CN117565893A

CN117565893A - Vehicle control method and device, electronic equipment and storage medium

Info

Publication number: CN117565893A
Application number: CN202311543726.5A
Authority: CN
Inventors: 郝晨希
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-11-17
Filing date: 2023-11-17
Publication date: 2024-02-20

Abstract

The disclosure provides a vehicle control method, a device, electronic equipment and a storage medium, relates to the technical field of artificial intelligence, and particularly relates to the technical field of automatic driving. The method comprises the following steps: acquiring an initial projection function and an initial vehicle control model; based on a small-angle assumption of the difference value between the actual course angle and the reference course angle of the automatic driving vehicle, carrying out transformation processing on the initial projection function to obtain a target projection function; performing projection processing on the initial vehicle control model based on the target projection function to obtain a candidate vehicle control model; and performing predictive control on the automatic driving vehicle based on the candidate vehicle control model. According to the scheme, the prediction precision of the vehicle control model can be improved, and the control precision of the automatic driving vehicle is further guaranteed.

Description

Vehicle control method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and more particularly, to the field of autopilot technology, and in particular, to a vehicle control method, apparatus, electronic device, storage medium, and computer program product.

Background

An autonomous vehicle, also called an unmanned vehicle, mainly relies on various sensors to sense the surrounding environment of the vehicle and controls the vehicle to run on a road according to information obtained by sensing without any human initiative.

Disclosure of Invention

The present disclosure provides a vehicle control method, apparatus, electronic device, storage medium, and computer program product.

According to an aspect of the present disclosure, there is provided a vehicle control method including:

acquiring an initial projection function and an initial vehicle control model;

based on a small-angle assumption of the difference value between the actual course angle and the reference course angle of the automatic driving vehicle, carrying out transformation processing on the initial projection function to obtain a target projection function;

performing projection processing on the initial vehicle control model based on the target projection function to obtain a candidate vehicle control model;

and performing predictive control on the automatic driving vehicle based on the candidate vehicle control model.

According to another aspect of the present disclosure, there is provided a vehicle control apparatus including:

the acquisition module is used for acquiring an initial projection function and an initial vehicle control model;

the transformation processing module is used for carrying out transformation processing on the initial projection function based on a small angle assumption of the difference value between the actual course angle and the reference course angle of the automatic driving vehicle to obtain a target projection function;

The model processing module is used for carrying out projection processing on the initial vehicle control model based on the target projection function to obtain a candidate vehicle control model;

and the control module is used for carrying out predictive control on the automatic driving vehicle based on the candidate vehicle control model.

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

at least one processor; and

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

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the vehicle control method of any embodiment of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the vehicle control method according to any embodiment of the present disclosure.

According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the vehicle control method of any embodiment of the present disclosure.

According to the technology disclosed by the invention, the prediction precision of the vehicle control model can be improved, and the control precision of the automatic driving vehicle is further ensured.

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

Drawings

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

FIG. 1 is a flow chart diagram of a vehicle control method according to an embodiment of the present disclosure;

FIG. 2 is a flow chart diagram of another vehicle control method according to an embodiment of the present disclosure;

FIG. 3 is a flow chart diagram of another vehicle control method according to an embodiment of the present disclosure;

fig. 4 is a schematic structural view of a vehicle control apparatus according to an embodiment of the present disclosure;

fig. 5 is a block diagram of an electronic device used to implement a vehicle control method of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one 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 disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the scheme of the disclosure, the transverse control of the automatic driving vehicle can be realized based on an MPC (Model Predictive Control ) control framework. In the MPC control framework, each step requires a recursion of the model and then calculates an optimization problem for a period of time in the future. The optimization problem needs to calculate the control error, that is, the recursive error of each step needs to be unified to the current reference point for calculation, and the transverse vehicle control model is generally a model constructed under the vehicle body coordinate system, so that the vehicle control model under the vehicle body coordinate system needs to be converted to the current reference point coordinate system for recursive calculation to obtain the final control result. In order to ensure the prediction accuracy of the converted model, the present disclosure proposes a vehicle control method, and the specific flow of the vehicle control method may be referred to as the following embodiment.

Fig. 1 is a schematic diagram of a vehicle control method according to an embodiment of the present disclosure, which may be applied to a scenario in which an autonomous vehicle is laterally controlled. The method may be performed by a vehicle control device implemented in software and/or hardware and configured in an electronic device.

As shown in fig. 1, the method specifically includes the following steps:

s101, acquiring an initial projection function and an initial vehicle control model.

In this embodiment, the initial projection function is a projection function that converts the initial vehicle control model from the vehicle body coordinate system to the reference point coordinate. The initial vehicle control model may be a vehicle dynamics model previously constructed based on vehicle state parameters.

In an alternative implementation, the expression of the initial projection function may be:wherein phi represents the actual heading angle of the autonomous vehicle at any position, +.>Representing the lateral speed obtained after deriving the lateral position of the autonomous vehicle, < >>Representing the longitudinal speed obtained after deriving the longitudinal position of the autonomous vehicle, < >>The lateral projection speed obtained by deriving the projection of the lateral position of the autonomous vehicle is represented.

While the initial vehicle control model may be exemplary:

where y represents the lateral position of the autonomous vehicle,representing the lateral speed obtained after deriving the lateral position of the autonomous vehicle, < >>The differential operation formula is represented by cf and cr, the cornering stiffness of front and rear wheels of the vehicle is represented by m, the mass of the vehicle is represented by lf and lr, the distance from the front and rear axles of the vehicle to the center of the vehicle is represented by I _z Representing the moment of inertia of the vehicle about the z-axis, v _x Representing the longitudinal speed of the vehicle, delta representing the front wheel rotation angle of the vehicle, phi representing the actual heading angle of the autonomous vehicle at any position,/for the vehicle>And represents the angular velocity obtained by deriving the actual heading angle of the autonomous vehicle at any position.

S102, based on the small angle assumption of the difference value between the actual course angle and the reference course angle of the automatic driving vehicle, the initial projection function is transformed, and the target projection function is obtained.

In this embodiment, in the process of converting the initial vehicle control model from the vehicle body coordinate system to the reference point coordinate system, coordinate rotation conversion calculation is involved, and in order to ensure the linearity of the recursive model, the initial projection function cannot be directly used to perform projective transformation on the initial vehicle control model, but the rotation transformation needs to be linearized, that is, the initial projection function needs to be linearized.

In this embodiment, the reference course angle refers to a course angle associated with a reference point on a reference motion track; the reference motion trajectory is a motion trajectory planned in advance for the autonomous vehicle, for example, a travel trajectory planned according to a start/end point. In the movement process of the automatic driving vehicle, the smaller the difference value between the actual movement track and the reference movement track of the automatic driving vehicle is, the better. The reference motion track comprises a plurality of reference points, and each reference point is pre-associated with a preset reference course angle; the reference point may be a specific object such as a building, a road green belt, a road sign board, etc. in the physical world, or may be a specific position point in the road. In the moving process of the automatic driving vehicle, the corresponding reference point can be found on the reference movement track at any position of the automatic driving vehicle, so that the actual course angle of the automatic driving vehicle at any position has a corresponding reference course angle. The essence of the automatic driving vehicle control is to control the actual course angle of the automatic driving vehicle at any position to be as close as possible to the reference course angle associated with the reference point corresponding to the position, and the two are equal to each other, so that the automatic driving vehicle control is in an optimal control state.

Based on the control nature of the automatic driving vehicle, the difference between the actual course angle of the vehicle and the reference course angle of the corresponding reference point can be considered to be small, so that the scheme disclosed by the invention is based on the assumption of small angle of the difference between the actual course angle of the automatic driving vehicle and the reference course angle, and the initial projection function is transformed to obtain the target projection function; in the automatic driving field, the small-angle assumption refers to that the angle is approximated as a linear function when sensor data is processed or path planning is performed, so that the calculation function is simplified.

When in implementation, the initial heading angle is calculated based on the small angle assumption of the difference value between the actual heading angle and the reference heading angle of the automatic driving vehicleThe initial projection function is transformed to obtain an objective projection function, which comprises the following steps: and based on a small angle assumption of the difference value between the actual course angle and the reference course angle, performing parameter change and approximate transformation processing on the intermediate projection function obtained by expansion on the initial projection function to obtain the target projection function. The process of performing parameter change and expansion on the initial projection function to obtain an intermediate projection function may include: taking the difference value between the actual course angle and the reference course angle of the automatic driving vehicle as an angle parameter variable, and carrying out parameter change and expansion on the initial projection function to obtain an intermediate projection function; exemplary, φ represents the actual heading angle of the autonomous vehicle at any location, φ _f The reference course angle of the reference point corresponding to the position of the automatic driving vehicle is represented, so that after the initial projection function is subjected to parameter change, the obtained function is as follows: and performing expansion operation on the obtained function to obtain an intermediate projection function, wherein the expression of the intermediate projection function is as follows: it should be understood that the above manner of determining the intermediate projection function is only an example, and other manners may be adopted to rewrite the initial projection function, and then perform parameter replacement according to the difference between the actual heading angle and the reference heading angle to obtain the final intermediate projection function.

Further, based on the small angle assumption of the difference between the actual course angle and the reference course angle, phi-phi can be considered when the intermediate projection function is subjected to approximate transformation processing _f Is smaller, at this time cos (. Phi. -phi.) _f ) Is approximately equal to 1, sin (phi-phi) _f ) Is approximately equal to phi-phi _f Thus utilize generation 1Replacing cos (phi-phi) in intermediate projection function _f ) By phi-phi _f Substitution of sin (phi-phi) in intermediate projection functions _f ) The obtained target projection function is

It should be noted that, the small angle assumption of the difference between the actual course angle and the reference course angle is adopted to transform the initial projection function, and the small angle assumption based on the actual course angle is not adopted, because the course angle change is larger when the vehicle turns with large curvature, if the actual course angle is smaller, and the initial projection function is approximately transformed, the projection function has larger error, and the accuracy of the vehicle control model based on the projection transformation is greatly reduced, which affects the vehicle control accuracy. In actual vehicle control, even when the vehicle turns with large curvature, the difference value between the actual course angle and the reference course angle at the reference point is generally smaller, so that the assumption of the small angle is easy to realize, the error of the transformed projection function is smaller, the accuracy loss of the vehicle control model after the projection processing based on the projection function is further smaller, and the prediction accuracy of the vehicle control model can be effectively ensured.

And S103, carrying out projection processing on the initial vehicle control model based on the target projection function to obtain a candidate vehicle control model.

In this embodiment, after the initial vehicle control model is obtained in step S101 and the target projection function is obtained in step S102, the projection conversion process may be performed on the initial vehicle control model based on the target projection function, so that the initial vehicle control model is converted into the reference point coordinate system, that is, after the projection conversion process, the candidate vehicle control model in the reference point coordinate system may be obtained.

S104, performing predictive control on the automatic driving vehicle based on the candidate vehicle control model.

In this embodiment, after the candidate vehicle control model is obtained, current state data (such as a position, a speed, an acceleration, a front wheel corner, etc. of the vehicle) of the autonomous vehicle may be directly obtained, and then prediction is performed based on the candidate vehicle control model and the current state data of the vehicle, that is, a possible future motion track of the vehicle is predicted, and then, the motion of the autonomous vehicle is controlled according to a difference between the predicted motion track and a planned reference motion track.

In the embodiment of the disclosure, based on the small angle assumption of the difference between the actual course angle and the reference course angle of the autonomous vehicle, the initial projection function is transformed to obtain the target projection function, so that the obtained target projection function has smaller error, and further, the accuracy loss of the vehicle control model converted based on the target projection function is ensured to be smaller, thereby ensuring the prediction accuracy of the vehicle control model, and further ensuring the control accuracy of the autonomous vehicle.

Fig. 2 is a flow chart diagram of another vehicle control method according to an embodiment of the present disclosure. As shown in fig. 2, the vehicle control method specifically includes the steps of:

s201, acquiring an initial projection function and an initial vehicle control model.

For specific forms of the initial projection function and the initial vehicle control model, reference may be made to the description of the above embodiments, and no further description is given here.

S202, based on the small angle assumption of the difference value between the actual course angle and the reference course angle of the automatic driving vehicle, performing transformation processing on the initial projection function to obtain a target projection function.

In this embodiment, the obtained objective projection function is The specific process of determining the objective projection function may be referred to the above embodiments, and will not be described herein.

After the objective projection function is obtained, projection processing is performed on the initial vehicle control model based on the objective projection function, and the process of obtaining the candidate vehicle control model can be seen in steps S203-S204.

S203, conducting derivation processing on the target projection function to obtain a derived target projection function.

Illustratively, the expression of the derived objective projection function is as follows:

s204, performing projection processing on the initial vehicle control model based on the target projection function and the derived target projection function to obtain a candidate vehicle control model.

In this embodiment, after obtaining the target projection function and the derived target projection function, the target projection function is transformed to obtainTransforming the derived target projection function to obtain +.>And will be->And->The expression of the model is carried into the initial vehicle control model to be operated, and the candidate vehicle control model can be obtained.

Exemplary, the expression of the candidate vehicle control model is as follows:

wherein,

the differential operation formula is represented by cf and cr, the cornering stiffness of front and rear wheels of the vehicle is represented by m, the mass of the vehicle is represented by lf and lr, the distance from the front and rear axles of the vehicle to the center of the vehicle is represented by I _z Representing the moment of inertia of the vehicle about the z-axis, v _x Represents the longitudinal speed of the vehicle, phi _f A reference heading angle, y, representing a reference point corresponding to any position of the automatically-built vehicle _proj Representing the projected position of the lateral position of the autonomous vehicle in the reference point coordinate system, phi representing the actual heading angle of the autonomous vehicle at any position, +.>The angular velocity obtained by deriving the actual course angle of the automatic driving vehicle at any position is represented, and delta represents the front wheel corner of the vehicle; />The longitudinal acceleration obtained by deriving the longitudinal position of the autonomous vehicle is represented. / >Representing an objective projection function; />Representing the derived object projection function.

S205, performing predictive control on the automatic driving vehicle based on the candidate vehicle control model.

In an alternative implementation, the current position of the autonomous vehicle may be determined first, and a current reference point corresponding to the current position may be determined from a reference motion trajectory; the reference motion trail is a motion trail planned for the automatic driving vehicle in advance; acquiring a reference heading angle of a reference point, an actual heading angle of the vehicle at a current location, and other vehicle state data of the autonomous vehicle at the current location (e.g., speed, acceleration, moment of inertia, front wheel steering angle, etc. of the autonomous vehicle); according to the reference course angle of the reference point, the actual course angle of the vehicle at the current position and other vehicle state data of the automatic driving vehicle at the current position, the vehicle motion trail prediction is carried out by combining a candidate vehicle control model; and carrying out optimization operation according to the predicted motion trail and the reference motion trail to obtain vehicle control data of the next moment, and carrying out vehicle control based on the vehicle control data.

In this embodiment, the specific form of the candidate vehicle control model may be determined, so that vehicle control may be performed based on the candidate vehicle control model, and it may be ensured that the vehicle may also be controlled with accuracy even when turning with a large curvature.

Fig. 3 is a flow chart diagram of another vehicle control method according to an embodiment of the present disclosure. As shown in fig. 3, the method specifically includes the following steps:

s301, acquiring an initial projection function and an initial vehicle control model.

S302, based on the small angle assumption of the difference value between the actual course angle and the reference course angle of the automatic driving vehicle, the initial projection function is transformed, and the target projection function is obtained.

S303, conducting derivation processing on the target projection function to obtain a derived target projection function.

S304, performing projection processing on the initial vehicle control model based on the target projection function and the derived target projection function to obtain a candidate vehicle control model.

Exemplary, the expression of the candidate vehicle control model is as follows:

wherein,

the meaning of each parameter in the model may be referred to the description of the above embodiment, and will not be described herein.

And S305, performing singular point elimination processing on the candidate vehicle control model to obtain a processed candidate vehicle control model.

In the present embodiment, after the candidate vehicle control model is obtained through steps S301-S304, when φ _f Approaching pi/2, singularities may occur, resulting in certain terms in the candidate vehicle control model (e.g.) Infinity phenomenon occurs, and the candidate vehicle control model diverges, so that the model is subjected to singular point elimination treatment near the singular point, that is, the candidate vehicle control model is rewritten.

In an alternative implementation, the expression of the candidate vehicle control model after eliminating the singular point is as follows:

where phi denotes the actual heading angle of the autonomous vehicle at any position,representing the angular velocity, v, derived from the actual heading angle of the autonomous vehicle at any position _x Representing the longitudinal speed of an autonomous vehicle, a _x Representing longitudinal acceleration, w, detected by vehicle sensors _b Representing the wheelbase of the vehicle.

S306, performing predictive control on the automatic driving vehicle based on the candidate vehicle control model.

Two types of candidate vehicle control models are obtained through steps S301 to S305, and alternatively, for convenience of description, the candidate vehicle control model before the elimination of the singular point is referred to as a first candidate vehicle control model, and the candidate vehicle control model after the elimination of the singular point is referred to as a second candidate vehicle control model. According to the scheme, different candidate vehicle control models can be selected according to the magnitude of the current reference course angle, so that the influence of singular points is avoided.

In an alternative implementation, predictive control of the autonomous vehicle based on the candidate vehicle control model includes: determining the current position of the automatic driving vehicle, and determining a current reference point corresponding to the current position from a reference motion track; the reference motion trail is a motion trail planned for the automatic driving vehicle in advance; determining a reference course angle corresponding to the current reference point; selecting a target vehicle control model from the candidate vehicle control models according to the reference course angle corresponding to the current reference point; illustratively, in response to the value of the reference heading angle being within the preset angle interval, taking the processed candidate vehicle control model as the target vehicle control model; namely, the second candidate vehicle control model is taken as a target vehicle control model; or, in response to the value of the current reference course angle not being within the preset angle interval, taking the candidate vehicle control model before processing as a target vehicle control model; i.e., the first candidate vehicle control model is the target vehicle control model. The preset angle interval may be an interval close to pi/2, for example, the preset angle interval may be [ θ, pi/2 ], and θ may be set according to actual needs. Further, based on the target vehicle control model, vehicle motion trail prediction is performed in combination with vehicle state data of the autonomous vehicle at the current position. It will be appreciated that if the target vehicle control model is a candidate vehicle control model before the elimination of the singular point, the vehicle state data of the autonomous vehicle at the current position includes an actual heading angle of the autonomous vehicle at the current position, a reference heading angle associated with a reference point corresponding to the current position, and other vehicle state data of the autonomous vehicle at the current position (e.g., speed, acceleration, front wheel steering angle, etc. of the autonomous vehicle). If the target vehicle control model is a candidate vehicle control model after the singular point is eliminated, the vehicle state data of the autonomous vehicle at the current position includes the longitudinal speed, the longitudinal acceleration, the vehicle wheelbase, and the actual heading angle at the current position of the vehicle. Further, performing optimization operation according to the predicted motion trail and the reference motion trail to obtain subsequent vehicle control data, and performing vehicle control based on the vehicle control data.

According to the scheme, the influence of the singular point on the candidate vehicle control model is eliminated, different candidate vehicle control models can be selected according to the value of the current reference course angle, the sectional prediction is realized, and the accuracy of vehicle control is further ensured.

Fig. 4 is a schematic structural view of a vehicle control apparatus according to an embodiment of the present disclosure, which is applicable to a scenario in which an autonomous vehicle is laterally controlled. The device can realize the vehicle control method according to any embodiment of the disclosure. As shown in fig. 4, the apparatus 400 specifically includes:

an acquisition module 401 for acquiring an initial projection function and an initial vehicle control model;

the transformation processing module 402 is configured to perform transformation processing on the initial projection function based on a small angle assumption of a difference value between an actual heading angle and a reference heading angle of the autonomous vehicle, so as to obtain a target projection function;

the model processing module 403 is configured to perform projection processing on the initial vehicle control model based on the target projection function, so as to obtain a candidate vehicle control model;

a control module 404 for performing predictive control on the autonomous vehicle based on the candidate vehicle control model

On the basis of the above embodiment, the transformation processing module is further configured to:

And based on a small angle assumption of the difference value between the actual course angle and the reference course angle, performing parameter change and approximate transformation processing on the intermediate projection function obtained by expansion on the initial projection function to obtain the target projection function.

On the basis of the above embodiment, the expression of the initial projection function is:

the expression of the intermediate projection function is:

the expression of the objective projection function is as follows:

wherein phi represents the actual heading angle of the autonomous vehicle at any position _f A reference heading angle representing a reference point corresponding to any location of the autonomous vehicle,representing the lateral speed obtained after deriving the lateral position of the autonomous vehicle, < >>Representing the longitudinal speed obtained after deriving the longitudinal position of the autonomous vehicle, < >>The lateral projection speed obtained by deriving the projection of the lateral position of the autonomous vehicle is represented.

On the basis of the above embodiment, the model processing module is further configured to:

conducting derivation processing on the target projection function to obtain a derived target projection function;

and carrying out projection processing on the initial vehicle control model based on the target projection function and the derived target projection function to obtain a candidate vehicle control model. Wherein the expression of the candidate vehicle control model is as follows:

Wherein,

the differential operation formula is represented by cf and cr, the cornering stiffness of front and rear wheels of the vehicle is represented by m, the mass of the vehicle is represented by lf and lr, the distance from the front and rear axles of the vehicle to the center of the vehicle is represented by I _z Representing the moment of inertia of the vehicle about the z-axis, v _x Represents the longitudinal speed of the vehicle, phi represents the actual heading angle of the autonomous vehicle at any location, phi _f Representing a reference heading of the autonomous vehicle at a reference point corresponding to any position, wherein delta represents a front wheel corner of the vehicle; />Representing longitudinal acceleration derived from the longitudinal position of an autonomous vehicle。

On the basis of the above embodiment, optionally, the method further includes:

and the singular processing module is used for performing singular point elimination processing on the candidate vehicle control model to obtain a processed candidate vehicle control model.

On the basis of the above embodiment, the expression of the processed candidate vehicle control model is as follows:

where phi denotes the actual heading angle of the autonomous vehicle at any position,representing angular velocity, v, derived from actual heading angle of autonomous vehicle at any position _x Representing the longitudinal speed of an autonomous vehicle, a _x Representing the longitudinal acceleration, w, of an autonomous vehicle _b Representing the wheelbase of the vehicle.

On the basis of the above embodiment, the control module includes:

a first determining unit, configured to determine a current position of the autonomous vehicle, and determine a current reference point corresponding to the current position from a reference motion trajectory; the reference motion trail is a motion trail planned for the automatic driving vehicle in advance;

the second determining unit is used for determining a reference course angle corresponding to the current reference point;

a selection unit, configured to select a target vehicle control model from the candidate vehicle control models according to a reference heading angle corresponding to the current reference point;

the prediction unit is used for predicting a vehicle motion trail based on the target vehicle control model and combining vehicle state data of the automatic driving vehicle at the current position;

and the control unit is used for carrying out optimization operation according to the predicted motion trail and the reference motion trail to obtain subsequent vehicle control data and carrying out vehicle control based on the vehicle control data.

On the basis of the above embodiment, the selection unit is further configured to:

responding to the value of the reference course angle in a preset angle interval, and taking the processed candidate vehicle control model as a target vehicle control model; or alternatively, the first and second heat exchangers may be,

And responding to the fact that the value of the reference course angle is not in the preset angle interval, and taking the candidate vehicle control model before processing as a target vehicle control model.

The product can execute the method provided by any embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of executing the method.

In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.

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

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

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

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

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

Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

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

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

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or 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 may 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 input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background 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 background, 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), blockchain networks, and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs executing on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.

Artificial intelligence is the discipline of studying the process of making a computer mimic certain mental processes and intelligent behaviors (e.g., learning, reasoning, thinking, planning, etc.) of a person, both hardware-level and software-level techniques. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligent software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge graph technology and the like.

Cloud computing (cloud computing) refers to a technical system that a shared physical or virtual resource pool which is elastically extensible is accessed through a network, resources can comprise servers, operating systems, networks, software, applications, storage devices and the like, and resources can be deployed and managed in an on-demand and self-service mode. Through cloud computing technology, high-efficiency and powerful data processing capability can be provided for technical application such as artificial intelligence and blockchain, and model training.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the technical solutions provided by the present disclosure are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A vehicle control method comprising:

acquiring an initial projection function and an initial vehicle control model;

2. The method of claim 1, wherein transforming the initial projection function based on a small angle assumption of an actual heading angle of the autonomous vehicle to a reference heading angle difference value to obtain an objective projection function comprises:

3. The method of claim 2, wherein the expression of the initial projection function is:

the expression of the intermediate projection function is:

the expression of the objective projection function is as follows:

wherein phi represents the actual heading angle of the autonomous vehicle at any position _f A reference heading angle representing a reference point corresponding to any location of the autonomous vehicle,represents the lateral velocity obtained after deriving the lateral position of the autonomous vehicle,representing the longitudinal speed obtained after deriving the longitudinal position of the autonomous vehicle, < >>The lateral projection speed obtained by deriving the projection of the lateral position of the autonomous vehicle is represented.

4. The method of claim 1, wherein projecting the initial vehicle control model based on the target projection function results in a candidate vehicle control model, comprising:

and carrying out projection processing on the initial vehicle control model based on the target projection function and the derived target projection function to obtain a candidate vehicle control model.

5. The method according to claim 1 or 4, wherein the expression of the candidate vehicle control model is as follows:

Wherein,

the differential operation formula is represented by cf and cr, the cornering stiffness of front and rear wheels of the vehicle is represented by m, the mass of the vehicle is represented by lf and lr, the distance from the front and rear axles of the vehicle to the center of the vehicle is represented by I _z Representing the moment of inertia of the vehicle about the z-axis, v _x Represents the longitudinal speed of the vehicle, phi represents the actual heading angle of the autonomous vehicle at any location, phi _f A reference course angle of a reference point corresponding to any position of the automatic driving vehicle is represented, and delta represents a front wheel corner of the vehicle; />The longitudinal acceleration obtained by deriving the longitudinal position of the autonomous vehicle is represented.

6. The method of claim 5, further comprising:

and performing singular point elimination treatment on the candidate vehicle control model to obtain a treated candidate vehicle control model.

7. The method of claim 6, wherein the expression of the processed candidate vehicle control model is as follows:

8. The method of claim 7, wherein predictive controlling the autonomous vehicle based on the candidate vehicle control model comprises:

determining the current position of the automatic driving vehicle, and determining a current reference point corresponding to the current position from a reference motion track; the reference motion trail is a motion trail planned for the automatic driving vehicle in advance;

determining a reference course angle corresponding to the current reference point;

selecting a target vehicle control model from the candidate vehicle control models according to the reference course angle corresponding to the current reference point;

based on the target vehicle control model, combining the vehicle state data of the automatic driving vehicle at the current position to predict the vehicle motion trail;

and carrying out optimization operation according to the predicted motion trail and the reference motion trail to obtain subsequent vehicle control data, and carrying out vehicle control based on the vehicle control data.

9. The method of claim 8, wherein selecting a target vehicle control model from candidate vehicle control models according to a reference heading angle corresponding to the current reference point comprises:

10. A vehicle control apparatus comprising:

11. The apparatus of claim 10, wherein the transform processing module is further to:

12. The apparatus of claim 11, wherein the expression of the initial projection function is:

the expression of the intermediate projection function is:

the expression of the objective projection function is as follows:

wherein phi represents the actual heading angle of the autonomous vehicle at any position _f Indicating a reference heading of an autonomous vehicle at a reference point corresponding to any locationThe angle of the corner of the plate,representing the lateral speed obtained after deriving the lateral position of the autonomous vehicle, < >>Representing the longitudinal speed obtained after deriving the longitudinal position of the autonomous vehicle, < >>The lateral projection speed obtained by deriving the projection of the lateral position of the autonomous vehicle is represented.

13. The apparatus of claim 10, wherein the model processing module is further to:

14. The apparatus according to claim 10 or 13, wherein an expression of the candidate vehicle control model is as follows:

wherein,

15. The apparatus of claim 14, further comprising:

16. The apparatus of claim 15, wherein the expression of the processed candidate vehicle control model is as follows:

17. The apparatus of claim 16, wherein the control module comprises:

18. The apparatus of claim 17, wherein the selection unit is further configured to:

19. An electronic device, comprising:

at least one processor; and

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

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the vehicle control method of any one of claims 1-9.

20. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the vehicle control method according to any one of claims 1 to 9.

21. A computer program product comprising a computer program which, when executed by a processor, implements the vehicle control method according to any one of claims 1-9.