index δ in the index prediction result of the target vehicle e Related. In the embodiment of the present application, the collision probability coefficient can be calculated using the above-mentioned benefit functions of the target vehicle and the ego vehicle. As previously mentioned, the collision probability relationship φ(t) is included in the benefit function of the target vehicle and the benefit function of the ego vehicle. It can be understood that the calculation result of φ(t) corresponds to different collision probability coefficients and represents the probability of different collision risks.

[0122] In a preferred embodiment of the present application, the collision probability coefficient is determined based on the benefit function of the target vehicle and the benefit function of the own vehicle, including: constructing an optimal benefit objective function based on the benefit function of the target vehicle and the benefit function of the own vehicle; and determining the collision probability coefficient based on the optimal benefit objective function.

[0123] Since the collision probability relationship and the collision probability coefficient are only related to the ego vehicle and are not controlled by the target vehicle, the total benefit function is maximized when the collision probability coefficient is within a certain range. Based on the game theory strategy, f The profit function at each moment is integrated to construct the optimal profit objective function as follows:

[0124]

[0125] Where, J m represents the profit function of the vehicle, J o represents the profit function of the target vehicle.

[0126] In the optimal benefit objective function, the only variable is the collision probability coefficient φ in the benefit function.

[0127] Step S170: Execute vehicle braking control according to the braking decision of the own vehicle.

[0128] In one embodiment of the present application, by presetting the judgment conditions through the value of the collision probability coefficient, the AEB system can make and execute the corresponding braking decision. For example, it is set that when the collision probability coefficient φ ≥ 0.8, the vehicle braking is triggered. In this embodiment, based on asymmetric game theory and Nash equilibrium theory, a target vehicle style index model and a braking decision model are established. At the same time, the collision probability coefficient calculated according to the model represents the risk of collision as a result of the game. When the collision probability coefficient is not less than 0.8, it indicates that the probability of a collision is high, and emergency braking is required to avoid risks. The present application can make emergency braking decisions more accurately and efficiently while ensuring safety, effectively improving driving comfort.

[0129] In one embodiment of the present application, the collision probability coefficient is determined based on the benefit function of the target vehicle and the benefit function of the own vehicle, and also includes: when a collision occurs, the collision probability coefficient = 1, and when no collision occurs, the collision probability coefficient = 0.

[0130] Furthermore, in one embodiment of the present application, when the collision probability coefficient meets the conditions, triggering vehicle braking includes: when the collision probability coefficient is not less than 0.8, triggering vehicle braking; when the collision probability coefficient is less than 0.5, canceling vehicle braking.

[0131] This embodiment of the application establishes a model based on 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. Simultaneously, by establishing the optimal game objective, the optimal strategy is derived, enabling the AEB system to make and execute correct braking decisions. This technical solution enables the AEB system to accurately and efficiently make braking decisions to avoid danger in emergency situations, effectively improving driving comfort while meeting vehicle safety requirements.

[0132] like Figure 3 As shown, the vehicle state prediction model, the fuzzy state estimation model and the decision model in the method described in the embodiment of the present application can cooperate with each other. Specifically, the following process is adopted to realize the emergency braking control of the AEB system: first, the environmental information is obtained through the perception module, and a vehicle state prediction model is established according to the vehicle state information of the target vehicle and the own vehicle; secondly, in the vehicle state prediction model, the predicted vehicle state information of the target vehicle at the next moment is predicted based on the double-layer state prediction model; then, using the fuzzy state estimation model, the vehicle state information of the target vehicle at the next moment is converted into the safety index of the target vehicle, the comfort index of the target vehicle and the high efficiency index of the target vehicle through fuzzy state conversion; further, the decision model is established using the converted vehicle index information, and the braking decision of the own vehicle at the next moment is judged according to the collision probability coefficient calculated by the model; finally, the vehicle's braking execution system implements corresponding braking control according to the decision content.

[0133] like Figure 4 As shown, an embodiment of the present application further provides a vehicle braking control device 400, the device comprising:

[0134] The first establishing module 410 is used to establish a vehicle state prediction model according to the real-time state of the target vehicle and the real-time state of the ego vehicle at the current moment.

[0135] The first prediction module 420 is configured to predict the vehicle state information of the target vehicle at the next moment using the vehicle state prediction model.

[0136] The second establishing module 430 is used to establish a fuzzy state estimation model according to the vehicle state information of the target vehicle at the next moment.

[0137] The second prediction module 440 is configured to predict the vehicle index information of the target vehicle at the next moment using the fuzzy state estimation model.

[0138] The third establishing module 450 is used to establish a decision model according to the vehicle index information of the target vehicle at the next moment.

[0139] The third prediction module 460 is configured to predict the braking decision of the vehicle at the next moment using the decision model.

[0140] The decision-making braking module 470 is used to perform vehicle braking control according to the braking decision of the vehicle.

[0141] In one embodiment of the present application, in the first prediction module 420,

[0142] The vehicle state prediction model predicts the vehicle state information of the target vehicle at the next moment based on the double-layer state prediction model.

[0143] In one embodiment of the present application, in the second prediction module 440,

[0144] The fuzzy state estimation model converts the vehicle state information of the target vehicle at the next moment through fuzzy state conversion to obtain the safety index of the target vehicle, the comfort index of the target vehicle, and the efficiency index of the target vehicle.

[0145] In one embodiment of the present application, in the third prediction module 450,

[0146] The decision model determines the braking decision of the vehicle at the next moment according to the collision probability coefficient.

[0147] In one embodiment of the present application, in the first prediction module 420,

[0148] Feedback correction and / or rolling optimization are performed on the two-layer state prediction model in real time.

[0149] In one embodiment of the present application, in the first prediction module 420,

[0150] The vehicle state information of the target vehicle at the next moment includes the real-time speed, historical speed, real-time position, historical position, real-time offset angle, and historical offset angle of the target vehicle.

[0151] In one embodiment of the present application, in the decision-making braking module 470,

[0152] When the collision probability coefficient is not less than 0.8, emergency braking is performed on the vehicle.

[0153] In one embodiment of the present application, in the second establishing module 430,

[0154] The step of establishing a fuzzy state estimation model based on the vehicle state information of the target vehicle at the next moment includes:

[0155] A fuzzy state estimation model is established based on the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle in the vehicle state information of the target vehicle at the next moment, so as to predict the vehicle index information of the target vehicle at the next moment.

[0156] In one embodiment of the present application, in the first establishing module 410,

[0157] The method further includes: acquiring environmental information through a perception module to obtain the historical state and the real-time state of the target vehicle at the current moment, as well as the historical state and the real-time state of the ego vehicle at the current moment.

[0158] It should be noted that the above-mentioned vehicle braking control device can implement the various steps of the vehicle braking control method provided in the aforementioned embodiment. The relevant explanations about the vehicle braking control method are applicable to the vehicle braking control device and will not be repeated here.

[0159] In summary, the technical solution of the present application achieves at least the following technical effects: establishing a vehicle state prediction model based on the real-time state of the target vehicle at the current moment and the real-time state of the ego vehicle at the current moment; predicting the vehicle state information of the target vehicle at the next moment through the vehicle state prediction model; establishing a fuzzy state estimation model based on the vehicle state information of the target vehicle at the next moment; predicting the vehicle index information of the target vehicle at the next moment through the fuzzy state estimation model; establishing a decision model based on the vehicle index information of the target vehicle at the next moment; predicting the braking decision of the ego vehicle at the next moment through the decision model; and executing vehicle braking control based on the braking decision of the ego vehicle. By establishing a vehicle state prediction model, a fuzzy state estimation model, and a decision model respectively, the present application can accurately predict the operating state of the target vehicle at the next moment, realizes the conversion of target vehicle state information into multi-dimensional index information, effectively solves the problem of decision-making errors caused by a single evaluation index, and at the same time, in emergency situations, the present application enables the AEB system to make braking decisions to avoid risks more safely, accurately, and efficiently, greatly improving driving comfort.

[0160] It should be noted that:

[0161] The algorithms and displays provided herein are not inherently related to any particular computer, virtual device, or other device. Various general-purpose devices may also be used together with the teachings herein. Based on the above description, it is apparent that the structure required for constructing such devices is suitable. In addition, the present application is not directed to any specific programming language. It should be understood that various programming languages ​​may be utilized to implement the present application described herein, and the description of the specific languages ​​above is provided for the purpose of disclosing the preferred embodiment of the present application.

[0162] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0163] Similarly, it should be understood that in order to streamline the present application and aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the claims below, inventive aspects lie in fewer than all the features of the individual embodiments disclosed above. Accordingly, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim itself serving as a separate embodiment of the present application.

[0164] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition may be divided into multiple submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed herein may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0165] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of this application and to form different embodiments. For example, in the claims below, any of the claimed embodiments may be used in any combination.

[0166] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the vehicle brake control device according to the embodiment of the present application. The present application can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0167] For example, Figure 5 A schematic structural diagram of an electronic device according to an embodiment of the present application is shown. The electronic device 500 includes a processor 510 and a memory 520 arranged to store computer-executable instructions (computer-readable program code). The memory 520 can be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory 520 has a storage space 530 for storing a computer-readable program code 531 for executing any method step in the above method. For example, the storage space 530 for storing computer-readable program code may include various computer-readable program codes 531 respectively used to implement various steps in the above method. The computer-readable program code 531 can be read from or written to one or more computer program products. These computer program products include program code carriers such as a hard disk, a compact disk (CD), a memory card or a floppy disk. Such a computer program product is typically, for example Figure 6 The computer-readable storage medium shown.

[0168] Figure 6 A schematic diagram of the structure of a computer-readable storage medium according to one embodiment of the present application is shown. The computer-readable storage medium 600 stores computer-readable program code 531 for executing the method steps according to the present application and can be read by the processor 510 of the electronic device 500. When the computer-readable program code 531 is executed by the electronic device 500, the electronic device 500 executes each step of the method described above. Specifically, the computer-readable program code 531 stored in the computer-readable storage medium can execute the method described in any of the above embodiments. The computer-readable program code 531 can be compressed in an appropriate form.

[0169] It should be noted that the above embodiments illustrate rather than limit the present application, and that a person skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbols placed between brackets 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. The present application may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim 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 may be interpreted as names.

Claims

1. A vehicle braking control method, wherein: The method comprises: According to the real-time status of the target vehicle and the real-time status of the ego vehicle at the current moment, a vehicle state prediction model is established; The vehicle state prediction model predicts the vehicle state information of the target vehicle at the next moment based on the double-layer state prediction model; Predicting the vehicle state information of the target vehicle at the next moment through the vehicle state prediction model; Establishing a fuzzy state estimation model based on the vehicle state information of the target vehicle at the next moment; The fuzzy state estimation model converts the vehicle state information of the target vehicle at the next moment into the vehicle state information of the target vehicle at the next moment through fuzzy state conversion, wherein the vehicle state information of the target vehicle at the next moment includes at least one of the following: a safety index of the target vehicle, a comfort index of the target vehicle, and an efficiency index of the target vehicle; Predicting the vehicle index information of the target vehicle at the next moment through the fuzzy state estimation model; Establishing a decision model based on vehicle index information of the target vehicle at the next moment; The decision model determines the braking decision of the vehicle at the next moment according to the collision probability coefficient; When establishing the decision model, a style index model of the target vehicle is first established based on the vehicle state information of the target vehicle at the next moment; then, a profit function of the target vehicle is determined based on the style index model of the target vehicle, and a profit function of the own vehicle is determined based on the collision probability relationship of the own vehicle; finally, a collision probability coefficient is determined based on the profit function of the target vehicle and the profit function of the own vehicle; the collision probability coefficient is calculated by the profit functions of the target vehicle and the own vehicle, and the collision probability relationship φ(t) is included in the profit function of the target vehicle and the profit function of the own vehicle. The calculation results of φ(t) correspond to different collision probability coefficients and represent the probability of different collision risks; Predicting the braking decision of the vehicle at the next moment through the decision model; Vehicle braking control is executed according to the braking decision of the own vehicle.

2. The method according to claim 1, wherein: Feedback correction and / or rolling optimization are performed on the two-layer state prediction model in real time.

3. The method according to claim 1, wherein: The vehicle state information of the target vehicle at the next moment includes the real-time speed, historical speed, real-time position, historical position, real-time offset angle, and historical offset angle of the target vehicle.

4. The method according to claim 1, wherein: When the collision probability coefficient is not less than 0.8, emergency braking is performed on the vehicle.

5. The method of claim 1, wherein: The step of establishing a fuzzy state estimation model based on the vehicle state information of the target vehicle at the next moment includes: A fuzzy state estimation model is established based on the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle in the vehicle state information of the target vehicle at the next moment, so as to predict the vehicle index information of the target vehicle at the next moment.

6. The method of claim 1, wherein: The method further comprises: The environmental information is acquired through the perception module to obtain the historical state and the real-time state of the target vehicle at the current moment, as well as the historical state and the real-time state of the self-vehicle at the current moment.

7. A vehicle brake control device, wherein: The device comprises: The first establishing module is used to establish a vehicle state prediction model according to the real-time state of the target vehicle and the real-time state of the own vehicle at the current moment; The vehicle state prediction model predicts the vehicle state information of the target vehicle at the next moment based on the double-layer state prediction model; A first prediction module is used to predict the vehicle state information of the target vehicle at the next moment through the vehicle state prediction model; A second establishing module is used to establish a fuzzy state estimation model according to the vehicle state information of the target vehicle at the next moment; The fuzzy state estimation model converts the vehicle state information of the target vehicle at the next moment into the vehicle state information of the target vehicle at the next moment through fuzzy state conversion, wherein the vehicle state information of the target vehicle at the next moment includes at least one of the following: a safety index of the target vehicle, a comfort index of the target vehicle, and an efficiency index of the target vehicle; A second prediction module is used to predict the vehicle index information of the target vehicle at the next moment through the fuzzy state estimation model; A third establishing module is used to establish a decision model based on the vehicle index information of the target vehicle at the next moment; The decision model determines the braking decision of the vehicle at the next moment according to the collision probability coefficient; When establishing the decision model, a style index model of the target vehicle is first established based on the vehicle state information of the target vehicle at the next moment; then, a profit function of the target vehicle is determined based on the style index model of the target vehicle, and a profit function of the own vehicle is determined based on the collision probability relationship of the own vehicle; finally, a collision probability coefficient is determined based on the profit function of the target vehicle and the profit function of the own vehicle; the collision probability coefficient is calculated by the profit functions of the target vehicle and the own vehicle, and the collision probability relationship φ(t) is included in the profit function of the target vehicle and the profit function of the own vehicle. The calculation results of φ(t) correspond to different collision probability coefficients and represent the probability of different collision risks; A third prediction module is used to predict the braking decision of the vehicle at the next moment through the decision model; The decision-making braking module is used to execute vehicle braking control according to the braking decision of the vehicle.

8. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 5.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute the method according to any one of claims 1 to 5.

Images