CN111216738A

CN111216738A - Vehicle control method and device, electronic equipment and vehicle

Info

Publication number: CN111216738A
Application number: CN202010102094.9A
Authority: CN
Inventors: 郭鼎峰; 谭益农; 朱振广
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Apollo Intelligent Technology Beijing Co Ltd
Priority date: 2020-02-19
Filing date: 2020-02-19
Publication date: 2020-06-02
Anticipated expiration: 2040-02-19
Also published as: CN111216738B

Abstract

The application discloses a control method and device of a vehicle, electronic equipment and the vehicle, which can be used for automatic driving, when the vehicle is controlled based on a preset track line, M reference points are firstly determined on the preset track line, state information corresponding to each reference point in the M reference points is respectively obtained, a target control sequence is determined according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points, then the vehicle is controlled according to the target control sequence, and because the output of the state information of the reference points with the future preset number on the preset track line is considered, namely the consideration of the future prediction following estimation is added, the average error of the state information in the reference points with the future preset number can be ensured to be minimum, and the accuracy of the vehicle control is improved.

Description

Vehicle control method and device, electronic equipment and vehicle

Technical Field

The application relates to the technical field of computers, in particular to an automatic driving technology.

Background

In the technical field of automatic driving, taking a vehicle running process as an example, in the running process of a vehicle, a track to be followed in a future period of time needs to be considered, and control operation is executed in advance based on a track reference line to be followed, so that lag caused by system delay can be reduced, system response can be accelerated, and following precision can be improved.

In general, when a control operation is performed in advance based on a trajectory reference line to be followed, it is a feedforward-based method to control a vehicle. However, the feedforward-based method cannot ensure the control accuracy of the feedforward quantity, so that the feedforward value may be too large or too small; and the feedforward-based method relies too much on the curvature of the trajectory reference line and on the upstream information and the like (for example, the jitter of the upstream signal may seriously affect the actual control effect), resulting in poor accuracy of the vehicle control.

Disclosure of Invention

The embodiment of the application provides a vehicle control method and device, an electronic device and a vehicle, and improves the accuracy of vehicle control when the vehicle is controlled.

In a first aspect, an embodiment of the present application provides a control method for a vehicle, which may include:

determining M reference points on a preset trajectory line, and respectively acquiring state information corresponding to each reference point in the M reference points; the M reference points comprise a first reference point matched with the current position of the vehicle and M-1 reference points located behind the first reference point based on the future running direction of the vehicle, wherein M is an integer greater than or equal to 2.

Determining a target control sequence according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points; wherein the target control sequence is used to indicate steering wheel angle information of the vehicle.

And controlling the vehicle according to the target control sequence.

Therefore, in the embodiment of the application, when the vehicle control is performed based on the preset trajectory line, the target control sequence is determined according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points, and the vehicle is controlled according to the target control sequence.

In a possible implementation manner, the determining a target control sequence according to the current state information of the vehicle and the state information corresponding to each of the M reference points may include:

based on a vehicle body coordinate system of a vehicle, performing projection processing on the current state information of the vehicle and the state information corresponding to each reference point in the M reference points to obtain error information between the current state information of the vehicle and the state information of the first reference point; and determining the target control sequence according to the error information and the state information corresponding to each reference point in the M reference points.

Therefore, after the target control sequence is determined, the vehicle can be controlled according to the target control sequence, and the average error of the state information in the reference points of the future preset number can be ensured to be minimum due to the fact that the output of the state information of the reference points of the future preset number on the preset trajectory is considered, namely the consideration of the future prediction following estimation is added, so that the accuracy of vehicle control is improved.

In a possible implementation manner, the determining the target control sequence according to the error information and the state information corresponding to each of the M reference points may include:

and inputting the error information and the state information corresponding to each reference point in the M reference points into a model predictive control model to obtain M control sequences, and determining the control sequence corresponding to the first reference point in the M control sequences as the target control sequence, so that the vehicle can be controlled according to the target control sequence. Wherein the M control sequences include a control sequence corresponding to each of the M reference points.

In a possible implementation manner, the determining M reference points on the preset trajectory line may include:

determining a reference point matched with the current position of the vehicle on the preset planning trajectory line as the first reference point according to the current position of the vehicle; determining a reference point which is positioned behind the first reference point and corresponds to a timestamp which is separated by one preset time length from a timestamp corresponding to the first reference point as a second reference point, determining a reference point which corresponds to a timestamp which is separated by two preset time lengths from a timestamp corresponding to the first reference point as a third reference point, and so on, determining a reference point which corresponds to a timestamp which is separated by M-1 preset time lengths from a timestamp corresponding to the first reference point as an Mth reference point so as to obtain M reference points, wherein the average error of the state information in the reference points of the preset number in the future can be ensured to be minimum by taking the output of the state information of the reference points of the preset number in the future on a preset trajectory into consideration of the future prediction following estimation into consideration based on the future running direction of the vehicle, thereby improving the accuracy of vehicle control.

In a possible implementation manner, the respectively obtaining the state information corresponding to each of the M reference points may include:

determining an index corresponding to each reference point in the M reference points according to the timestamp corresponding to each reference point in the M reference points and the mapping relation between the timestamp corresponding to each reference point on the preset trajectory line and the index; and determining the state information corresponding to each reference point in the M reference points according to the index corresponding to each reference point in the M reference points, so as to obtain the state information corresponding to each reference point.

In a possible implementation manner, the determining, according to the index corresponding to each of the M reference points, the state information corresponding to each of the M reference points may include:

determining a mapping relation between the index of each reference point on the preset trajectory and the state information; and determining the state information corresponding to each reference point in the M reference points according to the index corresponding to each reference point in the M reference points and the mapping relation between the index of each reference point on the preset track line and the state information.

In a possible implementation manner, before determining the mapping relationship between the index of each reference point on the preset trajectory and the state information, the method may further include:

under the transverse control, carrying out linear processing on the kinematic model to obtain a linear kinematic model; the kinematic model is obtained by training by taking the center of a rear axle of the vehicle as a control point; inputting the parameter information corresponding to each reference point in the M reference points into the linear kinematics model to obtain the lateral speed and the yaw rate corresponding to each reference point; the parameter information corresponding to the reference point comprises the coordinate position, the speed, the rotation angle, the length of the center of mass of the vehicle and the center of the rear axle of the vehicle and the yaw angle of the reference point; and integrating the lateral speed and the yaw rate corresponding to each reference point to obtain the state information corresponding to each reference point, so that after the state information corresponding to each reference point is obtained, a target control sequence can be determined according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points, and the vehicle is controlled according to the target control sequence.

In a possible implementation manner, before performing linear processing on the kinematic model under the lateral control, the method may further include:

acquiring parameter information corresponding to the center of the rear axle of the vehicle at different moments; the parameter information corresponding to the center of the rear axle of the vehicle at different moments comprises the coordinate position of the center of the rear axle of the vehicle, the parking speed of the vehicle, the corner of a front wheel of the vehicle, the length of the center of mass of the vehicle and the center of the rear axle of the vehicle and the yaw angle of the vehicle; and training the initial kinematics model according to the parameter information corresponding to the vehicle rear axle center at different moments to obtain the kinematics model, so that the lateral speed and the yaw angular velocity corresponding to each reference point can be obtained based on the kinematics model, and the state information corresponding to each reference point can be further obtained according to the lateral speed and the yaw angular velocity corresponding to each reference point, so that the average error of the state information in a preset number of reference points in the future can be ensured to be minimum, and the accuracy of vehicle parking control is improved.

In one possible implementation manner, the current state information of the vehicle includes a current position of the vehicle, a current orientation of the vehicle, and a current speed of the vehicle, and correspondingly, the state information of the reference point includes coordinates, an orientation, and a speed of the reference point.

In one possible implementation, the current state information of the vehicle includes a current lateral position of the vehicle and a current yaw angle of the vehicle, and correspondingly, the state information of the reference point includes a lateral position of the reference point and a yaw angle of the reference point.

In a second aspect, embodiments of the present application further provide a control device for a vehicle, where the control device for a vehicle may include:

the acquisition unit is used for determining M reference points on a preset trajectory and respectively acquiring state information corresponding to each reference point in the M reference points; the M reference points comprise a first reference point matched with the current position of the vehicle and M-1 reference points located behind the first reference point based on the future running direction of the vehicle, wherein M is an integer greater than or equal to 2.

The processing unit is used for determining a target control sequence according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points; wherein the target control sequence is used to indicate steering wheel angle information of the vehicle.

And the control unit is used for controlling the vehicle according to the target control sequence.

In a possible implementation manner, the processing unit is specifically configured to perform projection processing on the current state information of the vehicle and the state information corresponding to each of the M reference points based on a vehicle body coordinate system of the vehicle, so as to obtain error information between the current state information of the vehicle and the state information of the first reference point; and determining the target control sequence according to the error information and the state information corresponding to each reference point in the M reference points.

In a possible implementation manner, the processing unit is specifically configured to input the error information and state information corresponding to each of the M reference points into a model predictive control model to obtain M control sequences, where the M control sequences include a control sequence corresponding to each of the M reference points; and determining the control sequence corresponding to the first reference point in the M control sequences as the target control sequence.

In a possible implementation manner, the obtaining unit is specifically configured to determine, according to a current location of a vehicle, a reference point on the preset planning trajectory line, where the reference point matches the current location of the vehicle, as the first reference point; and determining a reference point which is positioned behind the first reference point and corresponds to a timestamp with a time interval of one preset duration corresponding to the first reference point as a second reference point, determining a reference point which corresponds to a timestamp with a time interval of two preset durations corresponding to the first reference point as a third reference point, and determining a reference point which corresponds to a timestamp with a time interval of M-1 preset durations corresponding to the first reference point as an Mth reference point according to the future running direction of the vehicle by taking the first reference point as a starting point.

In a possible implementation manner, the obtaining unit is specifically configured to determine, according to a timestamp corresponding to each of the M reference points and a mapping relationship between the timestamp corresponding to each of the reference points on the preset trajectory line and an index, an index corresponding to each of the M reference points; and determining the state information corresponding to each reference point in the M reference points according to the index corresponding to each reference point in the M reference points.

In a possible implementation manner, the obtaining unit is specifically configured to determine a mapping relationship between an index of each reference point on the preset trajectory and the state information; and determining the state information corresponding to each reference point in the M reference points according to the index corresponding to each reference point in the M reference points and the mapping relation between the index of each reference point on the preset track line and the state information.

In a possible implementation manner, the obtaining unit is specifically configured to perform linear processing on the kinematics model under lateral control to obtain a linear kinematics model; the kinematic model is obtained by training by taking the center of a rear axle of the vehicle as a control point; inputting the parameter information corresponding to each reference point in the M reference points into the linear kinematics model to obtain the lateral speed and the yaw rate corresponding to each reference point; the parameter information corresponding to the reference point comprises the coordinate position, the speed, the rotation angle, the length of the center of mass of the vehicle and the center of the rear axle of the vehicle and the yaw angle of the reference point; and integrating the lateral speed and the yaw rate corresponding to each reference point to obtain the state information corresponding to each reference point.

In a possible implementation manner, the processing unit is further configured to obtain parameter information corresponding to the vehicle rear axle center at different times; the parameter information corresponding to the center of the rear axle of the vehicle at different moments comprises the coordinate position of the center of the rear axle of the vehicle, the parking speed of the vehicle, the corner of a front wheel of the vehicle, the length of the center of mass of the vehicle and the center of the rear axle of the vehicle and the yaw angle of the vehicle; and training an initial kinematics model according to the corresponding parameter information of the vehicle rear axle center at different moments to obtain the kinematics model.

In a third aspect, embodiments of the present application further provide a vehicle, where the vehicle may include:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of controlling a vehicle as set forth in any one of the possible implementations of the first aspect.

In a fourth aspect, embodiments of the present application further provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method for controlling a vehicle described in any one of the possible implementations of the first aspect.

In a fifth aspect, an embodiment of the present application further provides a vehicle, including: a vehicle body and a control device of a vehicle provided in the vehicle body.

Wherein the control device of the vehicle is the control device of the vehicle described in any one of the possible implementations of the first aspect.

One embodiment in the above application has the following advantages or benefits: when vehicle control is carried out based on the preset track line, a target control sequence is determined according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points, and the vehicle is controlled according to the target control sequence.

Other effects of the above-described alternative will be described below with reference to specific embodiments.

Drawings

The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:

fig. 1 is a scene diagram of a control method of a vehicle in which an embodiment of the present application may be implemented;

FIG. 2 is a schematic flow chart diagram of a control method for a vehicle according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a predetermined trace line provided in an embodiment of the present application;

FIG. 4 is a schematic flow chart diagram of a control method of a vehicle according to a first embodiment of the present application;

FIG. 5 is a schematic flow chart diagram of a control method of a vehicle according to a second embodiment of the present application;

FIG. 6 is a schematic diagram illustrating control of a vehicle during parking according to an embodiment of the present disclosure;

fig. 7 is a schematic configuration diagram of a control apparatus of a vehicle according to a fourth embodiment of the present application;

fig. 8 is a block diagram of an electronic device of a control method of a vehicle according to an embodiment of the present application.

Detailed Description

The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. 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 present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the embodiments of the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. In the description of the text of the present application, the character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

Fig. 1 is a scene diagram of a vehicle control method that can implement an embodiment of the present application, and for example, please refer to fig. 1, the vehicle control method can be applied to an automatic driving scene. During the running process of the vehicle, the track to be followed in a future period of time needs to be considered, and the vehicle is generally subjected to follow control based on a feed-forward method. However, the feedforward-based method cannot ensure the control accuracy of the feedforward quantity, so that the feedforward value may be too large or too small; and the feedforward-based method relies too much on the curvature of the trajectory reference line and on the upstream information, etc., resulting in a low accuracy of the vehicle control.

In order to improve the accuracy of vehicle control, it may be attempted to improve the control accuracy of the feedforward amount and reduce the dependence on the curvature of the trajectory reference line and the upstream information to improve the accuracy of vehicle control when the vehicle is subjected to follow-up control by the feedforward-based method. However, in practical use, the control accuracy of the feedforward amount cannot be ensured, and the dependence on the curvature of the trajectory reference line and the upstream information cannot be reduced, so that the accuracy of the vehicle control still cannot be improved by this attempt.

Based on the above discussion, in order to improve the accuracy of vehicle control, the embodiment of the present application provides a control method for a vehicle, which introduces a multi-point preview idea, adds consideration to future prediction following estimation, and considers the output of state information of a future preset number of reference points on a preset trajectory line to ensure that the average error of the state information in the future preset number of reference points is minimum, thereby improving the accuracy of vehicle control. For example, see FIG. 2. Fig. 2 is a schematic flowchart of a control method of a vehicle according to an embodiment of the present application, where when controlling the vehicle based on a preset trajectory line, S201 may be first performed to determine M reference points on the preset trajectory line, and respectively obtain state information corresponding to each reference point in the M reference points; the M reference points comprise a first reference point matched with the current position of the vehicle and M-1 reference points behind the first reference point based on the future running direction of the vehicle; s202, determining a target control sequence according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points; wherein the target control sequence is used to indicate steering wheel angle information of the vehicle; and executing S203 to control the vehicle according to the target control sequence. Therefore, according to the control method of the vehicle provided by the embodiment of the application, when the vehicle control is performed based on the preset trajectory line, the target control sequence is determined according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points, and the vehicle is controlled according to the target control sequence.

The preset trajectory line can be understood as a running route of the vehicle at this time set before the vehicle runs, and the vehicle needs to follow the preset trajectory line to complete the whole running process. A future predetermined number of reference points on the predetermined trajectory line may be understood as reference points which, according to the future direction of travel of the vehicle, are located after a reference point matching the current position of the vehicle (indicating that the vehicle has currently traveled to the position indicated by the reference point), i.e. to which the vehicle has not currently traveled, and which the vehicle will pass at some point in the future. Taking M reference points as 9 reference points as an example, as shown in fig. 3, fig. 3 is a schematic diagram of a preset trajectory provided in the embodiment of the present application, an arrow of the preset trajectory in fig. 3 indicates a driving direction of a vehicle, a first reference point is a reference point matching a current position of the vehicle, a second reference point is a reference point located after the first reference point on the preset trajectory according to a future driving direction of the vehicle, a third reference point is a reference point located after the second reference point on the preset trajectory according to the future driving direction of the vehicle, a fourth reference point is a reference point located after the third reference point on the preset trajectory according to the future driving direction of the vehicle, and so on, a ninth reference point is a reference point located after an eighth reference point on the preset trajectory according to the future driving direction of the vehicle, thereby determining 9 reference points on the preset trajectory. It should be understood that the embodiment of the present application is only described by taking M reference points as 9 reference points, but does not represent that the embodiment of the present application is limited thereto.

It is understood that, in the embodiment of the present application, when determining M reference points on the preset trajectory line, the more the number of the selected reference points is, that is, the greater the value of M is, the higher the accuracy of the target control sequence for controlling the vehicle obtained according to the state information of the M reference points is, so that when the vehicle is controlled based on the target control sequence with higher accuracy, the higher the accuracy of the vehicle control is.

Generally, the operation process of the vehicle may include at least two scenarios. In one scenario, the running process of the vehicle is a running process of the vehicle; in another scenario, the operation process of the vehicle is a parking process of the vehicle. It should be noted that, in different scenarios, the current state information of the vehicle and the state information of the reference point include different contents. It is understood that, when the operation process of the vehicle is a driving process of the vehicle, the current state information of the vehicle includes a current position of the vehicle, a current orientation of the vehicle, and a current speed of the vehicle, and correspondingly, the state information of the reference point includes coordinates, an orientation, and a speed of the reference point. For example, the state information of the reference point may further include a heading angle of the reference point, a heading angle change rate, and the like. When the running process of the vehicle is a parking process of the vehicle, the current state information of the vehicle comprises the current lateral position of the vehicle and the current yaw angle of the vehicle, and correspondingly, the state information of the reference point comprises the lateral position of the reference point and the yaw angle of the reference point.

Next, the control method of the vehicle in the above two scenarios will be described in detail by specific first and second embodiments, respectively. It is to be understood that the following detailed description may be combined with other embodiments, and that the same or similar concepts or processes may not be repeated in some embodiments.

Example one

In one scenario, when the operation process of the vehicle is a driving process of the vehicle, for example, please refer to fig. 4, fig. 4 is a flowchart of a control method of the vehicle according to the first embodiment of the present application, the control method of the vehicle may be executed by software and/or a hardware device, for example, the hardware device may be a control device of the vehicle, and the control method device of the vehicle may be disposed in the vehicle. The control method of the vehicle may include:

s401, determining M reference points on a preset track line, and respectively acquiring state information corresponding to each reference point in the M reference points.

The M reference points comprise a first reference point matched with the current position of the vehicle, and M-1 reference points located behind the first reference point based on the future driving direction of the vehicle, the state information of the reference points comprises the coordinates, the direction and the speed of the reference points, and M is an integer greater than or equal to 2.

It should be noted that, in the embodiment of the present application, since the vehicle center point position can better describe the current position of the vehicle, when the current position of the vehicle is at the first reference point matched with the current position of the vehicle on the preset trajectory, the current position of the vehicle can be understood as the vehicle center point position, and of course, other position points of the vehicle are also feasible. Here, the embodiment of the present application is only described by taking the current position of the vehicle as the center position of the vehicle as an example, but the embodiment of the present application is not limited thereto.

It can be understood that, in the embodiment of the present application, when the vehicle control is performed based on the preset trajectory line, it is because the output of the state information of the future preset number of reference points on the preset trajectory line is considered to ensure that the average error of the state information within the future preset number of reference points is minimized, thereby improving the accuracy of the vehicle control. Therefore, a future preset number of reference points on the preset trajectory and the state information of each reference point need to be determined. Taking the preset number of M as an example, M reference points may be determined on the preset trajectory, and the state information corresponding to each reference point in the M reference points may be obtained respectively.

For example, when M reference points are determined on the preset trajectory line, M-1 reference points located after the first reference point may be sequentially determined on the preset trajectory line based on the future driving direction of the vehicle according to the timestamp and the preset duration corresponding to the first reference point, and the specific determination manner may be as described in the following third embodiment. After the M reference points are determined on the preset trajectory line, the state information corresponding to each reference point in the M reference points is respectively obtained, for example, when the state information corresponding to each reference point in the M reference points is respectively obtained, because the mapping relationship between the timestamp corresponding to each reference point on the preset trajectory line and the index is pre-stored, the index corresponding to each reference point in the M reference points can be determined according to the timestamp corresponding to each reference point in the M reference points and the mapping relationship between the timestamp corresponding to each reference point on the preset trajectory line and the index; and the mapping relation between the index of each reference point on the preset track line and the state information is prestored, so that the state information corresponding to each reference point in the M reference points can be determined according to the index corresponding to each reference point in the M reference points and the mapping relation between the index of each reference point on the preset track line and the state information, and the coordinate, the orientation and the speed corresponding to each reference point in the M reference points can be obtained.

With reference to fig. 3, taking the determination of 9 reference points on the preset trajectory line as an example, when determining the 9 reference points, a timestamp and a preset duration corresponding to a first reference point in the 9 reference points may be determined first, and a second reference point, a third reference point, a fourth reference point, a fifth reference point, a sixth reference point, a seventh reference point, an eighth reference point, and a ninth reference point located after the first reference point are sequentially determined on the preset trajectory line based on the future driving direction of the vehicle; after the 9 reference points are determined, the state information corresponding to each of the 9 reference points, which includes the coordinates, the orientation, and the speed of the reference point, may be obtained.

After determining M reference points on the preset trajectory and respectively obtaining the state information corresponding to each reference point of the M reference points, the following S402 may be performed:

s402, based on a vehicle body coordinate system of the vehicle, performing projection processing on the current state information of the vehicle and the state information corresponding to each reference point in the M reference points to obtain error information between the current state information of the vehicle and the state information of the first reference point.

The vehicle body coordinate system is a world coordinate system, the current vehicle body position is taken as an origin, and the current vehicle body orientation is used for establishing the vehicle body coordinate system, the vehicle body coordinate system conforms to the Society of Automotive Engineers (SAE) standard, and the current and future states of the vehicle center and the reference point are projected on the vehicle body coordinate system.

After the coordinates, the direction, and the speed corresponding to each of the M reference points are obtained in S401, the current coordinates, the direction, and the speed of the vehicle and the coordinates, the direction, and the speed corresponding to each of the M reference points may be projected based on the vehicle body coordinate system of the vehicle, so as to obtain error information between the current state information of the vehicle and the state information of the first reference point. It can be understood that the current state information of the vehicle includes the position, orientation and speed of the vehicle; and the state information of each reference point also comprises the coordinates, the direction and the speed of the reference point, so that the current state information of the vehicle and the state information of each reference point are subjected to projection processing based on a vehicle body coordinate system of the vehicle, and the obtained error information between the current state information of the vehicle and the state information of the first reference point also comprises errors in three dimensions of the position, the direction and the speed.

With reference to fig. 3, taking the determination of 9 reference points on the preset trajectory as an example, after the coordinates, the orientation, and the speed corresponding to each of the 9 reference points are respectively obtained, the current coordinates, the orientation, and the speed of the vehicle and the coordinates, the orientation, and the speed corresponding to each of the 9 reference points can be all subjected to projection processing, so that error information between the current state information of the vehicle and the state information of the first reference point can be obtained.

After obtaining the error information between the current state information of the vehicle and the state information of the first reference point, i.e., M error information, the following S403 may be performed:

s403, inputting the error information and the state information corresponding to each reference point in the M reference points into a model predictive control model to obtain M control sequences; and selecting a control sequence corresponding to the first reference point from the M control sequences, and determining the control sequence corresponding to the first reference point as a target control sequence.

The target control sequence is used for indicating the steering wheel angle information of the vehicle, and the current state information of the vehicle comprises the current position of the vehicle, the current orientation of the vehicle and the current speed of the vehicle.

After obtaining the error information between the current state information of the vehicle and the state information of the first reference point, the error information and the state information corresponding to each of the M reference points may be input to the model predictive control model to obtain M control sequences, where the M control sequences include a control sequence corresponding to each of the M reference points. After obtaining the control sequence corresponding to each of the M reference points, since the first reference point is a reference point matched with the current position of the vehicle, the control sequence corresponding to the first reference point may be selected from the M control sequences, and the control sequence corresponding to the first reference point is determined as a target control sequence, so as to control the vehicle to run through the target control sequence.

And S404, controlling the running of the vehicle according to the target control sequence.

After the target control sequence is determined by the above-described S403, the vehicle can be subjected to running control according to the target control sequence determined for indicating the steering wheel angle information of the vehicle. Different from the prior art, in the embodiment of the application, when the vehicle is controlled to run, because the output of the state information of the reference points with the future preset number on the preset trajectory is considered, namely, the consideration of the future prediction following estimation is added, the average error of the state information in the reference points with the future preset number can be ensured to be minimum, the stability and the continuity of the system are improved, the phenomena of overshoot and the like are reduced, the phenomena of drawing dragon, hurrying the direction and the like are avoided, especially the transverse following errors under the condition of large curvature change of S-turn and the like, including the transverse position error and the course angle error, the body feeling of turning and lane changing is improved, and the accuracy of the vehicle running control is effectively improved.

It should be noted that, when the vehicle is driven to another position at the next time, that is, when the vehicle driving process is controlled at the next time, the above steps S401 to S404 need to be repeated, that is, new control sequences corresponding to the reference points of the future preset number are obtained again; and selecting a new control sequence corresponding to the first reference point from the control sequences corresponding to the new future preset number of reference points as a control basis to control the vehicle to run, wherein the control method is similar to the control method described in the above S401-S404, and reference may be made to the related description in the above S401-S404, and details are not repeated in this application.

Therefore, according to the control method of the vehicle provided by the embodiment of the application, when the running control is performed based on the preset track line, the target control sequence is determined according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points, and the vehicle is controlled according to the target control sequence.

It can be seen that the above embodiment describes in detail how to implement the control method of the vehicle when the operation process of the vehicle is the driving process of the vehicle in one scenario. In another scenario, when the operation process of the vehicle is a parking process of the vehicle, how to implement the technical solution of the control method of the vehicle will be described in detail through the following second embodiment.

Example two

Fig. 5 is a flowchart of a control method of a vehicle according to a second embodiment of the present application, where the control method of the vehicle may also be executed by software and/or hardware devices, for example, the hardware devices may be control devices of the vehicle, and the control method devices of the vehicle may be provided in the vehicle. The control method of the vehicle may include:

s501, determining M reference points on a preset track line, and respectively acquiring state information corresponding to each reference point in the M reference points.

The vehicle parking method comprises the following steps that M reference points comprise a first reference point matched with the current position of a vehicle and M-1 reference points located behind the first reference point based on the future parking direction of the vehicle, state information of the reference points comprises the lateral position and the yaw angle of the reference points, and M is an integer greater than or equal to 2.

It should be noted that, in the embodiment of the present application, since the stability of the center of the rear axle of the vehicle is better, when the current position of the vehicle on the preset trajectory line is at the first reference point matched with the current position of the vehicle, the current position of the vehicle may be understood as the position of the center of the rear axle of the vehicle, and of course, other positions of the vehicle are also possible if the stability is not considered. Here, the embodiment of the present application is described by taking the current position of the vehicle as an example of a position of a center of a rear axle of the vehicle, but the embodiment of the present application is not limited thereto.

For example, when M reference points are determined on the preset trajectory line, M-1 reference points located after the first reference point may be sequentially determined on the preset trajectory line based on the future parking direction of the vehicle according to the timestamp and the preset duration corresponding to the first reference point, and the specific determination manner may be as described in the following third embodiment. After the M reference points are determined on the preset trajectory line, the state information corresponding to each reference point in the M reference points is respectively obtained, for example, when the state information corresponding to each reference point in the M reference points is respectively obtained, because the mapping relationship between the timestamp corresponding to each reference point on the preset trajectory line and the index is pre-stored, the index corresponding to each reference point in the M reference points can be determined according to the timestamp corresponding to each reference point in the M reference points and the mapping relationship between the timestamp corresponding to each reference point on the preset trajectory line and the index; and because the mapping relation between the index of each reference point on the preset track line and the state information is stored in advance, the state information corresponding to each reference point in the M reference points can be determined according to the index corresponding to each reference point in the M reference points and the mapping relation between the index of each reference point on the preset track line and the state information, and the state information of each reference point in the M reference points can be acquired.

It is understood that before determining the state information corresponding to each reference point on the M reference points according to the index corresponding to each reference point in the M reference points and the mapping relationship between the index of each reference point on the preset trajectory line and the state information, the mapping relationship between the index of each reference point on the preset trajectory line and the state information needs to be established. Before establishing a mapping relationship between the index and the state of each reference point on the planned trajectory line, the state of each reference point needs to be acquired first.

For example, when the state of each reference point is obtained, the state of each reference point is obtained based on a kinematic model, and different from the prior art, in the embodiment of the present application, the stability based on the rear axle center is better, so that when the kinematic model is established, parameter information corresponding to the rear axle center of the vehicle at different times can be obtained first; the parameter information corresponding to the center of the rear axle of the vehicle at different moments comprises the coordinate position of the center of the rear axle of the vehicle, the parking speed of the vehicle, the corner of a front wheel of the vehicle, the length of the center of mass of the vehicle and the center of the rear axle of the vehicle and the yaw angle of the vehicle; and training the initial kinematics model according to the corresponding parameter information of the vehicle rear axle center at different moments to obtain a final kinematics model. For example, the initial kinematic model may be a deep learning model. Under the normal condition, only the transverse control is considered in the vehicle parking process, so that the kinematic model can be subjected to linear processing under the transverse control to obtain a linear kinematic model; inputting the parameter information corresponding to each reference point in the M reference points (the parameter information corresponding to the reference points comprises the coordinate position, the speed and the corner of the reference point, the length of the center of mass of the vehicle and the center of a rear axle of the vehicle and the yaw angle) into the linear kinematics model to obtain the lateral speed and the yaw angle speed corresponding to each reference point; and then integrating the lateral speed and the yaw rate corresponding to each reference point respectively to obtain the lateral position and the yaw angle corresponding to each reference point on the planned trajectory.

For example, please refer to fig. 6, where fig. 6 is a schematic diagram of a vehicle control during parking according to an embodiment of the present disclosure. Where the coordinates (x, y) expressed as the position of the point can be understood as the vehicle centroid position, the center point of the upper right rectangle shown in fig. 6 can be understood as the coordinate position of the vehicle rear axle center, delta can be understood as the vehicle front wheel corner,

based on these parameters, which may be understood as the vehicle yaw angle, ω may be understood as the vehicle yaw rate, and v may be understood as the vehicle parking rate, a final kinematic model may be trained, which may be represented by the following equation 1:

wherein L is the length of the center of mass of the vehicle and the center of the rear axle of the vehicle.

After obtaining the kinematic model shown in equation 1, the kinematic model may be subjected to a linear processing under a lateral control to obtain a linear kinematic model, which may be represented by equation 2 below:

also referring to fig. 3, taking the determination of 9 reference points on the preset trajectory line as an example, when determining the 9 reference points, a timestamp and a preset duration corresponding to a first reference point in the 9 reference points may be determined first, and a second reference point, a third reference point, a fourth reference point, a fifth reference point, a sixth reference point, a seventh reference point, an eighth reference point, and a ninth reference point located after the first reference point are sequentially determined on the preset trajectory line based on the future parking direction of the vehicle; after the 9 reference points are determined, the lateral position and the yaw angle corresponding to each of the 9 reference points can be respectively obtained.

After determining M reference points on the preset trajectory and respectively obtaining the state information corresponding to each reference point of the M reference points, the following step S502 may be performed:

s502, based on a vehicle body coordinate system of the vehicle, performing projection processing on the current state information of the vehicle and the state information corresponding to each reference point in the M reference points to obtain error information between the current state information of the vehicle and the state information of the first reference point.

After the lateral position and the yaw angle corresponding to each of the M reference points are obtained through the above S501, the current lateral position and the current yaw angle of the vehicle and the lateral position and the yaw angle corresponding to each of the M reference points may be projected based on the vehicle body coordinate system of the vehicle, so as to obtain error information between the current state information of the vehicle and the state information of the first reference point. It can be understood that the current state information of the vehicle includes the position, orientation and speed of the vehicle; and the state information of each reference point also comprises the coordinates, the direction and the speed of the reference point, so that the current state information of the vehicle and the state information of each reference point are subjected to projection processing based on a vehicle body coordinate system of the vehicle, and the obtained error information between the current state information of the vehicle and the state information of the first reference point also comprises errors in three dimensions of the position, the direction and the speed.

With reference to fig. 3, taking the determination of 9 reference points on the preset trajectory as an example, after the lateral position and the yaw angle corresponding to each of the 9 reference points are respectively obtained, the current lateral position and the current yaw angle of the vehicle and the lateral position and the yaw angle corresponding to each of the 9 reference points can be both subjected to projection processing, so that error information between the current state information of the vehicle and the state information of the first reference point can be obtained.

After obtaining the error information between the current state information of the vehicle and the state information of the first reference point, i.e. M error information, the following S503 may be performed:

s503, inputting the error information and the state information corresponding to each reference point in the M reference points into a model predictive control model to obtain M control sequences; and selecting a control sequence corresponding to the first reference point from the M control sequences, and determining the control sequence corresponding to the first reference point as a target control sequence.

The target control sequence is used for indicating steering wheel angle information of the vehicle, and the current state information of the vehicle comprises the current lateral position of the vehicle and the current yaw angle of the vehicle.

After obtaining the error information between the current state information of the vehicle and the state information of the first reference point, the error information and the state information corresponding to each of the M reference points may be input to the model predictive control model to obtain M control sequences, where the M control sequences include a control sequence corresponding to each of the M reference points. After obtaining the control sequence corresponding to each of the M reference points, since the first reference point is a reference point matched with the current position of the vehicle, the control sequence corresponding to the first reference point may be selected from the M control sequences, and the control sequence corresponding to the first reference point is determined as a target control sequence, so as to perform parking control on the vehicle through the target control sequence.

And S504, parking control is carried out on the vehicle according to the target control sequence.

After the target control sequence is determined by the above-described S403, the parking control of the vehicle can be performed according to the target control sequence determined for indicating the steering wheel angle information of the vehicle. Different from the prior art, in the embodiment of the application, when the vehicle is controlled to park, because the output of the state information of the reference points with the future preset number on the preset trajectory line is considered, namely, the consideration of the future prediction following estimation is added, the average error of the state information in the reference points with the future preset number can be ensured to be minimum, the stability and the continuity of the system are improved, the vehicle can be smoothly and stably parked in a garage without pressing a line, and the direction is parallel to the garage line after the vehicle is parked in the garage, so that the accuracy of controlling the vehicle to park is effectively improved.

It should be noted that, when the vehicle backs up to another position at the next time, that is, when the vehicle parking process is controlled at the next time, the steps S501 to S504 need to be repeated, that is, new control sequences corresponding to the reference points with the future preset number are obtained again; and selecting a new control sequence corresponding to the first reference point from the control sequences corresponding to the new future preset number of reference points as a control basis to control the vehicle to park, wherein the control method is similar to the control method described in the above S501-S504, and reference may be made to the related description in the above S501-S504, and details are not repeated in this application.

Therefore, when parking control is performed based on the preset trajectory line, the target control sequence is determined according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points, and the vehicle is controlled according to the target control sequence.

The foregoing embodiment describes in detail how, in the embodiment of the present application, when the vehicle running process is the vehicle running process, a target control sequence is calculated based on M reference points determined on a preset trajectory, and the vehicle is controlled according to the target control sequence. The second embodiment describes in detail how, in the embodiment of the present application, when the vehicle operation process is a vehicle parking process, a target control sequence is calculated based on M reference points determined on a preset trajectory line, and a vehicle is controlled according to the target control sequence. Based on the second embodiment and the third embodiment, in order to more clearly describe how to determine M reference points on the preset trajectory line in the above embodiments, how to determine M reference points on the preset trajectory line in the embodiment of the present application will be described in detail by the third embodiment below.

EXAMPLE III

For example, when determining M reference points on the preset trajectory line, at least two possible implementations may be included:

in a possible implementation manner, a reference point matched with the current position of the vehicle can be found on a track line according to the current position of the vehicle, and the reference point matched with the current position of the vehicle on a preset planning track line is determined as a first reference point, so that the first reference point in the M reference points is obtained; then, with the first reference point as a starting point, determining a reference point which is determined to be located behind the first reference point on a preset track line and corresponds to a timestamp which is separated by a preset time length and corresponds to the first reference point as a second reference point, so as to obtain a second reference point of the M reference points; determining a reference point corresponding to a timestamp corresponding to the first reference point, wherein the timestamp is separated by two preset durations, as a third reference point, so as to obtain a third reference point of the M reference points; determining a reference point corresponding to a timestamp corresponding to the first reference point, wherein the timestamp interval is three preset durations, as a fourth reference point, so as to obtain a fourth reference point of the M reference points; and by analogy, determining the reference point corresponding to the timestamp with the timestamp interval of M-1 preset duration corresponding to the first reference point as the Mth reference point, thereby obtaining the Mth reference point, and determining the M reference points on the preset trajectory line in sequence.

In this possible implementation manner, it is easy to see that, when determining the ith reference point in the M reference points, the ith time stamp is determined according to the time stamp corresponding to the first reference point and the preset time duration extending backwards, and the reference point corresponding to the ith time stamp is determined as the ith reference point. For example, the timestamp corresponding to the first reference point can be represented by relative _ time [0], the ith timestamp in the M reference points can be represented by relative _ time [ i ], the ith timestamp relative _ time [ i ] - [ relative _ time [0] + (i-1) T _ s, wherein T _ s represents the interval duration, thereby calculating the ith timestamp relative _ time [ i ], because the time stamp corresponding to each reference point and the index of the reference point are in one-to-one correspondence, the obtained time stamp (relative time) can be interpolated, and determining the index of the reference point corresponding to the ith timestamp relative _ time [ i ] according to the mapping relation between the ith timestamp relative _ time [ i ] and the timestamp corresponding to the reference point and the index of the reference point, and determining a reference point corresponding to the index as an ith reference point, thereby sequentially determining M reference points on the preset trajectory line.

In another possible implementation manner, a reference point matched with the current position of the vehicle can be found on the trajectory line according to the current position of the vehicle, and the reference point matched with the current position of the vehicle on the preset planning trajectory line is determined as a first reference point, so that the first reference point in the M reference points is obtained; then, with the first reference point as a starting point, determining a reference point which is determined to be located behind the first reference point on a preset track line and corresponds to a timestamp which corresponds to the first reference point and is spaced by a preset time length as a second reference point, thereby obtaining a second reference point of the M reference points; determining a reference point which is determined to be positioned behind the second reference point on the preset track line and corresponds to a timestamp which corresponds to the second reference point and is spaced by a preset time length as a third reference point by taking the second reference point as a starting point, thereby obtaining a second reference point of the M reference points; and determining a reference point which is determined to be positioned behind the third reference point on the preset track line and corresponds to the timestamp with the timestamp interval preset time length corresponding to the third reference point as a fourth reference point by taking the third reference point as a starting point, and determining a reference point which is determined to be positioned behind the M-1 reference point on the preset track line and corresponds to the timestamp with the timestamp interval preset time length corresponding to the M-1 reference point as an Mth reference point by taking the M-1 reference point as a starting point so as to obtain the Mth reference point, thereby sequentially determining the M reference points on the preset track line.

For convenience of calculation, in general, the first possible implementation is adopted to determine M reference points on the preset trajectory line, and of course, the second possible implementation may also be adopted to determine M reference points on the preset trajectory line, and the calculation results are consistent. It should be understood that, when determining the M reference points on the preset trajectory line, the above two possible implementations are only used as examples for illustration, but the embodiments of the present application are not limited thereto. After the M reference points are determined on the preset track line, the state information corresponding to each reference point in the M reference points can be respectively obtained. It is understood that the state information herein includes the coordinates, orientation, and speed of the reference point; of course, the lateral position of the reference point and the yaw angle of the reference point may also be included, specifically related to the operation scene of the vehicle, and the embodiment of the present application is not further limited to the content included in the status information.

After M reference points are determined on the preset track line, a target control sequence can be determined according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points, and the vehicle is controlled according to the target control sequence.

Example four

Fig. 7 is a schematic structural diagram of a control device 70 of a vehicle according to a fourth embodiment of the present application, and for example, please refer to fig. 7, the control device 70 of the vehicle may include:

an obtaining module 701, configured to determine M reference points on a preset trajectory, and obtain state information corresponding to each reference point in the M reference points respectively; the M reference points comprise a first reference point matched with the current position of the vehicle, and M-1 reference points located behind the first reference point based on the future running direction of the vehicle, wherein M is an integer greater than or equal to 2.

A processing module 702, configured to determine a target control sequence according to current state information of the vehicle and state information corresponding to each of the M reference points; wherein the target control sequence is used to indicate steering wheel angle information of the vehicle.

And the control module 703 is configured to control the vehicle according to the target control sequence.

Optionally, the processing module 702 is specifically configured to perform projection processing on the current state information of the vehicle and the state information corresponding to each of the M reference points based on a vehicle body coordinate system of the vehicle, so as to obtain error information between the current state information of the vehicle and the state information of the first reference point; and determining a target control sequence according to the error information and the state information corresponding to each reference point in the M reference points.

Optionally, the processing module 702 is specifically configured to input the error information and the state information corresponding to each of the M reference points into the model predictive control model to obtain M control sequences, where the M control sequences include a control sequence corresponding to each of the M reference points; and determining the control sequence corresponding to the first reference point in the M control sequences as a target control sequence.

Optionally, the obtaining module 701 is specifically configured to determine, according to the current position of the vehicle, a reference point on the preset planning trajectory line, which is matched with the current position of the vehicle, as a first reference point; and determining a reference point which is positioned behind the first reference point and corresponds to a timestamp with a time interval of one preset duration corresponding to the first reference point as a second reference point, determining a reference point which corresponds to a timestamp with a time interval of two preset durations corresponding to the first reference point as a third reference point, and determining a reference point which corresponds to a timestamp with a time interval of M-1 preset durations corresponding to the first reference point as an Mth reference point by analogy based on the future running direction of the vehicle.

Optionally, the obtaining module 701 is specifically configured to determine an index corresponding to each reference point of the M reference points according to a timestamp corresponding to each reference point of the M reference points and a mapping relationship between the timestamp corresponding to each reference point on the preset trajectory line and the index; and determining the state information corresponding to each reference point in the M reference points according to the index corresponding to each reference point in the M reference points.

Optionally, the obtaining module 701 is specifically configured to determine a mapping relationship between an index of each reference point on the preset trajectory and the state information; and determining the state information corresponding to each reference point in the M reference points according to the index corresponding to each reference point in the M reference points and the mapping relation between the index of each reference point on the preset track line and the state information.

Optionally, the obtaining module 701 is specifically configured to perform linear processing on the kinematics model under lateral control to obtain a linear kinematics model; the kinematic model is obtained by training by taking the center of a rear axle of the vehicle as a control point; inputting the parameter information corresponding to each reference point in the M reference points into the linear kinematics model to obtain the lateral speed and the yaw rate corresponding to each reference point; the parameter information corresponding to the reference point comprises the coordinate position, the speed, the rotation angle, the length of the center of mass of the vehicle and the center of the rear axle of the vehicle and the yaw angle of the reference point; and integrating the lateral speed and the yaw rate corresponding to each reference point to obtain the state information corresponding to each reference point.

Optionally, the processing module 702 is further configured to obtain parameter information corresponding to the center of the rear axle of the vehicle at different times; the parameter information corresponding to the center of the rear axle of the vehicle at different moments comprises the coordinate position of the center of the rear axle of the vehicle, the parking speed of the vehicle, the corner of a front wheel of the vehicle, the length of the center of mass of the vehicle and the center of the rear axle of the vehicle and the yaw angle of the vehicle; and training the initial kinematics model according to the corresponding parameter information of the vehicle rear axle center at different moments to obtain the kinematics model.

Optionally, the current state information of the vehicle includes a current position of the vehicle, a current orientation of the vehicle, and a current speed of the vehicle, and correspondingly, the state information of the reference point includes coordinates, an orientation, and a speed of the reference point.

Optionally, the current state information of the vehicle includes a current lateral position of the vehicle and a current yaw angle of the vehicle, and correspondingly, the state information of the reference point includes a lateral position of the reference point and a yaw angle of the reference point.

The control device 70 of the vehicle provided in the embodiment of the present application can execute the technical solution of the control method of the vehicle in any embodiment, and the implementation principle and the beneficial effects thereof are similar to those of the control method of the vehicle, and reference may be made to the implementation principle and the beneficial effects of the control method of the vehicle, which are not described herein again.

The embodiment of the present application further provides a vehicle, and the vehicle may include: a vehicle body and a control device of a vehicle provided in the vehicle body; wherein the control device of the vehicle is the control device of the vehicle described in fig. 7; correspondingly, the vehicle provided in the embodiment of the present application may execute the technical solution of the control method of the vehicle in any embodiment, and the implementation principle and the beneficial effect of the vehicle are similar to those of the control method of the vehicle, which can be referred to and are not described herein again.

According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.

As shown in fig. 8, fig. 8 is a block diagram of an electronic device of a control method of a vehicle according to an embodiment of the present application. 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 present application that are described and/or claimed herein.

As shown in fig. 8, the electronic apparatus includes: one or more processors 801, memory 802, and interfaces for connecting the various components, including a high speed interface and a low speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). Fig. 8 illustrates an example of a processor 801.

The memory 802 is a non-transitory computer readable storage medium as provided herein. Wherein the memory stores instructions executable by at least one processor to cause the at least one processor to perform the method of controlling a vehicle provided herein. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to execute the control method of a vehicle provided by the present application.

The memory 802, as a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the control method of the vehicle in the embodiment of the present application (for example, the obtaining module 701, the processing module 702, and the control module 703 shown in fig. 7). The processor 801 executes various functional applications of the server and data processing by running non-transitory software programs, instructions, and modules stored in the memory 802, that is, implements the control method of the vehicle in the above-described method embodiment.

The memory 802 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device of the control method of the vehicle, and the like. Further, the memory 802 may include high speed random access memory and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 802 optionally includes memory located remotely from the processor 801, which may be connected to the vehicle's control method electronics over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device of the control method of the vehicle may further include: an input device 803 and an output device 804. The processor 801, the memory 802, the input device 803, and the output device 804 may be connected by a bus or other means, and are exemplified by a bus in fig. 8.

The input device 803 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic equipment of the control method of the vehicle, such as an input device of a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or the like. The output devices 804 may include a display device, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.

Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), 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.

These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

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 may 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.

According to the technical scheme of the embodiment of the application, when vehicle control is carried out based on the preset track line, M reference points are firstly determined on the preset track line, the state information corresponding to each reference point in the M reference points is respectively obtained, the target control sequence is determined according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points, and then the vehicle is controlled according to the target control sequence.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.

The above-described embodiments should not be construed as limiting the scope of the present application. 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 application shall be included in the protection scope of the present application.

Claims

1. A control method of a vehicle, characterized by comprising:

determining M reference points on a preset trajectory line, and respectively acquiring state information corresponding to each reference point in the M reference points; the M reference points comprise a first reference point matched with the current position of the vehicle and M-1 reference points behind the first reference point based on the future running direction of the vehicle, wherein M is an integer greater than or equal to 2;

determining a target control sequence according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points; wherein the target control sequence is indicative of steering wheel angle information of a vehicle;

and controlling the vehicle according to the target control sequence.

2. The method of claim 1, wherein determining a target control sequence based on current state information of the vehicle and corresponding state information for each of the M reference points comprises:

based on a vehicle body coordinate system of a vehicle, performing projection processing on the current state information of the vehicle and the state information corresponding to each reference point in the M reference points to obtain error information between the current state information of the vehicle and the state information of the first reference point;

and determining the target control sequence according to the error information and the state information corresponding to each reference point in the M reference points.

3. The method of claim 2, wherein determining the target control sequence according to the error information and the state information corresponding to each of the M reference points comprises:

inputting the error information and the state information corresponding to each reference point in the M reference points into a model predictive control model to obtain M control sequences, wherein the M control sequences include a control sequence corresponding to each reference point in the M reference points;

and determining the control sequence corresponding to the first reference point in the M control sequences as the target control sequence.

4. The method of claim 1, wherein determining M reference points on the preset trajectory line comprises:

determining a reference point matched with the current position of the vehicle on the preset planning trajectory line as the first reference point according to the current position of the vehicle;

and determining a reference point which is positioned behind the first reference point and corresponds to a timestamp with a time interval of one preset duration corresponding to the first reference point as a second reference point, determining a reference point which corresponds to a timestamp with a time interval of two preset durations corresponding to the first reference point as a third reference point, and determining a reference point which corresponds to a timestamp with a time interval of M-1 preset durations corresponding to the first reference point as an Mth reference point according to the future running direction of the vehicle by taking the first reference point as a starting point.

5. The method according to claim 1, wherein the respectively obtaining the state information corresponding to each of the M reference points comprises:

determining an index corresponding to each reference point in the M reference points according to the timestamp corresponding to each reference point in the M reference points and the mapping relation between the timestamp corresponding to each reference point on the preset trajectory line and the index;

and determining the state information corresponding to each reference point in the M reference points according to the index corresponding to each reference point in the M reference points.

6. The method according to claim 5, wherein the determining the state information corresponding to each of the M reference points according to the index corresponding to each of the M reference points comprises:

determining a mapping relation between the index of each reference point on the preset trajectory and the state information;

and determining the state information corresponding to each reference point in the M reference points according to the index corresponding to each reference point in the M reference points and the mapping relation between the index of each reference point on the preset track line and the state information.

7. The method according to claim 6, wherein before determining the mapping relationship between the index of each reference point on the preset trajectory line and the state information, the method further comprises:

under the transverse control, carrying out linear processing on the kinematic model to obtain a linear kinematic model; the kinematic model is obtained by training by taking the center of a rear axle of the vehicle as a control point;

inputting the parameter information corresponding to each reference point in the M reference points into the linear kinematics model to obtain the lateral speed and the yaw rate corresponding to each reference point; the parameter information corresponding to the reference point comprises the coordinate position, the speed, the rotation angle, the length of the center of mass of the vehicle and the center of the rear axle of the vehicle and the yaw angle of the reference point;

and integrating the lateral speed and the yaw rate corresponding to each reference point to obtain the state information corresponding to each reference point.

8. The method of claim 7, wherein prior to linearly processing the kinematic model under the lateral control, further comprising:

acquiring parameter information corresponding to the center of the rear axle of the vehicle at different moments; the parameter information corresponding to the center of the rear axle of the vehicle at different moments comprises the coordinate position of the center of the rear axle of the vehicle, the parking speed of the vehicle, the corner of a front wheel of the vehicle, the length of the center of mass of the vehicle and the center of the rear axle of the vehicle and the yaw angle of the vehicle;

and training an initial kinematics model according to the parameter information corresponding to the vehicle rear axle center at different moments to obtain the kinematics model.

9. The method according to any one of claims 1 to 6,

the current state information of the vehicle comprises the current position of the vehicle, the current orientation of the vehicle and the current speed of the vehicle, and correspondingly, the state information of the reference point comprises the coordinates, the orientation and the speed of the reference point.

10. The method according to any one of claims 1 to 8,

the current state information of the vehicle comprises the current lateral position of the vehicle and the current yaw angle of the vehicle, and correspondingly, the state information of the reference point comprises the lateral position of the reference point and the yaw angle of the reference point.

11. A control apparatus of a vehicle, characterized by comprising:

the acquisition unit is used for determining M reference points on a preset trajectory and respectively acquiring state information corresponding to each reference point in the M reference points; the M reference points comprise a first reference point matched with the current position of the vehicle and M-1 reference points behind the first reference point based on the future running direction of the vehicle, wherein M is an integer greater than or equal to 2;

the processing unit is used for determining a target control sequence according to the current state information of the vehicle and the state information corresponding to each reference point in the M reference points; wherein the target control sequence is indicative of steering wheel angle information of a vehicle;

12. The apparatus of claim 11,

the processing unit is specifically configured to perform projection processing on the current state information of the vehicle and the state information corresponding to each of the M reference points based on a vehicle body coordinate system of the vehicle, so as to obtain error information between the current state information of the vehicle and the state information of the first reference point; and determining the target control sequence according to the error information and the state information corresponding to each reference point in the M reference points.

13. The apparatus of claim 12,

the processing unit is specifically configured to input the error information and state information corresponding to each of the M reference points to a model predictive control model to obtain M control sequences, where the M control sequences include a control sequence corresponding to each of the M reference points; and determining the control sequence corresponding to the first reference point in the M control sequences as the target control sequence.

14. The apparatus of claim 11,

the obtaining unit is specifically configured to determine, according to a current location of a vehicle, a reference point on the preset planning trajectory line, which is matched with the current location of the vehicle, as the first reference point; and determining a reference point which is positioned behind the first reference point and corresponds to a timestamp with a time interval of one preset duration corresponding to the first reference point as a second reference point, determining a reference point which corresponds to a timestamp with a time interval of two preset durations corresponding to the first reference point as a third reference point, and determining a reference point which corresponds to a timestamp with a time interval of M-1 preset durations corresponding to the first reference point as an Mth reference point according to the future running direction of the vehicle by taking the first reference point as a starting point.

15. The apparatus of claim 11,

the acquiring unit is specifically configured to determine an index corresponding to each reference point in the M reference points according to a timestamp corresponding to each reference point in the M reference points and a mapping relationship between a timestamp corresponding to each reference point on the preset trajectory line and the index; and determining the state information corresponding to each reference point in the M reference points according to the index corresponding to each reference point in the M reference points.

16. The apparatus of claim 15,

the acquiring unit is specifically configured to determine a mapping relationship between an index of each reference point on the preset trajectory and the state information; and determining the state information corresponding to each reference point in the M reference points according to the index corresponding to each reference point in the M reference points and the mapping relation between the index of each reference point on the preset track line and the state information.

17. The apparatus of claim 16,

the acquisition unit is specifically used for carrying out linear processing on the kinematic model under the transverse control to obtain a linear kinematic model; the kinematic model is obtained by training by taking the center of a rear axle of the vehicle as a control point; inputting the parameter information corresponding to each reference point in the M reference points into the linear kinematics model to obtain the lateral speed and the yaw rate corresponding to each reference point; the parameter information corresponding to the reference point comprises the coordinate position, the speed, the rotation angle, the length of the center of mass of the vehicle and the center of the rear axle of the vehicle and the yaw angle of the reference point; and integrating the lateral speed and the yaw rate corresponding to each reference point to obtain the state information corresponding to each reference point.

18. The apparatus of claim 17,

the processing unit is further used for acquiring parameter information corresponding to the vehicle rear axle center at different moments; the parameter information corresponding to the center of the rear axle of the vehicle at different moments comprises the coordinate position of the center of the rear axle of the vehicle, the parking speed of the vehicle, the corner of a front wheel of the vehicle, the length of the center of mass of the vehicle and the center of the rear axle of the vehicle and the yaw angle of the vehicle; and training an initial kinematics model according to the corresponding parameter information of the vehicle rear axle center at different moments to obtain the kinematics model.

19. The apparatus according to any one of claims 11-16,

20. The apparatus according to any one of claims 11-18,

21. An electronic device, comprising:

at least one processor; and

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

22. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the control method of the vehicle according to any one of claims 1 to 10.

23. A vehicle, characterized by comprising:

a vehicle body and a control device of a vehicle provided in the vehicle body;

wherein the control device of the vehicle is the control device of the vehicle according to any one of claims 1 to 10.