CN114763149A

CN114763149A - Automatic driving control method and device for vehicle and electronic equipment

Info

Publication number: CN114763149A
Application number: CN202210517268.7A
Authority: CN
Inventors: 刘征宇; 谭益农; 朱振广; 梁琪; 李柳涛
Original assignee: Apollo Intelligent Technology Beijing Co Ltd
Current assignee: Apollo Intelligent Technology Beijing Co Ltd
Priority date: 2022-05-11
Filing date: 2022-05-11
Publication date: 2022-07-19

Abstract

The disclosure provides an automatic driving control method and device for a vehicle and electronic equipment, and relates to the technical field of artificial intelligence, in particular to the technical field of automatic driving, deep learning and intelligent transportation. The specific implementation scheme is as follows: determining the current vehicle state information of the vehicle and a model parameter sequence corresponding to the vehicle state information, wherein the model parameter sequence comprises: model parameter information of each prediction time point in a prediction time domain is obtained by a model prediction controller, wherein the model parameter information at different prediction time points is different; determining a control quantity sequence by using a model prediction controller according to the model parameter sequence and the expected track of the vehicle; according to the control quantity sequence, automatic driving control processing is carried out on the vehicle, so that the model parameter sequence can be determined based on the current vehicle state information of the vehicle; and aiming at different prediction time points, different model parameter information is adopted, the convergence speed of the model prediction controller is increased, and the automatic driving control efficiency of the vehicle is improved.

Description

Automatic driving control method and device for vehicle and electronic equipment

Technical Field

The present disclosure relates to the field of artificial intelligence technologies, and in particular, to the field of automated driving, deep learning, and intelligent transportation technologies, and in particular, to an automated driving control method and apparatus for a vehicle, and an electronic device.

Background

Currently, in the related art, in the lateral-longitudinal control of the automatic driving, model parameter information is determined based on speed, curvature, and acceleration information of the vehicle; and then, the model predictive controller is used for carrying out automatic driving control on the vehicle according to the model parameter information.

In the scheme, the model parameter information is fixed, and the convergence speed of the model prediction controller is low, so that the automatic driving control efficiency of the vehicle is reduced.

Disclosure of Invention

The disclosure provides an automatic driving control method and device for a vehicle and electronic equipment.

According to an aspect of the present disclosure, there is provided an automatic driving control method of a vehicle, including: determining current vehicle state information of a vehicle and a model parameter sequence corresponding to the vehicle state information, wherein the model parameter sequence comprises: model parameter information of the model prediction controller at each prediction time point in a prediction time domain, wherein the model parameter information at different prediction time points is different; determining a control quantity sequence according to the model parameter sequence and the expected track of the vehicle by using the model predictive controller, wherein the control quantity sequence comprises: a lateral control amount and a longitudinal control amount at each of the predicted time points; and carrying out automatic driving control processing on the vehicle according to the transverse control quantity and the longitudinal control quantity at the first prediction time point in the prediction time domain.

According to another aspect of the present disclosure, there is provided an automatic driving control apparatus of a vehicle, including: the first determination module is used for determining the current vehicle state information of a vehicle and a model parameter sequence corresponding to the vehicle state information, wherein the model parameter sequence comprises: model parameter information of the model prediction controller at each prediction time point in a prediction time domain, wherein the model parameter information at different prediction time points is different; a second determining module, configured to determine a control quantity sequence according to the model parameter sequence and the desired trajectory of the vehicle by using the model predictive controller, where the control quantity sequence includes: a lateral control amount and a longitudinal control amount at each of the predicted time points; and the control module is used for carrying out automatic driving control processing on the vehicle according to the transverse control quantity and the longitudinal control quantity at the first prediction time point in the prediction time domain.

According to another aspect of the present disclosure, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of automatic driving control of a vehicle as set forth above in the present disclosure.

According to still another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the automatic driving control method of a vehicle set forth above in the present disclosure.

According to yet another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method for automatic driving control of a vehicle as set forth above in the present disclosure.

It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic illustration according to a first embodiment of the present disclosure;

FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure;

FIG. 3 is a schematic diagram according to a third embodiment of the present disclosure;

FIG. 4 is a schematic diagram according to a fourth embodiment of the present disclosure;

fig. 5 is a block diagram of an electronic device for implementing an automatic driving control method of a vehicle according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of embodiments of the present disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In order to solve the problems, the disclosure provides an automatic driving control method and device for a vehicle and an electronic device.

Fig. 1 is a schematic diagram of a first embodiment of the present disclosure, and it should be noted that the method for controlling automatic driving of a vehicle according to the embodiment of the present disclosure is applicable to an automatic driving control apparatus of a vehicle, which may be configured in an electronic device, so that the electronic device may perform an automatic driving control function of the vehicle.

The electronic device may be any device having a computing capability, for example, a Personal Computer (PC), a mobile terminal, a server, and the like, and the mobile terminal may be a hardware device having various operating systems, touch screens, and/or display screens, such as an in-vehicle device, a mobile phone, a tablet Computer, a Personal digital assistant, and a wearable device.

As shown in fig. 1, the automatic driving control method of a vehicle may include the steps of:

step 101, determining current vehicle state information of a vehicle and a model parameter sequence corresponding to the vehicle state information, wherein the model parameter sequence comprises: and the model prediction controller predicts the model parameter information at each prediction time point in the prediction time domain, wherein the model parameter information at different prediction time points is different.

In the disclosed embodiment, the current vehicle state information of the vehicle may include at least one of the following vehicle state parameters: a lateral vehicle state parameter, a longitudinal vehicle state parameter, an expected lateral vehicle state parameter, an expected longitudinal vehicle state parameter, a lateral vehicle state parameter error, a longitudinal vehicle state parameter error.

Wherein the lateral vehicle state parameter may comprise at least one of the following: lateral position, lateral course angle, lateral displacement, lateral velocity, lateral acceleration, lateral curvature, yaw rate, front wheel angle. Wherein the longitudinal vehicle state parameters may comprise at least one of the following parameters: longitudinal position, longitudinal displacement, longitudinal velocity, longitudinal acceleration, longitudinal moment. And the error of the transverse vehicle state parameter is the error between the transverse vehicle state parameter and the expected transverse vehicle state parameter. And the error of the longitudinal vehicle state parameter is the error between the longitudinal vehicle state parameter and the expected longitudinal vehicle state parameter.

The automatic driving control device of the vehicle is used for combining the expected track and the current vehicle state information of the vehicle to automatically drive and control the vehicle. The expected track comprises a plurality of expected track points, and each expected track point is provided with a corresponding expected transverse vehicle state parameter and an expected longitudinal vehicle state parameter.

The method for determining the expected transverse vehicle state parameter and the expected longitudinal vehicle state parameter in the current vehicle state information of the vehicle is, for example, to select a matched expected track point from an expected track according to the current transverse vehicle state parameter and the longitudinal vehicle state parameter of the vehicle, and to use the expected transverse vehicle state parameter of the matched expected track point as the expected transverse vehicle state parameter in the current vehicle state information of the vehicle; and taking the expected longitudinal vehicle state parameters of the matched expected track points as the expected longitudinal vehicle state parameters in the current vehicle state information of the vehicle.

The determination of the plurality of vehicle state parameters is used for determining the model parameter sequence, so that different vehicle state information can be differentiated finely by adopting different model parameter sequences, the accuracy of the determined model parameter sequence is improved, the determined model parameter sequence can be better suitable for the current vehicle state information, and the automatic driving control efficiency of the vehicle is further improved.

The Model Predictive Controller (MPC) is configured to predict, according to current vehicle state information, an expected trajectory, and a Model parameter sequence of the vehicle, a lateral Control quantity and a longitudinal Control quantity at each prediction time point in a prediction time domain, so as to perform automatic driving Control processing on the vehicle according to the lateral Control quantity and the longitudinal Control quantity at a first prediction time point in the prediction time domain. The model predictive controller adopts an advanced process control strategy to carry out prediction processing. For example, a sequence of control quantities is randomly determined, and a predicted trajectory is determined based on the sequence of control quantities; adjusting the control quantity sequence once based on the predicted track, the expected track and the constraint information; the above process is repeated until the difference between the predicted trajectory and the desired trajectory satisfies a specified condition.

In an embodiment of the present disclosure, predicting model parameter information at a time point includes: transverse model parameter information and longitudinal model parameter information. Wherein the lateral model parameter information includes: the system comprises a transverse error term penalty weight, a transverse control amount penalty weight and a transverse control amount increment penalty weight. The longitudinal model parameter information includes: the method comprises the steps of a longitudinal error term penalty weight, a longitudinal control quantity penalty weight and a longitudinal control quantity increment penalty weight.

And the transverse error term penalty weight represents the weight of the transverse vehicle state parameter error term. And the longitudinal error term penalty weight represents the weight of the longitudinal vehicle state parameter error term. The different model parameter information at different prediction time points may refer to different penalties of the lateral error term at different prediction time points and/or different penalties of the longitudinal error term at different prediction time points.

The model parameter information can comprise a plurality of punishment weights, so that attenuation parameters are conveniently set, and then the punishment weights are selected for attenuation processing. Due to the control of the vehicle, generally, the lateral error term and the longitudinal error term at the former prediction time point in the prediction time domain are important, and the lateral error term and the longitudinal error term at the latter prediction time point are not important. Therefore, in order to shorten the convergence speed of the model predictive controller, the weights of the lateral error term and the longitudinal error term at the earlier prediction time point need to be large, and the weights of the lateral error term and the longitudinal error term at the later prediction time point need to be small. That is, the penalty weight of the lateral error term at each prediction time point may be in a decay trend, and/or the penalty weight of the longitudinal error term at each prediction time point may be in a decay trend.

Step 102, determining a control quantity sequence by using a model predictive controller according to the model parameter sequence and the expected track of the vehicle, wherein the control quantity sequence comprises the following steps: the lateral control amount and the longitudinal control amount at the respective predicted time points.

In the embodiment of the present disclosure, the lateral control amount is, for example, a lower front wheel turning angle. The vertical control amount is, for example, a delivered torque.

The model prediction controller is used for determining the transverse control quantity and the longitudinal control quantity at each prediction time point in a prediction time domain at each sampling moment according to the current vehicle state information of the vehicle and the model parameter sequence, and further determining a prediction track; constructing an objective function according to errors of the predicted track and the expected track; and solving and determining a control quantity sequence and outputting the control quantity sequence by combining the objective function and the constraint information.

Wherein, (1) the model predictive controller can determine an initial control quantity sequence; (2) the transverse model in the model prediction controller can determine a predicted transverse vehicle state parameter at a first prediction time point according to the current transverse vehicle state parameter of the vehicle and a transverse control quantity at the first prediction time point; the longitudinal model in the model prediction controller can determine the predicted longitudinal vehicle state parameter at the first prediction time point according to the current longitudinal vehicle state parameter of the vehicle and the transverse control quantity at the first prediction time point; (3) and (5) repeatedly executing the step (2), obtaining the predicted transverse vehicle state parameters and the predicted longitudinal vehicle state parameters at each predicted time point, and further obtaining the predicted track.

And 103, performing automatic driving control processing on the vehicle according to the transverse control quantity and the longitudinal control quantity at the first prediction time point in the prediction time domain.

In the embodiment of the present disclosure, the prediction time points in the prediction time domain may be sorted according to a time sequence, where the first prediction time point is the first prediction time point in the sorting result. For example, the ranking results are t1, t2, t3, t4, t 5. Where t1 is the first predicted time point.

In the embodiment of the disclosure, taking the lateral control quantity as the corner of the lower front wheel and the longitudinal control quantity as the lower torque as an example, the vehicle controls the engine of the vehicle and the like according to the corner of the lower front wheel and the lower torque, thereby realizing the automatic driving control processing.

According to the automatic driving control method of the vehicle, the current vehicle state information of the vehicle and the model parameter sequence corresponding to the vehicle state information are determined, wherein the model parameter sequence comprises the following steps: model parameter information of each prediction time point in a prediction time domain is obtained by a model prediction controller, wherein the model parameter information at different prediction time points is different; determining a control quantity sequence by using a model predictive controller according to the model parameter sequence and the expected track of the vehicle, wherein the control quantity sequence comprises the following steps: a lateral control amount and a longitudinal control amount at each predicted time point; according to the transverse control quantity and the longitudinal control quantity at the first prediction time point in the prediction time domain, automatic driving control processing is carried out on the vehicle, so that a model parameter sequence can be determined based on the current vehicle state information of the vehicle; and aiming at different prediction time points, different model parameter information is adopted, the convergence speed of the model prediction controller is accelerated, the determination speed of the control quantity sequence is further improved, and the automatic driving control efficiency of the vehicle is improved.

In order to accurately determine the model parameter sequence corresponding to the vehicle state information, as shown in fig. 2, fig. 2 is a schematic diagram according to a second embodiment of the present disclosure, in the embodiment of the present disclosure, the model parameter sequence is determined according to the basic model parameter information corresponding to the vehicle state information and the attenuation parameter information. The embodiment shown in fig. 2 may include the following steps:

step 201, determining the current vehicle state information of the vehicle.

Step 202, determining basic model parameter information and attenuation parameter information corresponding to the vehicle state information.

And the basic model parameter information is the model parameter information at the first prediction time point in the prediction time domain. The model parameter information at other prediction time points in the prediction time domain can be determined according to the basic model parameter information and the attenuation parameter information.

In the embodiment of the present disclosure, the automatic driving control device of the vehicle may execute the step 202 by, for example, inputting the vehicle state information into a preset neural network model, and obtaining scaling information output by the neural network model; and determining basic model parameter information and attenuation parameter information corresponding to the vehicle state information according to the scaling information, the reference model parameter information and the reference attenuation parameter information.

The basic model parameter information corresponding to the vehicle state information can be determined according to the scaling information and the reference model parameter information. The reference model parameter information may be model parameter information of an existing vehicle model, or model parameter information of a newly added vehicle model which is manually adjusted or automatically adjusted, and may be set according to actual needs, and is not specifically limited here.

When the reference model parameter information includes a multidimensional control parameter, the scaling information may also be multidimensional, and the number of dimensions is consistent with the number of dimensions of the control parameter in the reference model parameter information. And the multi-dimensional scaling in the scaling information corresponds to the multi-dimensional control parameters in the reference model parameter information one by one and respectively represents the scaling of the corresponding control parameters.

The neural network model has high accuracy, more vehicle state parameters can be considered, refined differentiation of different vehicle state parameters can be achieved, and the accuracy of the determined model parameter sequence is improved. And the use of the scaling information is combined with the constraint on the scaling information, so that the mutation of the model parameter information can be avoided, the accuracy of the determined basic model parameter information is further improved, and the accuracy of the determined model parameter sequence is further improved.

Here, taking the example that the scaling information includes multi-dimensional scaling, the constraint on the scaling information refers to a constraint on the scaling of each dimension. Taking the scaling of the first dimension as an example, the constraint means that the limit range of the scaling of the first dimension is required to be within the limit range. Wherein, for example, the scale ratio of the first dimension needs to be larger than the first scale ratio and smaller than the second scale ratio.

The training process of the neural network model may be, for example, (1) determining an initial neural network model including an initial strategy network, the input of the network being vehicle state information, and the output being scaling information; (2) the initial strategy network provides the scaling information to the control module; (3) the control module determines a model parameter sequence according to the scaling information and the reference model parameter information, and further determines a control quantity sequence by combining the vehicle state information; (4) determining a predicted track according to the vehicle state information and the control quantity sequence in the dynamic simulation environment; combining the predicted track, the expected track and a return function to generate a training sample, and putting the training sample into a memory playback pool; wherein, training the sample includes: the vehicle state parameters at the current moment, the control quantity, the return value and the vehicle state parameters at the next moment; (5) selecting training samples from a memory playback pool, and training an initial neural network model by combining a reinforcement learning algorithm and a value network; wherein, the input of the value network is the scaling information, and the output is the value function used for evaluating the scaling information; (6) and repeating the above 5 steps until the trained neural network model meets the specified training convergence condition.

The formula of the reward function can be shown as the following formula (1):

r(t)＝a₁r₁(t)+a₂r₂(t)+a₃r₃(t)+a₄r₄(t) (1)

wherein, r (t) represents the value of the reward function at the t-predicted time point; r is₁(t) represents error return; r is a radical of hydrogen₂(t) represents error rate of change return; r is₃(t) represents a return of a control variable; r is₄(t) represents the simulated metric report. Wherein, the return of the control quantity variation is-Deltau, and Deltau represents the control quantity variation.

The formula for the error return and the formula for the error change rate return can be shown as the following formulas (2) and (3):

where e (t) represents the error of the t prediction time point, which may include the lateral state parameter error and the longitudinal state parameter error.

The formula for simulating the metric report can be shown as the following formula (4):

r₄(t)＝∑r_4-i(t) (4)

wherein, in one example, the return on collision r_4-1(t) — 500; high and sudden braking return r_4-2(t) — 20; jerk direction reward r_4-3(t) — 20; return for trajectory occurrence replanning r_4-4(t)＝－200。

It should be noted that the four return values are only examples, and may be adjusted according to actual needs, and are not limited specifically here.

And step 203, determining model parameter information at each prediction time point in a prediction time domain according to the basic model parameter information and the attenuation parameter information.

In the embodiment of the present disclosure, the automatic driving control device of the vehicle may perform the process of step 203, for example, by determining serial numbers of respective predicted time points within the prediction time domain; determining attenuation proportion information on each prediction time point according to the attenuation parameter information and the serial number; and determining model parameter information at the prediction time point according to the basic model parameter information and the attenuation proportion information at the prediction time point.

The process of determining the attenuation ratio information at the predicted time point by the automatic driving control device of the vehicle based on the attenuation parameter information and the serial number may be, for example, taking the attenuation parameter information as d, assuming that the serial number at a certain predicted time point is z, the attenuation ratio information at the predicted time point is a result obtained by multiplying the attenuation parameter information by z d, and further, model parameter information at the predicted time point is obtained.

Taking attenuation parameter information as a first attenuation parameter for the lateral error term penalty weight as an example, a calculation formula of the lateral error term penalty weight in the model parameter information at the prediction time point may be as shown in the following formula (5):

Q_i＝Q*d^i-1 (5)

q represents a transverse error term penalty weight in the parameter information of the basic model; q _iRepresenting the penalty weight of the transverse error term at the i-1 st prediction time point; i-1 represents the sequence number at the predicted time point.

Wherein, the basic model parameter information may include: the method comprises the following steps of transverse error item punishment weight, transverse control quantity increment punishment weight, longitudinal error item punishment weight, longitudinal control quantity punishment weight and longitudinal control quantity increment punishment weight. The attenuation parameter information may include: a first attenuation parameter for the lateral error term penalty weight and a second attenuation parameter for the longitudinal error term penalty weight.

The method comprises the steps of determining attenuation proportion information at a forecasting time point according to attenuation parameter information and a serial number, ensuring that the punishment weight of a transverse error item and the punishment weight of a longitudinal error item in model parameter information at each forecasting time point are in an attenuation trend, ensuring that the weight of the transverse error item and the weight of the longitudinal error item at the front forecasting time point are larger, and the weight of the transverse error item and the weight of the longitudinal error item at the rear forecasting time point are smaller, so that the convergence rate of a model predictive controller is shortened, a control quantity sequence can be determined in time, and automatic driving control processing is performed on a vehicle in time.

And 204, determining a model parameter sequence corresponding to the vehicle state information according to the model parameter information at each prediction time point in the prediction time domain.

Step 205, determining a control quantity sequence according to the model parameter sequence and the expected track of the vehicle by using the model predictive controller, wherein the control quantity sequence comprises: the lateral control amount and the longitudinal control amount at the respective predicted time points.

And step 206, performing automatic driving control processing on the vehicle according to the transverse control quantity and the longitudinal control quantity at the first prediction time point in the prediction time domain.

It should be noted that details of step 205 and step 206 may refer to step 102 and step 103 in the embodiment shown in fig. 1, and detailed description thereof is omitted here.

The automatic driving control method of the vehicle of the embodiment of the disclosure determines the current vehicle state information of the vehicle; determining basic model parameter information and attenuation parameter information corresponding to the vehicle state information; determining model parameter information at each prediction time point in a prediction time domain according to the basic model parameter information and the attenuation parameter information; determining a model parameter sequence corresponding to the vehicle state information according to the model parameter information at each prediction time point in the prediction time domain; determining a control quantity sequence according to the model parameter sequence and the expected track of the vehicle by using a model prediction controller, wherein the control quantity sequence comprises the following steps: a lateral control amount and a longitudinal control amount at each prediction time point; according to the transverse control quantity and the longitudinal control quantity at the first prediction time point in the prediction time domain, automatic driving control processing is carried out on the vehicle, so that a model parameter sequence can be determined based on the current vehicle state information of the vehicle; and aiming at different prediction time points, different model parameter information is adopted, the convergence speed of the model prediction controller is accelerated, the determination speed of the control quantity sequence is further improved, and the automatic driving control efficiency of the vehicle is improved.

In order to accurately determine the controlled variable sequence, as shown in fig. 3, fig. 3 is a schematic diagram according to a third embodiment of the present disclosure, in the embodiment of the present disclosure, a horizontal controlled variable and a vertical controlled variable at each prediction time point are respectively determined by using a horizontal model and a vertical model in a model predictive controller and combining with a model parameter sequence, and then the controlled variable sequence is determined. The embodiment shown in fig. 3 may include the following steps:

step 301, determining current vehicle state information of a vehicle and a model parameter sequence corresponding to the vehicle state information, wherein the model parameter sequence includes: model parameter information of each prediction time point in a prediction time domain is obtained by a model prediction controller, wherein the model parameter information at different prediction time points is different; the model parameter information includes: transverse model parameter information and longitudinal model parameter information.

And step 302, determining the transverse control quantity at each prediction time point according to the transverse model parameter information at each prediction time point in the model parameter sequence and the expected track by using the transverse model in the model prediction controller.

In the embodiment of the present disclosure, the automatic driving control device of the vehicle may perform the process of step 302, for example, by determining the lateral vehicle state parameter in the vehicle state information, and the initial lateral control amount at each predicted time point; determining predicted transverse vehicle state parameters at each prediction time point according to the transverse vehicle state parameters and the initial transverse control quantity at each prediction time point by using a transverse model; constructing a first objective function according to the predicted transverse vehicle state parameters at each predicted time point, the expected transverse vehicle state parameters at each predicted time point in the expected track and the transverse model parameter information; and adjusting the initial transverse control quantity at each prediction time point according to the numerical value of the first objective function to obtain the transverse control quantity at each prediction time point.

Wherein, the formula of the transverse model can be shown as the following formula (6):

wherein, y_eRepresenting a lateral displacement in the vehicle state information;

representing a lateral velocity in the vehicle state information; theta.theta._eRepresenting a lateral heading angle in the vehicle state information;

representing a yaw rate in the vehicle state information; δ represents a front wheel rotation angle in the vehicle state information; delta_desThe lateral control amount, i.e., the lower-issued front wheel turning angle, is indicated. Correspondingly, the number of the dimensions of the transverse error term penalty weight may be 5 dimensions, wherein each dimension sequentially represents the error term penalty weight of the transverse displacement, the error term penalty weight of the transverse speed, the error term penalty weight of the transverse heading angle, the error term penalty weight of the yaw speed, and the error term penalty weight of the front wheel rotation angle.

The above equation (6) is integrated over time, and the lateral displacement, the lateral velocity, the lateral course angle, the yaw rate, and the front wheel rotation angle at the next predicted time point can be obtained.

It should be noted that, in the formula (6), the vehicle state parameters in the input of the lateral model are lateral displacement, lateral velocity, lateral heading angle, yaw rate, and front wheel steering angle, which are taken as examples for explanation. The vehicle state parameters in the input of the transverse model can also be replaced by other transverse vehicle state parameters, and the parameters are not limited here and can be set according to actual needs.

Wherein, the formula of the first objective function of the lateral model can be shown as the following formula (7):

wherein J represents a first objective function; y is_iThe lateral vehicle state parameter of the ith prediction time point is obtained according to the lateral vehicle state parameter of the ith-1 prediction time point and the lateral control quantity of the ith prediction time point; y is_riA desired lateral vehicle state parameter representing an ith prediction time point; q represents a transverse error term penalty weight, including the transverse error term penalty weight of each prediction time point; u shape_iA lateral control amount indicating an ith prediction time point; delta U_iA lateral control amount increment representing an ith prediction time point; r1 represents a lateral control penalty weight; r2 represents the lateral control increment penalty weight.

The method comprises the steps of determining predicted transverse vehicle state parameters at each prediction time point by utilizing a transverse model according to transverse vehicle state parameters and initial transverse control quantities at each prediction time point, further constructing a first objective function by combining transverse model parameter information, and adjusting the initial transverse control quantities at each prediction time point to obtain the transverse control quantities at each prediction time point, so that the convergence speed of a model prediction controller can be increased, and the accuracy of the determined transverse control quantities is improved.

And step 303, determining a longitudinal control quantity at each prediction time point according to the longitudinal model parameter information and the expected trajectory at each prediction time point in the model parameter sequence by using the longitudinal model in the model prediction controller.

In the embodiment of the present disclosure, the automatic driving control device of the vehicle may perform the process of step 303, for example, by determining the longitudinal vehicle state parameter in the vehicle state information, and the initial longitudinal control amount at each predicted time point; determining predicted longitudinal vehicle state parameters at each prediction time point according to the longitudinal vehicle state parameters and the initial longitudinal control quantity at each prediction time point by using a longitudinal model; constructing a second objective function according to the predicted longitudinal vehicle state parameters at each predicted time point, the expected longitudinal vehicle state parameters at each predicted time point in the expected track and the longitudinal model parameter information; and adjusting the initial longitudinal control quantity at each prediction time point according to the numerical value of the second objective function to obtain the longitudinal control quantity at each prediction time point.

Wherein, the formula of the longitudinal model can be shown as the following formula (8):

Wherein x represents a longitudinal displacement in the vehicle state information; v represents a longitudinal speed in the vehicle state information; t represents a longitudinal moment in the vehicle state information; t is_desAnd the longitudinal control quantity, namely the issued torque is represented. Corresponding toThe number of the dimensionalities of the longitudinal error term penalty weight can be 3 dimensionalities, wherein each dimensionality sequentially represents the error term penalty weight of longitudinal displacement, the error term penalty weight of longitudinal speed and the error term penalty weight of longitudinal torque.

The above equation (8) is integrated over time, and the longitudinal displacement, the longitudinal velocity, and the longitudinal moment at the next predicted time point can be obtained.

It should be noted that, in the formula (8), the vehicle state parameters in the input of the longitudinal model are taken as longitudinal displacement, longitudinal speed and longitudinal moment for example. The vehicle state parameters in the input of the longitudinal model can also be replaced by other longitudinal vehicle state parameters, which are not limited herein and can be set according to actual needs.

The second objective function can be obtained by correspondingly replacing the transverse vehicle state parameter, the transverse control quantity, the expected transverse vehicle state parameter, the transverse error term penalty weight, the transverse control quantity increment, the transverse control quantity penalty weight and the transverse control quantity increment penalty weight in the formula of the first objective function with the longitudinal vehicle state parameter, the longitudinal control quantity, the expected longitudinal vehicle state parameter, the longitudinal error term penalty weight, the longitudinal control quantity increment, the longitudinal control quantity penalty weight and the longitudinal control quantity increment penalty weight by referring to the formula of the first objective function.

The method comprises the steps of determining predicted longitudinal vehicle state parameters at each prediction time point by using a longitudinal model according to longitudinal vehicle state parameters and initial longitudinal control quantities at each prediction time point, further constructing a second objective function by combining longitudinal model parameter information, and adjusting the initial longitudinal control quantities at each prediction time point to obtain the longitudinal control quantities at each prediction time point, so that the convergence speed of a model prediction controller can be increased, and the accuracy of the determined longitudinal control quantities is improved.

Step 304, determining a control quantity sequence according to the transverse control quantity and the longitudinal control quantity at each predicted time point, wherein the control quantity sequence comprises: the lateral control amount and the longitudinal control amount at the respective predicted time points.

And 305, performing automatic driving control processing on the vehicle according to the transverse control quantity and the longitudinal control quantity at the first prediction time point in the prediction time domain.

It should be noted that, details of step 301 and step 305 may refer to step 101 and step 103 in the embodiment shown in fig. 1, and detailed description is not repeated here.

The automatic driving control method of the vehicle of the embodiment of the disclosure determines the current vehicle state information of the vehicle and the model parameter sequence corresponding to the vehicle state information, wherein the model parameter sequence comprises: model parameter information of the model prediction controller at each prediction time point in a prediction time domain, wherein the model parameter information at different prediction time points is different; determining a transverse control quantity at each prediction time point by using a transverse model in a model prediction controller according to transverse model parameter information and an expected track at each prediction time point in a model parameter sequence; determining longitudinal control quantity at each prediction time point by using a longitudinal model in a model prediction controller according to longitudinal model parameter information and an expected track at each prediction time point in a model parameter sequence; determining a control quantity sequence according to the transverse control quantity and the longitudinal control quantity at each prediction time point; according to the transverse control quantity and the longitudinal control quantity at the first prediction time point in the prediction time domain, automatic driving control processing is carried out on the vehicle, so that a model parameter sequence can be determined based on the current vehicle state information of the vehicle; and aiming at different prediction time points, different model parameter information is adopted, the convergence speed of the model prediction controller is accelerated, the determination speed of the control quantity sequence is further improved, and the automatic driving control efficiency of the vehicle is improved.

In order to realize the embodiment, the disclosure also provides an automatic driving control device of the vehicle.

As shown in fig. 4, fig. 4 is a schematic diagram according to a fourth embodiment of the present disclosure. The automatic driving control device 400 of the vehicle includes: a first determination module 410, a second determination module 420, and a control module 430.

The first determining module 410 is configured to determine current vehicle state information of a vehicle and a model parameter sequence corresponding to the vehicle state information, where the model parameter sequence includes: model parameter information of each prediction time point in a prediction time domain is obtained by a model prediction controller, wherein the model parameter information at different prediction time points is different;

a second determining module 420, configured to determine a control quantity sequence according to the model parameter sequence and the desired trajectory of the vehicle by using the model predictive controller, where the control quantity sequence includes: a lateral control amount and a longitudinal control amount at each of the predicted time points;

and the control module 430 is configured to perform automatic driving control processing on the vehicle according to the lateral control quantity and the longitudinal control quantity at the first predicted time point in the prediction time domain.

As a possible implementation manner of the embodiment of the present disclosure, the first determining module 410 includes: a first determination unit, a second determination unit, a third determination unit and a fourth determination unit; the first determining unit is used for determining the current vehicle state information of the vehicle; the second determining unit is used for determining basic model parameter information and attenuation parameter information corresponding to the vehicle state information;

the third determining unit is configured to determine, according to the basic model parameter information and the attenuation parameter information, model parameter information at each of the prediction time points in the prediction time domain; and the fourth determining unit is configured to determine a model parameter sequence corresponding to the vehicle state information according to the model parameter information at each of the prediction time points in the prediction time domain.

As a possible implementation manner of the embodiment of the present disclosure, the second determining unit is specifically configured to input the vehicle state information into a preset neural network model, and obtain scaling information output by the neural network model; and determining basic model parameter information and attenuation parameter information corresponding to the vehicle state information according to the scaling information, the reference model parameter information and the reference attenuation parameter information.

As a possible implementation manner of the embodiment of the present disclosure, the third determining unit is specifically configured to determine a sequence number of each prediction time point in the prediction time domain; for each prediction time point, determining attenuation proportion information on the prediction time point according to the attenuation parameter information and the serial number; and determining model parameter information at the prediction time point according to the basic model parameter information and the attenuation proportion information at the prediction time point.

As a possible implementation manner of the embodiment of the present disclosure, the model parameter information includes: transverse model parameter information and longitudinal model parameter information; the lateral model parameter information includes: the method comprises the steps of (1) punishing a transverse error item, punishing a transverse control quantity and punishing a transverse control quantity increment; the longitudinal model parameter information includes: the method comprises the steps of a longitudinal error term penalty weight, a longitudinal control quantity penalty weight and a longitudinal control quantity increment penalty weight.

As a possible implementation manner of the embodiment of the present disclosure, the model parameter information includes: a transverse error term punishment weight and a longitudinal error term punishment weight; the attenuation parameter information includes: a first attenuation parameter for the lateral error term penalty weight and a second attenuation parameter for the longitudinal error term penalty weight.

As a possible implementation manner of the embodiment of the present disclosure, the model parameter information includes: transverse model parameter information and longitudinal model parameter information; the second determining module 420 includes: a fifth determining unit, a sixth determining unit, and a seventh determining unit; the fifth determining unit is configured to determine, by using a transverse model in the model predictive controller, a transverse control amount at each of the prediction time points according to the transverse model parameter information at each of the prediction time points in the model parameter sequence and the expected trajectory; the sixth determining unit is configured to determine, by using a longitudinal model in the model predictive controller, a longitudinal control amount at each of the prediction time points according to the longitudinal model parameter information at each of the prediction time points in the model parameter sequence and the expected trajectory; the seventh determining unit is configured to determine the control amount sequence according to the lateral control amount and the longitudinal control amount at each of the prediction time points.

As a possible implementation manner of the embodiment of the present disclosure, the fifth determining unit is specifically configured to determine a lateral vehicle state parameter in the vehicle state information, and an initial lateral control amount at each of the predicted time points; determining the predicted transverse vehicle state parameters at each predicted time point according to the transverse vehicle state parameters and the initial transverse control quantity at each predicted time point by using the transverse model; constructing a first objective function according to the predicted transverse vehicle state parameters at the predicted time points, the expected transverse vehicle state parameters at the predicted time points in the expected track and the transverse model parameter information; and adjusting the initial transverse control quantity at each prediction time point according to the numerical value of the first objective function to obtain the transverse control quantity at each prediction time point.

As a possible implementation manner of the embodiment of the present disclosure, the sixth determining unit is specifically configured to determine a longitudinal vehicle state parameter in the vehicle state information, and an initial longitudinal control amount at each of the predicted time points; determining the predicted longitudinal vehicle state parameters at each predicted time point according to the longitudinal vehicle state parameters and the initial longitudinal control quantity at each predicted time point by using the longitudinal model; constructing a second objective function according to the predicted longitudinal vehicle state parameters at the predicted time points, the expected longitudinal vehicle state parameters at the predicted time points in the expected track and the longitudinal model parameter information; and adjusting the initial longitudinal control quantity at each prediction time point according to the numerical value of the second objective function to obtain the longitudinal control quantity at each prediction time point.

As a possible implementation of the embodiment of the present disclosure, the vehicle state information includes at least one of the following vehicle state parameters: a lateral vehicle state parameter, a longitudinal vehicle state parameter, an expected lateral vehicle state parameter, an expected longitudinal vehicle state parameter, a lateral vehicle state parameter error, a longitudinal vehicle state parameter error.

The automatic driving control device of the vehicle in the embodiment of the disclosure determines the current vehicle state information of the vehicle and a model parameter sequence corresponding to the vehicle state information, wherein the model parameter sequence comprises: model parameter information of each prediction time point in a prediction time domain is obtained by a model prediction controller, wherein the model parameter information at different prediction time points is different; determining a control quantity sequence by using a model predictive controller according to the model parameter sequence and the expected track of the vehicle, wherein the control quantity sequence comprises the following steps: a lateral control amount and a longitudinal control amount at each prediction time point; according to the transverse control quantity and the longitudinal control quantity at the first prediction time point in the prediction time domain, automatic driving control processing is carried out on the vehicle, so that a model parameter sequence can be determined based on the current vehicle state information of the vehicle; and aiming at different prediction time points, different model parameter information is adopted, the convergence speed of the model prediction controller is accelerated, the determination speed of the control quantity sequence is further improved, and the automatic driving control efficiency of the vehicle is improved.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all carried out on the premise of obtaining the consent of the user, and all accord with the regulation of related laws and regulations without violating the good custom of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

According to an embodiment of the present disclosure, there is also provided a vehicle including the automatic driving control apparatus of the vehicle as shown in the fourth embodiment.

FIG. 5 illustrates a schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 5, the apparatus 500 comprises a computing unit 501 which may perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The calculation unit 501, the ROM 502, and the RAM 503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

A number of components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, or the like; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508, such as a magnetic disk, optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

The computing unit 501 may be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 501 executes the respective methods and processes described above, such as the automatic driving control method of the vehicle. For example, in some embodiments, the method of automatic driving control of a vehicle may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM 502 and/or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the above-described automatic driving control method of the vehicle may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured in any other suitable way (e.g., by means of firmware) to perform an automatic driving control method of the vehicle.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. An automatic driving control method of a vehicle, comprising:

determining current vehicle state information of a vehicle and a model parameter sequence corresponding to the vehicle state information, wherein the model parameter sequence comprises: model parameter information of the model prediction controller at each prediction time point in a prediction time domain, wherein the model parameter information at different prediction time points is different;

determining a control quantity sequence according to the model parameter sequence and the expected track of the vehicle by using the model predictive controller, wherein the control quantity sequence comprises: a lateral control amount and a longitudinal control amount at each of the predicted time points;

And carrying out automatic driving control processing on the vehicle according to the transverse control quantity and the longitudinal control quantity at the first prediction time point in the prediction time domain.

2. The method of claim 1, wherein the determining the current vehicle state information of the vehicle and the model parameter sequence corresponding to the vehicle state information comprises:

determining current vehicle state information of a vehicle;

determining basic model parameter information and attenuation parameter information corresponding to the vehicle state information;

determining model parameter information at each prediction time point in the prediction time domain according to the basic model parameter information and the attenuation parameter information;

and determining a model parameter sequence corresponding to the vehicle state information according to the model parameter information at each prediction time point in the prediction time domain.

3. The method of claim 2, wherein the determining base model parameter information and attenuation parameter information corresponding to the vehicle state information comprises:

inputting the vehicle state information into a preset neural network model, and acquiring scaling information output by the neural network model;

and determining basic model parameter information and attenuation parameter information corresponding to the vehicle state information according to the scaling information, the reference model parameter information and the reference attenuation parameter information.

4. The method of claim 2, wherein the determining, according to the base model parameter information and the attenuation parameter information, model parameter information at each of the prediction time points in the prediction time domain comprises:

determining a sequence number of each prediction time point in the prediction time domain;

for each prediction time point, determining attenuation proportion information on the prediction time point according to the attenuation parameter information and the serial number;

and determining model parameter information at the prediction time point according to the basic model parameter information and the attenuation proportion information at the prediction time point.

5. The method of any of claims 1 to 4, wherein the model parameter information comprises: transverse model parameter information and longitudinal model parameter information;

the lateral model parameter information includes: the method comprises the steps of obtaining a transverse error term penalty weight, a transverse control quantity penalty weight and a transverse control quantity increment penalty weight;

the longitudinal model parameter information includes: the method comprises the steps of a longitudinal error term penalty weight, a longitudinal control quantity penalty weight and a longitudinal control quantity increment penalty weight.

6. The method of any of claims 2 to 4, wherein the model parameter information comprises: a transverse error term punishment weight and a longitudinal error term punishment weight;

The attenuation parameter information includes: a first attenuation parameter for the lateral error term penalty weight and a second attenuation parameter for the longitudinal error term penalty weight.

7. The method of claim 1, wherein the model parameter information comprises: transverse model parameter information and longitudinal model parameter information; determining a sequence of control quantities from the sequence of model parameters and the desired trajectory of the vehicle using the model predictive controller, comprising:

determining a transverse control quantity at each prediction time point according to transverse model parameter information at each prediction time point in the model parameter sequence and the expected track by utilizing a transverse model in the model prediction controller;

determining a longitudinal control quantity at each prediction time point according to longitudinal model parameter information at each prediction time point in the model parameter sequence and the expected track by using a longitudinal model in the model prediction controller;

and determining the control quantity sequence according to the transverse control quantity and the longitudinal control quantity at each predicted time point.

8. The method of claim 7, wherein the determining, by using the lateral model in the model predictive controller, the lateral control quantity at each of the predicted time points according to the lateral model parameter information at each of the predicted time points in the model parameter sequence and the desired trajectory comprises:

Determining a transverse vehicle state parameter in the vehicle state information and an initial transverse control quantity at each predicted time point;

determining the predicted transverse vehicle state parameters at each predicted time point according to the transverse vehicle state parameters and the initial transverse control quantity at each predicted time point by using the transverse model;

constructing a first objective function according to the predicted transverse vehicle state parameters at the predicted time points, the expected transverse vehicle state parameters at the predicted time points in the expected track and the transverse model parameter information;

and adjusting the initial transverse control quantity at each prediction time point according to the numerical value of the first objective function to obtain the transverse control quantity at each prediction time point.

9. The method according to claim 7, wherein the determining, by using a longitudinal model in the model predictive controller, a longitudinal control quantity at each of the predicted time points according to longitudinal model parameter information at each of the predicted time points in the model parameter sequence and the desired trajectory comprises:

determining longitudinal vehicle state parameters in the vehicle state information and initial longitudinal control quantity at each predicted time point;

Determining the predicted longitudinal vehicle state parameters at each predicted time point according to the longitudinal vehicle state parameters and the initial longitudinal control quantity at each predicted time point by using the longitudinal model;

constructing a second objective function according to the predicted longitudinal vehicle state parameters at the predicted time points, the expected longitudinal vehicle state parameters at the predicted time points in the expected track and the longitudinal model parameter information;

and adjusting the initial longitudinal control quantity at each prediction time point according to the numerical value of the second objective function to obtain the longitudinal control quantity at each prediction time point.

10. The method according to any one of claims 1 to 4, wherein the vehicle state information comprises at least one of the following vehicle state parameters: a lateral vehicle state parameter, a longitudinal vehicle state parameter, an expected lateral vehicle state parameter, an expected longitudinal vehicle state parameter, a lateral vehicle state parameter error, a longitudinal vehicle state parameter error.

11. An automatic driving control apparatus of a vehicle, comprising:

the first determination module is used for determining the current vehicle state information of a vehicle and a model parameter sequence corresponding to the vehicle state information, wherein the model parameter sequence comprises: model parameter information of each prediction time point in a prediction time domain is obtained by a model prediction controller, wherein the model parameter information at different prediction time points is different;

A second determining module, configured to determine a control quantity sequence according to the model parameter sequence and the desired trajectory of the vehicle by using the model predictive controller, where the control quantity sequence includes: a lateral control amount and a longitudinal control amount at each of the predicted time points;

and the control module is used for carrying out automatic driving control processing on the vehicle according to the transverse control quantity and the longitudinal control quantity at the first prediction time point in the prediction time domain.

12. The apparatus of claim 11, wherein the first determining means comprises: a first determination unit, a second determination unit, a third determination unit and a fourth determination unit;

the first determination unit is used for determining the current vehicle state information of the vehicle;

the second determining unit is used for determining basic model parameter information and attenuation parameter information corresponding to the vehicle state information;

the third determining unit is configured to determine, according to the basic model parameter information and the attenuation parameter information, model parameter information at each of the prediction time points in the prediction time domain;

the fourth determining unit is configured to determine a model parameter sequence corresponding to the vehicle state information according to the model parameter information at each of the prediction time points in the prediction time domain.

13. The apparatus according to claim 12, wherein the second determining unit is specifically configured to,

14. The apparatus of claim 12, wherein the third determination unit is specifically configured to,

15. The apparatus of any of claims 11 to 14, wherein the model parameter information comprises: transverse model parameter information and longitudinal model parameter information;

16. The apparatus of any of claims 12 to 14, wherein the model parameter information comprises: a transverse error term punishment weight and a longitudinal error term punishment weight;

17. The apparatus of claim 11, wherein the model parameter information comprises: transverse model parameter information and longitudinal model parameter information; the second determining module includes: a fifth determining unit, a sixth determining unit, and a seventh determining unit;

the fifth determining unit is configured to determine, by using a transverse model in the model predictive controller, a transverse control amount at each of the prediction time points according to the transverse model parameter information at each of the prediction time points in the model parameter sequence and the expected trajectory;

the sixth determining unit is configured to determine, by using a longitudinal model in the model predictive controller, a longitudinal control amount at each of the prediction time points according to the longitudinal model parameter information at each of the prediction time points in the model parameter sequence and the expected trajectory;

The seventh determining unit is configured to determine the controlled variable sequence according to the lateral controlled variable and the longitudinal controlled variable at each of the predicted time points.

18. The apparatus according to claim 17, characterized in that the fifth determination unit is specifically configured to,

19. The apparatus according to claim 17, wherein the sixth determining unit is specifically configured to,

Determining longitudinal vehicle state parameters in the vehicle state information and initial longitudinal control quantities at the prediction time points;

20. The apparatus of any one of claims 11 to 14, wherein the vehicle state information comprises at least one of the following vehicle state parameters: a lateral vehicle state parameter, a longitudinal vehicle state parameter, an expected lateral vehicle state parameter, an expected longitudinal vehicle state parameter, a lateral vehicle state parameter error, a longitudinal vehicle state parameter error.

21. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-10.

22. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-10.

23. A computer program product comprising a computer program which, when being executed by a processor, carries out the steps of the method according to any one of claims 1-10.

24. A vehicle, comprising: the automatic driving control apparatus of a vehicle according to any one of claims 11 to 20.