Vehicle State Prediction Method, Device, Electronic Device, and Storage Medium

Abstract

The present application discloses a vehicle state prediction method, apparatus, electronic device, and storage medium. The method includes: establishing a control quantity prediction model of a target vehicle according to the control quantity of the target vehicle at the previous moment, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment; establishing a state prediction model of the target vehicle according to the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment; and predicting the operating state of the target vehicle at the next moment according to the state prediction model of the target vehicle. By constructing a two-level model of control quantity prediction and state prediction, the present application can predict the operating state of the target vehicle at the next moment, and on the basis of ensuring the accuracy of the vehicle state prediction result, can also provide an accurate and effective basis for the braking control decision of the host vehicle AEB system.

Description

Technical Field

[0001] This application relates to the field of assisted driving technology, and particularly to a method and device for predicting vehicle state, an electronic device, and a storage medium. Background Art

[0002] In the intelligent driving scenario, the host vehicle needs to predict the motion state of target vehicles in its surrounding environment in real time to achieve its own behavior decision-making and emergency avoidance purposes. In the prior art, when completing this prediction task, a machine learning model is usually used in combination with the historical motion trajectory to predict the trajectory of the target vehicle and generate the probability distribution of the prediction result for use by subsequent modules.

[0003] However, due to the complex diversity of the driving environment, the perception accuracy and stability of the traditional prediction model for target vehicles are limited, the accuracy of the prediction result is poor, and it cannot meet the requirements of safe driving; at the same time, the training efficiency of the existing prediction model is low and the computational amount is large, and it cannot achieve real-time prediction of the vehicle motion state, thereby affecting the driving efficiency of the host vehicle. Summary of the Invention

[0004] Embodiments of this application provide a method and device for predicting vehicle state, an electronic device, and a storage medium to achieve the technical effects of accurately and efficiently predicting the vehicle operation state and improving the safety and stability of the AEB system.

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

[0006] According to a first aspect of this application, there is provided a method for predicting vehicle state, the method including:

[0007] Based on the control quantity of the target vehicle at the previous moment, establish a control quantity prediction model of the target vehicle, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment;

[0008] Based on the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment, establish a state prediction model of the target vehicle; and

[0009] Based on the state prediction model of the target vehicle, predict the operation state of the target vehicle at the next moment.

[0010] Optionally, the variables of the operation state of the target vehicle at the next moment at least include one of the following: real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, real-time offset angle. The predicting the operation state of the target vehicle at the next moment based on the state prediction model of the target vehicle includes:

[0011] According to the state prediction model of the target vehicle, predict the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle of the target vehicle at the next moment, and obtain the predicted values of the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle of the target vehicle at the next moment.

[0012] Optionally, the control quantity includes the real-time acceleration of the target vehicle. Based on the control quantity of the target vehicle at the previous moment, establish a control quantity prediction model of the target vehicle, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment, including:

[0013] Based on the acceleration of the target vehicle at the previous moment in the control quantity and the brake light signal information of the target vehicle in the measurable input quantity, establish an acceleration prediction model of the target vehicle. The acceleration prediction model becomes a non-linear model when the brake light signal information of the target vehicle is detected to change, and performs linear interpolation according to the change of the acceleration at the previous moment when the change of the brake light signal information of the target vehicle is not detected, so as to predict the change amount of the acceleration at the current moment.

[0014] Optionally, the measurable input quantity includes the real-time speed of the host vehicle, the acceleration of the host vehicle, and the offset angle of the host vehicle, and the output quantity includes the time to collision. Based on the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment, establish a state prediction model of the target vehicle, including:

[0015] Based on the acceleration of the target vehicle at the current moment, the real-time speed of the host vehicle, the acceleration of the host vehicle, the offset angle of the host vehicle, and the time to collision of the target vehicle at the current moment, establish a state prediction model of the target vehicle.

[0016] Optionally, the control quantity prediction model of the target vehicle further includes a first calculation factor, a second calculation factor, a third calculation factor, a fourth calculation factor, and a fifth calculation factor required for the prediction of the state prediction model.

[0017] Among them, the first calculation factor is related to the vehicle offset angle and the brake light signal information, the second calculation factor is related to the maximum braking deceleration of the host vehicle, the third calculation factor is related to the deceleration output by the ABS system when the host vehicle steers, the fourth calculation factor is a constant, and the fifth calculation factor is related to the vehicle offset angle.

[0018] Optionally, the state prediction model of the target vehicle further includes a sixth calculation factor, a seventh calculation factor, an eighth calculation factor, a ninth calculation factor, and a tenth calculation factor required for the prediction of the control quantity prediction model.

[0019] Wherein, the sixth calculation factor is related to vehicle acceleration, vehicle real-time speed, and vehicle offset angle; the seventh calculation factor is a first matrix relationship established based on the vehicle offset angle; the eighth calculation factor is a second matrix relationship established based on the vehicle offset angle; the ninth calculation factor is related to vehicle offset angle and vehicle acceleration; the tenth calculation factor is related to vehicle offset angle and vehicle real-time speed.

[0020] Optionally, the method further includes: obtaining the real-time state information of the target vehicle and the host vehicle, forming a preset system based on the target vehicle and the host vehicle, and establishing a steady-state prediction model for the preset system.

[0021] According to a second aspect of the present application, there is provided a vehicle state prediction device, the device includes:

[0022] A first model establishment module, configured to establish a control quantity prediction model of the target vehicle according to the control quantity of the target vehicle at the previous moment, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment;

[0023] A second model establishment module, configured to establish a state prediction model of the target vehicle according to the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment; and a prediction module, configured to predict the operating state of the target vehicle at the next moment according to the state prediction model of the target vehicle.

[0024] According to a third aspect of the present application, there is provided an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, the executable instructions, when executed, cause the processor to execute the vehicle state prediction method as described in any one of the above.

[0025] According to a fourth aspect of the present application, there is provided a computer-readable storage medium, the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device is caused to execute the vehicle state prediction method as described in any one of the above.

[0026] At least one of the technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0027] Based on the control quantity of the target vehicle at the previous moment, a control quantity prediction model of the target vehicle is established, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment; based on the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment, a state prediction model of the target vehicle is established; and based on the state prediction model of the target vehicle, the running state of the target vehicle at the next moment is predicted. By constructing a two-level model of control quantity prediction and state prediction, the accuracy of the vehicle state prediction result is ensured, and the running state of the target vehicle at the next moment can be predicted efficiently and stably. At the same time, it can also provide an accurate and effective basis for the braking control of the host vehicle's AEB system. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The schematic embodiments and descriptions thereof of the present application are used to explain the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0029] Figure 1 It is a schematic flowchart of a vehicle state prediction method in an embodiment of the present application;

[0030] Figure 2 It is a schematic structural diagram of a vehicle state prediction device in an embodiment of the present application;

[0031] Figure 3 It is a schematic structural diagram of an electronic device in an embodiment of the present application;

[0032] Figure 4 It is a schematic structural diagram of a computer-readable storage medium in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments and corresponding drawings of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0034] As mentioned above, due to the complexity and diversity of driving scenarios, the perception accuracy and stability of the target vehicle in the prior art are limited. The traditional prediction model cannot meet the safety requirements, and there are errors in the prediction results. As a result, the warning and braking times of the AEB system (Autonomous Emergency Braking) deviate, resulting in poor safety and comfort of the system.

[0035] Based on this, in the embodiments of the present application, a vehicle state prediction method is proposed to accurately and efficiently predict the running state of the vehicle, and at the same time, improve the safety and stability of the AEB system.

[0036] The technical concept of the present application is to establish a control quantity prediction model of the target vehicle according to the control quantity of the target vehicle at the previous moment, and establish a state prediction model of the target vehicle according to the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment; by constructing a two-level model of control quantity prediction and state prediction, predict the running state of the target vehicle at the next moment, while ensuring the accuracy and accuracy of the vehicle state prediction result, and can also provide an accurate and effective basis for the braking control of the host vehicle AEB system.

[0037] The following will describe in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.

[0038] As Figure 1 shown, the method includes the following steps S110 to S130:

[0039] Step S110, establish a control quantity prediction model of the target vehicle according to the control quantity of the target vehicle at the previous moment, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment.

[0040] In an embodiment of the present application, since the current control quantity of the target vehicle cannot be obtained, therefore, in this embodiment, the control quantity of the target vehicle at the previous moment is obtained through the perception module of the host vehicle, and a control quantity prediction model for the target vehicle is established according to the control quantity of the target vehicle at the previous moment.

[0041] In the control quantity prediction model, t , k+1 , k-1 , , k ,

[0042] , k , k+1 ,

[0043] , k-1 ,

[0041] represents the previous moment, t k represents the current moment, t k+1 represents the next moment.

[0042] It is preset that the control quantity of the target vehicle at t k-1 moment is u(k - 1), then the control quantity of the target vehicle at t k moment is u(k), the control quantity of the target vehicle at t k+1 moment is u(k + 1), m(t) represents the relational expression related to the brake light signal information of the target vehicle, n(t) represents the relational expression related to the turn signal information of the target vehicle, p(k) represents the relational expression related to the lane change probability of the target vehicle, and the control quantity prediction model of the target vehicle is established as:

[0043]

[0044] where \(u = [a o \), \(n = [\rho t \), \(m = [\rho b \), \(p = [\delta l \);

[0045] B du = [-\tau b \), \(B dv = [-\tau t \),

[0046] The meanings of the parameters in the above model are as follows:

[0047] a o represents the real-time acceleration of the target vehicle, \(\rho b represents the brake light signal information of the target vehicle, \(\rho t represents the turn signal information of the target vehicle, \(\delta l represents the lane change probability of the target vehicle;

[0048] A d represents the first calculation factor, \(B du represents the second calculation factor, \(B dv represents the third calculation factor, \(C d represents the fourth calculation factor, \(D dv represents the fifth calculation factor, where, represents the real-time offset angle of the host vehicle, represents the real-time offset angle of the target vehicle, \(\tau d represents the maximum braking deceleration that the EPS (Electric Power Steering) can provide, \(\tau t represents the deceleration output by the ABS system (antilock brake system) during steering.

[0049] Using the above control quantity prediction model, the control quantity \(u(k)\) of the target vehicle at the current moment can be predicted. Substituting the control quantity \(u(k)\) into the state prediction model of the target vehicle, the operating state of the target vehicle at the next moment can be predicted.

[0050] Step S120, establish a state prediction model of the target vehicle according to the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment.

[0051] In the state prediction model, \(t k-1Denote the previous moment as \(t\). k Denote the current moment as \(t\). k+1 Denote the next moment. Assume that the variable of the operating state of the preset target vehicle at \(t\). k moment is \(x(k)\), then the state prediction model of the target vehicle is as follows:

[0052]

[0053] In the formula, the relational expressions related to \(x(k)\), \(u(k)\), \(v(k)\), and \(y(k)\) are as follows:

[0054] \(u = [a o \), \(y = [TTC]\);

[0055]

[0056]

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

[0058] \(x(k + 1)\) is the predicted value of the variable of the operating state of the target vehicle at \(t\). k+1 moment, \(u(k)\), \(v(k)\), and \(y(k)\) are the control quantity of the target vehicle, the measurable input quantity of the host vehicle, and the output quantity of the target vehicle in the model predictive control processor of the target vehicle system at \(t\). k moment respectively;

[0059] \(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 speed 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 host vehicle, \(a m represents the real-time acceleration of the host vehicle, represents the real-time offset angle of the host vehicle, represents the difference between the real-time offset angles of the host vehicle and the target vehicle (i.e., the included angle formed by the head orientations of the host vehicle and the target vehicle), and TTC represents the collision time of the target vehicle;

[0060] \(A\) 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, \(D vThe tenth calculation factor is represented as, 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.

[0061] Step S130: Predict the operating state of the target vehicle at the next moment according to the state prediction model of the target vehicle.

[0062] In the embodiment of the present application, according to the control quantity u(k - 1) of the target vehicle at the previous moment, a control quantity prediction model of the target vehicle is established, and the control quantity u(k) of the target vehicle at the current moment is calculated; according to the control quantity u(k) of the target vehicle at the current moment, the measurable input quantity v(k) of the host vehicle at the current moment, and the output quantity y(k) of the target vehicle at the current moment, a state prediction model of the target vehicle is established; by constructing the above-mentioned two-level models of control quantity prediction and state prediction, the prediction of the operating state of the target vehicle at the next moment can be realized, that is, the prediction of the variable x(k + 1) of the operating state of the target vehicle at time t k+1 is realized.

[0063] The embodiment of the present application adopts such a two-level prediction model, and combines 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 result; at the same time, it provides an accurate and effective basis for the braking control of the host vehicle's AEB system, enabling the host vehicle to make more accurate and efficient emergency braking decisions on the premise of ensuring safety, and effectively improving the driving comfort.

[0064] In an embodiment of the present application, the variables of the operating state of the target vehicle at the next moment at least include one of the following: real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, real-time offset angle. Predicting the operating state of the target vehicle at the next moment according to the state prediction model of the target vehicle includes:

[0065] Predict the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle of the target vehicle at the next moment according to the state prediction model of the target vehicle, and obtain the predicted values of the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle of the target vehicle at the next moment.

[0066] Specifically, in the above control quantity prediction model and state prediction model, the variable of the vehicle operating state of the target vehicle at time tk is x(k), and the matrix relationship expressions involved in x(k) include:

[0067] The real-time lateral distance d of the target vehicle at the current moment p, the real-time longitudinal distance d of the target vehicle H , the real-time lateral speed V of the target vehicle p , the real-time longitudinal speed V of the target vehicle H , the real-time offset angle of the target vehicle It can be seen that in this embodiment, the predicted value x(k + 1) of the operating state variable of the target vehicle at the next moment can be predicted according to the operating state variable of the target vehicle at the current moment in the state prediction model; meanwhile, the predicted value includes the real-time lateral distance, the real-time longitudinal distance, the real-time lateral speed, the real-time longitudinal speed, and the real-time offset angle.

[0068] Furthermore, in an embodiment of the present application, the control quantity includes the real-time acceleration of the target vehicle, and a control quantity prediction model of the target vehicle is established according to the control quantity of the target vehicle at the previous moment, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment, including: an acceleration prediction model of the target vehicle is established according to the acceleration of the target vehicle at the previous moment in the control quantity and the brake light signal information of the target vehicle in the measurable input quantity, where the acceleration prediction model is used to become a non-linear model when the brake light signal information of the target vehicle is detected to change, and perform linear interpolation according to the change of the acceleration at the previous moment when the brake light signal information of the target vehicle is not detected to change, so as to predict the change amount of the acceleration at the current moment.

[0069] Specifically, in the control quantity prediction model, since the current control quantity of the target vehicle cannot be obtained, the control quantity of the target vehicle at the previous moment is obtained through the perception module of the host vehicle, and the control quantity prediction model can be used to predict the control quantity u(k) of the target vehicle at the current moment, that is, the relationship expression involved in predicting the control quantity u(k) represents the real-time acceleration a of the target vehicle o , substituting the predicted control quantity u(k) at the current moment into the state prediction model of the target vehicle, the operating state of the target vehicle at the next moment can be predicted.

[0070] It can be understood that only at the moment of vehicle braking and non-braking, the acceleration of the target vehicle is non-linear; in other scenarios, the acceleration of the target vehicle can be considered as a linear change model. Therefore, the brake light signal information of the target vehicle observable by the host vehicle is introduced in this embodiment.

[0071] In this embodiment, as described above, in the control quantity prediction model of the target vehicle, u = [a o , n = [ρ t , m = [ρ b , p = [δ l ; a orepresents the real-time acceleration of the target vehicle, ρ b represents the brake light status of the target vehicle, ρ t represents the turn signal status of the target vehicle, δ l represents the lane-changing probability of the target vehicle. τ b represents the maximum braking deceleration that the EPS can provide, τ t represents the deceleration output by the ABS system during steering. Therefore, the measurable input quantity can be designed in the following form. For example, when the brake light is on, it is set to 1, and when the brake light is off, it is set to 0. Thus, an acceleration prediction model of the target vehicle is established. When the brake light signal information changes, the acceleration model becomes non-linear in a short time; when the change of the brake light signal information of the target vehicle is not detected, linear interpolation can be performed according to the change of the acceleration a o in u(k - 1) at the previous moment to predict the change of the control quantity u(k).

[0072] In an embodiment of the present application, the measurable input quantity includes the real-time speed v m of the host vehicle, the acceleration a m of the host vehicle, and the offset angle of the host vehicle. The output quantity includes the time to collision TTC. According to the control quantity u(k) of the target vehicle at the current moment, the measurable input quantity v(k) of the host vehicle at the current moment, and the output quantity y(k) of the target vehicle at the current moment, a state prediction model of the target vehicle is established, including: establishing the state prediction model of the target vehicle according to the acceleration of the target vehicle at the current moment, the real-time speed of the host vehicle, the acceleration of the host vehicle, the offset angle of the host vehicle, and the time to collision of the target vehicle at the current moment.

[0073] As described above, the state prediction model can be established by using u(k), v(k), and y(k). u(k), v(k), and y(k) are respectively the control quantity of the target vehicle, the measurable input quantity of the host vehicle, and the output quantity of the target vehicle in the model predictive control processor of the target vehicle system at time t k moment, where u(k), v(k), and y(k) are respectively related to the acceleration of the target vehicle at the current moment, the real-time speed of the host vehicle, the acceleration, the offset angle, and the time to collision of the target vehicle. The specific expressions are as follows:

[0074] u = [a o , y = [TTC];

[0075] Therefore, in this embodiment, the state of the vehicle at time t k can be used to predict the target vehicle at time t k+1The operating state variable x(k+1) at a moment.

[0076] In another embodiment of the present application, the control quantity prediction model of the target vehicle further includes a first calculation factor, a second calculation factor, a third calculation factor, a fourth calculation factor, and a fifth calculation factor required for the prediction of the state prediction model. The specific expressions are as follows:

[0077] B du =[-τ b , B dv =[-τ t ,

[0078] It can be seen that the first calculation factor A d is related to the offset angle between the target vehicle and the host vehicle and the brake light signal information of the target vehicle. The second calculation factor B du is related to the maximum braking deceleration that the host vehicle EPS system can provide. The third calculation factor B dv is related to the deceleration output by the host vehicle ABS system during steering. The fourth calculation factor C d is a constant, and the fifth calculation factor D dv is related to the offset angle of the target vehicle.

[0079] In an embodiment of the present application, the state prediction model of the target vehicle further includes a sixth calculation factor, a seventh calculation factor, an eighth calculation factor, a ninth calculation factor, and a tenth calculation factor required for the prediction of the control quantity prediction model. The specific expressions are as follows:

[0080]

[0081]

[0082] It can be understood that the sixth calculation factor A is related to the host vehicle acceleration, the host vehicle real-time speed, and the offset angle between the host 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 is a second matrix relationship established based on 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. The tenth calculation factor D v is related to the vehicle offset angle and the speed of the target vehicle.

[0083] In some embodiments of the present application, the vehicle state prediction method further includes: obtaining the real-time state information of the target vehicle and the host vehicle, forming a preset system based on the target vehicle and the host vehicle, and establishing a steady-state prediction model for the preset system. The preset system and the steady-state prediction model serve as the construction basis for the aforementioned two-level prediction model.

[0084] An embodiment of the present application also provides a vehicle state prediction device 200, as Figure 2 shown, the device includes:

[0085] A first model establishment module 210, configured to establish a control quantity prediction model of the target vehicle according to the control quantity of the target vehicle at the previous moment, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment.

[0086] In an embodiment of the present application, since the current control quantity of the target vehicle cannot be obtained, in this embodiment, the control quantity of the target vehicle at the previous moment is obtained through the perception module of the host vehicle, and a control quantity prediction model for the target vehicle is established according to the control quantity of the target vehicle at the previous moment.

[0087] In the control quantity prediction model, t k-1 represents the previous moment, t k represents the current moment, and t k+1 represents the next moment. It is assumed that the control quantity of the target vehicle at time t k-1 is u(k - 1), then the control quantity of the target vehicle at time t k is u(k), and the control quantity of the target vehicle at time t k+1 is u(k + 1). m(k) represents a relational expression related to the brake light signal information of the target vehicle, n(k) represents a relational expression related to the turn signal information of the target vehicle, and p(k) represents a relational expression related to the lane change probability of the target vehicle. The control quantity prediction model of the target vehicle is:

[0088]

[0089] In the formula, u = [a o , n = [ρ t , m = [ρ b , p = [δ l ;

[0090] B du = [-τ b , B dv = [-τ t ,

[0091] The meanings of the parameters in the above model are as follows:

[0092] a o represents the real-time acceleration of the target vehicle, ρ b represents the brake light signal information of the target vehicle, ρ t represents the turn signal information of the target vehicle, δ l represents the lane-changing probability of the target vehicle;

[0093] A d represents the first calculation factor, B du represents the second calculation factor, B dv represents the third calculation factor, C d represents the fourth calculation factor, D dv represents the fifth calculation factor, where represents the real-time offset angle of the host vehicle, represents the real-time offset angle of the target vehicle, τ b represents the maximum braking deceleration that EPS (Electric Power Steering) can provide, τ t represents the deceleration output by the ABS system (antilock brake system) during steering.

[0094] Using the above control quantity prediction model, the control quantity u(k) of the target vehicle at the current moment can be predicted. Substituting the control quantity u(k) into the state prediction model of the target vehicle, the operating state of the target vehicle at the next moment can be predicted.

[0095] The second model establishment module 220 is used to establish the state prediction model of the target vehicle according to the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment.

[0096] In the state prediction model, t k-1 represents the previous moment, t k represents the current moment, t k+1 represents the next moment. It is preset that the variable of the vehicle operating state of the target vehicle at t k moment is x(k), then the state prediction model of the target vehicle is as follows:

[0097]

[0098] In the formula, the relational expressions related to x(k), u(k), v(k), and y(k) are as follows:

[0099] u = [a o, y = [TTC];

[0100]

[0101]

[0102] The meanings of the parameters in the above model are as follows:

[0103] x(k + 1) is the predicted value of the variable of the operating state of the target vehicle at time t k+1 At time t, u(k), v(k), and y(k) are the control quantity of the target vehicle, the measurable input quantity of the host vehicle, and the output quantity of the target vehicle in the model predictive control processor of the target vehicle system, respectively; k At time t

[0104] 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 speed 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 host vehicle, a m represents the real-time acceleration of the host vehicle, represents the real-time offset angle of the host vehicle, represents the difference between the real-time offset angles of the host vehicle and the target vehicle (i.e., the included angle formed by the head orientations of the host vehicle and the target vehicle), and TTC represents the collision time of the target vehicle;

[0105] 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, D v represents the tenth calculation factor, y(k - 1) represents the output quantity of the target vehicle at the previous moment, and y(k) represents the output quantity of the target vehicle at the current moment.

[0106] The prediction module 230 is configured to predict the operating state of the target vehicle at the next moment according to the state prediction model of the target vehicle.

[0107] In the embodiment of the present application, according to the control quantity u(k-1) of the target vehicle at the previous moment, a control quantity prediction model of the target vehicle is established, and the control quantity u(k) of the target vehicle at the current moment is calculated; according to the control quantity u(k) of the target vehicle at the current moment, the measurable input quantity v(k) of the host vehicle at the current moment, and the output quantity y(k) of the target vehicle at the current moment, a state prediction model of the target vehicle is established; by constructing the above-mentioned two-level models of control quantity prediction and state prediction, the prediction of the operating state of the target vehicle at the next moment can be realized, that is, the prediction of the variable x(k+1) of the operating state of the target vehicle at time t k+1 is realized.

[0108] The embodiment of the present application adopts such a two-level prediction model and combines 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 result; at the same time, it provides an accurate and effective basis for the braking control of the host vehicle's AEB system, enabling the host vehicle to make more accurate and efficient emergency braking decisions on the premise of ensuring safety, and effectively improving the driving comfort.

[0109] In an embodiment of the present application, in the prediction module 230,

[0110] The variables of the operating state of the target vehicle at the next moment at least include one of the following: real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, real-time offset angle. Predicting the operating state of the target vehicle at the next moment according to the state prediction model of the target vehicle includes:

[0111] According to the state prediction model of the target vehicle, predicting the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle of the target vehicle at the next moment, and obtaining the predicted values of the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle of the target vehicle at the next moment.

[0112] In an embodiment of the present application, in the first model establishment module 210,

[0113] The control quantity includes the real-time acceleration of the target vehicle. Establishing the control quantity prediction model of the target vehicle according to the control quantity of the target vehicle at the previous moment, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment, includes:

[0114] An acceleration prediction model of the target vehicle is established based on the acceleration of the target vehicle at the previous moment in the control quantity and the brake light signal information of the target vehicle in the measurable input quantity. Wherein, the acceleration prediction model is used to become a non-linear model when the change of the brake light signal information of the target vehicle is detected, and to perform linear interpolation according to the change of the acceleration at the previous moment when the change of the brake light signal information of the target vehicle is not detected, so as to predict the change amount of the acceleration at the current moment.

[0115] In an embodiment of the present application, in the second model establishment module 220,

[0116] The measurable input quantity includes the real-time speed of the host vehicle, the acceleration of the host vehicle, and the offset angle of the host vehicle, and the output quantity includes the collision time. Establishing the state prediction model of the target vehicle according to the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment includes:

[0117] Establish the state prediction model of the target vehicle according to the acceleration of the target vehicle at the current moment, the real-time speed of the host vehicle, the acceleration of the host vehicle, the offset angle of the host vehicle, and the collision time of the target vehicle at the current moment.

[0118] In an embodiment of the present application, in the first model establishment module 210,

[0119] The control quantity prediction model of the target vehicle further includes a first calculation factor, a second calculation factor, a third calculation factor, a fourth calculation factor, and a fifth calculation factor required for the prediction of the state prediction model. Wherein, the first calculation factor is related to the vehicle offset angle and the brake light signal information, the second calculation factor is related to the maximum braking deceleration of the host vehicle, the third calculation factor is related to the deceleration output by the ABS system when the host vehicle turns, the fourth calculation factor is a constant, and the fifth calculation factor is related to the vehicle offset angle.

[0120] In an embodiment of the present application, in the second model establishment module 220,

[0121] The state prediction model of the target vehicle further includes a sixth calculation factor, a seventh calculation factor, an eighth calculation factor, a ninth calculation factor, and a tenth calculation factor required for the prediction of the control quantity prediction model.

[0122] Among them, the sixth calculation factor is related to the vehicle acceleration, the vehicle real-time speed, and the vehicle offset angle. The seventh calculation factor is based on the first matrix relationship established based on the vehicle offset angle. The eighth calculation factor is based on the second matrix relationship established based on the vehicle offset angle. The ninth calculation factor is related to the vehicle offset angle and the vehicle acceleration. The tenth calculation factor is related to the vehicle offset angle and the vehicle real-time speed.

[0123] In an embodiment of the present application, in the first model establishment module 210 and the second model establishment module 220,

[0124] It further includes: obtaining the real-time state information of the target vehicle and the host vehicle, forming a preset system based on the target vehicle and the host vehicle, and establishing a steady-state prediction model for the preset system.

[0125] It should be noted that the above vehicle state prediction device can implement each step of the vehicle state prediction method provided in the foregoing embodiment. The relevant explanations regarding the vehicle state prediction method are applicable to the vehicle state prediction device and will not be elaborated here.

[0126] In summary, the technical solution of the present application at least achieves the following technical effects: establishing a control quantity prediction model of the target vehicle according to the control quantity of the target vehicle at the previous moment, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment; establishing a state prediction model of the target vehicle according to the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment; and predicting the running state of the target vehicle at the next moment according to the state prediction model of the target vehicle. By constructing a two-level model of control quantity prediction and state prediction, the accuracy of the vehicle state prediction result is ensured, the running state of the target vehicle at the next moment can be predicted efficiently and stably, and at the same time, it can also provide an accurate and effective basis for the braking control of the host vehicle's AEB system, thereby improving the safety, efficiency, and comfort of the driving system.

[0127] It should be noted that:

[0128] The algorithms and displays provided herein are not inherently related to any specific computer, virtual device, or other equipment. Various general-purpose devices can also be used in conjunction with the teachings herein. The structures required to construct such devices are obvious from the above description. In addition, the present application is not directed to any specific programming language. It should be understood that the content of the present application described herein can be implemented using various programming languages, and the description of the specific language above is to disclose the best implementation manner of the present application.

[0129] In the description provided herein, numerous specific details are set forth. It will be understood, however, that embodiments of the present application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

[0130] Similarly, it should be understood that in order to streamline the present application and assist in understanding one or more of the various inventive aspects, in the foregoing description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together in a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting an intention that the claimed present application requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, the inventive aspects lie in less than all the features of the single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate embodiment of the present application.

[0131] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adaptively changed and disposed in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this description (including the accompanying claims, abstract and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise expressly stated, each feature disclosed in this description (including the accompanying claims, abstract and drawings) can be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0132] In addition, those skilled in the art will be able to understand that although some of the embodiments described herein include certain features included in other embodiments but not other features, the combination of the features of different embodiments means that it is within the scope of the present application and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

[0133] Each component embodiment 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 should understand that a microprocessor or a 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 state prediction device according to the embodiments of the present application. The present application can also be implemented as a device or device program (such as a computer program and a computer program product) for executing some or all of the methods described herein. Such a program for implementing the present 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, or provided on a carrier signal, or provided in any other form.

[0134] For example, Figure 3 The structural schematic diagram of an electronic device according to an embodiment of the present 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 can 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 executing any method step in the above methods. For example, the storage space 330 for storing computer-readable program code can include respective computer-readable program codes 331 for implementing various steps in the above methods. The computer-readable program code 331 can be read from or written into one or more computer program products. These computer program products include program code carriers such as hard disks, compact discs (CDs), memory cards, or floppy disks. Such computer program products are usually, for example Figure 4 the computer-readable storage media shown.

[0135] Figure 4 The structural schematic diagram of a computer-readable storage medium according to an embodiment of the present application is shown. The computer-readable storage medium 400 stores computer-readable program code 331 for executing the method steps according to the present application, and can be read by the processor 310 of the electronic device 300. When the computer-readable program code 331 is run by the electronic device 300, it causes the electronic device 300 to execute each step in the method described above. Specifically, the computer-readable program code 331 stored in the computer-readable storage medium can execute the methods shown in any of the above embodiments. The computer-readable program code 331 can be compressed in a suitable form.

[0136] It should be noted that the above embodiments are illustrative of the present application rather than restrictive of the present application, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim listing several devices, several of these devices can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

Claims

1. A vehicle state prediction method, wherein, The method includes: Based on the control quantity of the target vehicle at the previous moment, establish a control quantity prediction model of the target vehicle, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment; Based on the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment, establish a state prediction model of the target vehicle; and Based on the state prediction model of the target vehicle, predict the operating state of the target vehicle at the next moment; The variables of the operating state of the target vehicle at the next moment at least include one of the following: real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, real-time offset angle. The predicting the operating state of the target vehicle at the next moment based on the state prediction model of the target vehicle includes: Based on the state prediction model of the target vehicle, predict the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle of the target vehicle at the next moment, and obtain the predicted values of the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle of the target vehicle at the next moment; The control quantity includes the real-time acceleration of the target vehicle. The establishing the control quantity prediction model of the target vehicle based on the control quantity of the target vehicle at the previous moment, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment, includes: Based on the acceleration of the target vehicle at the previous moment in the control quantity and the brake light signal information of the target vehicle in the measurable input quantity, establish an acceleration prediction model of the target vehicle. The acceleration prediction model is used to become a non-linear model when the brake light signal information of the target vehicle is detected to change, and perform linear interpolation according to the change of the acceleration at the previous moment when the brake light signal information of the target vehicle is not detected to change, so as to predict the change amount of the acceleration at the current moment; The measurable input quantity includes the real-time speed of the host vehicle, the acceleration of the host vehicle, and the offset angle of the host vehicle. The output quantity includes the collision time. The establishing the state prediction model of the target vehicle based on the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment, includes: Based on the acceleration of the target vehicle at the current moment, the real-time speed of the host vehicle, the acceleration of the host vehicle, the offset angle of the host vehicle, and the collision time of the target vehicle at the current moment, establish a state prediction model of the target vehicle.

2. The method according to claim 1, wherein, The control quantity prediction model of the target vehicle further includes a first calculation factor, a second calculation factor, a third calculation factor, a fourth calculation factor, and a fifth calculation factor required for the prediction of the state prediction model. Among them, the first calculation factor is related to the vehicle offset angle and the brake light signal information, the second calculation factor is related to the maximum braking deceleration of the host vehicle, the third calculation factor is related to the deceleration output by the ABS system when the host vehicle is turning, the fourth calculation factor is a constant, and the fifth calculation factor is related to the vehicle offset angle.

3. The method according to claim 1, wherein The state prediction model of the target vehicle further includes a sixth calculation factor, a seventh calculation factor, an eighth calculation factor, a ninth calculation factor, and a tenth calculation factor required for the prediction of the control quantity prediction model. Among them, the sixth calculation factor is related to the vehicle acceleration, the vehicle real-time speed, and the vehicle offset angle, the seventh calculation factor is a first matrix relationship established based on the vehicle offset angle, the eighth calculation factor is a second matrix relationship established based on the vehicle offset angle, the ninth calculation factor is related to the vehicle offset angle and the vehicle acceleration, and the tenth calculation factor is related to the vehicle offset angle and the vehicle real-time speed.

4. The method according to claim 1, wherein The method further includes: obtaining the real-time state information of the target vehicle and the host vehicle, forming a preset system based on the target vehicle and the host vehicle, and establishing a steady-state prediction model for the preset system.

5. A vehicle state prediction device, wherein, The device includes: A first model establishment module, configured to establish a control quantity prediction model of the target vehicle according to the control quantity of the target vehicle at the previous moment, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment; A second model establishment module, configured to establish a state prediction model of the target vehicle according to the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment; and A prediction module, configured to predict the operating state of the target vehicle at the next moment according to the state prediction model of the target vehicle; The variables of the operating state of the target vehicle at the next moment at least include one of the following: real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, real-time offset angle. Predicting the operating state of the target vehicle at the next moment according to the state prediction model of the target vehicle includes: Predicting the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle of the target vehicle at the next moment according to the state prediction model of the target vehicle, and obtaining the predicted values of the real-time longitudinal distance, real-time lateral distance, real-time longitudinal speed, real-time lateral speed, and real-time offset angle of the target vehicle at the next moment; The control quantity includes the real-time acceleration of the target vehicle. Establishing the control quantity prediction model of the target vehicle according to the control quantity of the target vehicle at the previous moment, where the control quantity prediction model is used to predict the control quantity of the target vehicle at the current moment, includes: An acceleration prediction model of the target vehicle is established based on the acceleration of the target vehicle at the previous moment in the control quantity and the brake light signal information of the target vehicle in the measurable input quantity. The acceleration prediction model is used to become a non-linear model when the brake light signal information of the target vehicle is detected to change, and to perform linear interpolation according to the change of the acceleration at the previous moment when the brake light signal information of the target vehicle is not detected to change, so as to predict the change amount of the acceleration at the current moment. The measurable input quantity includes the real-time speed of the host vehicle, the acceleration of the host vehicle, and the offset angle of the host vehicle. The output quantity includes the collision time. Establishing the state prediction model of the target vehicle according to the control quantity of the target vehicle at the current moment, the measurable input quantity of the host vehicle at the current moment, and the output quantity of the target vehicle at the current moment includes: Establish the state prediction model of the target vehicle according to the acceleration of the target vehicle at the current moment, the real-time speed of the host vehicle, the acceleration of the host vehicle, the offset angle of the host vehicle, and the collision time of the target vehicle at the current moment.

6. An electronic device, comprising: A processor; And A memory arranged to store computer-executable instructions, the executable instructions, when executed, causing the processor to execute the method according to any one of claims 1 to 4.

7. A computer-readable storage medium storing one or more programs, the one or more programs, when executed by an electronic device including a plurality of application programs, causing the electronic device to execute the method according to any one of claims 1 to 4.

Images