CN114802203A

CN114802203A - Longitudinal control method and device of vehicle, storage medium and automatic driving vehicle

Info

Publication number: CN114802203A
Application number: CN202210514323.7A
Authority: CN
Inventors: 刘征宇; 谭益农; 朱振广; 梁琪; 李柳涛
Original assignee: Apollo Intelligent Technology Beijing Co Ltd
Current assignee: Apollo Intelligent Technology Beijing Co Ltd
Priority date: 2022-05-11
Filing date: 2022-05-11
Publication date: 2022-07-29

Abstract

The disclosure provides a longitudinal control method and device of a vehicle, a storage medium and an automatic driving vehicle, and relates to the technical field of computers, in particular to the technical fields of artificial intelligence, such as the field of intelligent transportation, the technical field of automatic driving and the like. The specific implementation scheme is as follows: when the longitudinal control of automatic driving is carried out on the vehicle, the predicted longitudinal control parameters of the model prediction controller of the vehicle at each predicted time point in the prediction time domain are determined by combining the predicted longitudinal speed of the vehicle at each predicted time point in the prediction time domain after the current time, the longitudinal control quantity at each predicted time point in the prediction time domain is determined by combining the longitudinal control parameter information, the longitudinal model in the model prediction controller and the expected track of the vehicle, and the longitudinal control quantity at the first predicted time point in the prediction time domain is based on the longitudinal control quantity at the first predicted time point in the prediction time domain, so that the longitudinal control is carried out on the vehicle. Therefore, the accuracy and the stability of longitudinal control of the vehicle are improved, and the safety of automatic driving of the vehicle is further improved.

Description

Longitudinal control method and device of vehicle, storage medium and automatic driving vehicle

Technical Field

The disclosure relates to the technical field of computers, in particular to the technical fields of artificial intelligence, such as the field of intelligent transportation and the technical field of automatic driving, and particularly relates to a longitudinal control method and device of a vehicle, a storage medium and an automatic driving vehicle.

Background

With the development of science and technology, the automatic driving vehicle becomes an important development direction of future automobiles. The automatic driving vehicle not only can help to improve the travel convenience and the travel experience of people, but also can greatly improve the travel efficiency of people.

In the process of longitudinal control of an autonomous vehicle, in the related art, the autonomous vehicle is generally longitudinally controlled based on a longitudinal control amount determined in an autonomous system. The accuracy of the longitudinal control amount is very important for the safe driving of the autonomous vehicle.

Disclosure of Invention

The disclosure provides a longitudinal control method and device for a vehicle, a storage medium and an automatic driving vehicle.

According to an aspect of the present disclosure, there is provided a longitudinal control method of a vehicle, the method including: determining a predicted longitudinal speed sequence of the vehicle in a predicted time domain after a current time, wherein the predicted longitudinal speed sequence comprises: predicted longitudinal velocities at respective predicted time points; for each prediction time point, determining longitudinal control parameter information of a model prediction controller of the vehicle at the prediction time point according to the predicted longitudinal speed at the prediction time point; determining a longitudinal control quantity sequence of the prediction time domain according to the longitudinal control parameter information, a longitudinal model in the model predictive controller and the expected track of the vehicle, wherein the longitudinal control quantity sequence comprises: longitudinal control amounts at respective predicted time points; and performing automatic driving longitudinal control on the vehicle according to the longitudinal control quantity at the first prediction time point in the prediction time domain.

According to another aspect of the present disclosure, there is provided a longitudinal control apparatus of a vehicle, the apparatus including: a first determination module configured to determine a predicted longitudinal speed sequence of the vehicle in a predicted time domain after a current time, wherein the predicted longitudinal speed sequence comprises: predicted longitudinal velocities at respective predicted time points; a second determination module, configured to determine, for each of the predicted time points, longitudinal control parameter information of a model predictive controller of the vehicle at the predicted time point according to a predicted longitudinal speed at the predicted time point; a third determining module, configured to determine a longitudinal control quantity sequence of the prediction time domain according to the longitudinal control parameter information, a longitudinal model in the model predictive controller, and a desired trajectory of the vehicle, where the longitudinal control quantity sequence includes: longitudinal control amounts at respective predicted time points; and the control module is used for carrying out longitudinal control on automatic driving on the vehicle according to the longitudinal control quantity at the first prediction time point in the prediction time domain.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the longitudinal control method of the vehicle 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 a longitudinal control method of a vehicle disclosed in an embodiment of the present disclosure.

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

According to another aspect of the present disclosure, an autonomous vehicle is provided, which includes the electronic device disclosed in the embodiments of the present disclosure.

One embodiment in the above application has the following advantages or benefits:

when the longitudinal control of automatic driving is carried out on the vehicle, the predicted longitudinal control parameters of the model prediction controller of the vehicle at each predicted time point in the prediction time domain are determined by combining the predicted longitudinal speed of the vehicle at each predicted time point in the prediction time domain after the current time, the longitudinal control quantity at each predicted time point in the prediction time domain is determined by combining the longitudinal control parameter information, the longitudinal model in the model prediction controller and the expected track of the vehicle, and the longitudinal control quantity at the first predicted time point in the prediction time domain is based on the longitudinal control quantity at the first predicted time point in the prediction time domain, so that the longitudinal control of the vehicle is carried out. Therefore, the longitudinal control quantity for longitudinally controlling the vehicle is accurately determined by combining the predicted longitudinal speed at each predicted time point in the prediction time domain, the accuracy and the stability of the longitudinal control of the vehicle are improved, and the safety of automatic driving of the vehicle can be further improved.

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

Drawings

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

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

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

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

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

FIG. 5 is a schematic diagram according to a fifth embodiment of the present disclosure;

FIG. 6 is a schematic diagram according to a sixth embodiment of the present disclosure;

FIG. 7 is a schematic diagram according to a seventh embodiment of the present disclosure;

fig. 8 is a block diagram of an electronic device for implementing a longitudinal control method of a vehicle according to an embodiment of the present disclosure.

Detailed Description

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

A longitudinal control method, an apparatus, a storage medium, and an autonomous vehicle of a vehicle of the embodiments of the present disclosure are described below with reference to the drawings.

Fig. 1 is a schematic diagram according to a first embodiment of the present disclosure, which provides a longitudinal control method of a vehicle.

As shown in fig. 1, the longitudinal control method of the vehicle may include:

step 101, determining a predicted longitudinal speed sequence of a predicted time domain of the vehicle after the current time, wherein the predicted longitudinal speed sequence comprises: predicted longitudinal velocity at each predicted time point.

The main execution body of the longitudinal control method of the vehicle is a longitudinal control device of the vehicle, the longitudinal control device of the vehicle can be realized by software and/or hardware, and the longitudinal control device of the vehicle can be an electronic device, or can be configured in the electronic device, so as to realize automatic driving control of the vehicle.

In some exemplary embodiments, the electronic device may be a terminal device or a server, and the embodiment is not particularly limited thereto.

In some exemplary embodiments, the terminal device may be a device that can be installed in any vehicle, such as an on-board controller, an on-board computer, and the like. In some examples, the longitudinal control device of the vehicle may be an on-board computer, where it should be noted that the on-board computer in this example has an automatic driving function, can plan a path of the vehicle, and can perform automatic driving control on the vehicle. In other examples, the longitudinal control device of the vehicle may be a server, and the server may communicate with the vehicle and may perform automatic driving control on the vehicle.

In some embodiments of the present disclosure, in order to accurately perform longitudinal control of automatic driving on a vehicle and improve safety and stability of vehicle driving during vehicle driving, a speed of the vehicle in a prediction time domain after a current time may be predicted based on a current vehicle state of the vehicle at the current time to obtain predicted longitudinal speeds of the vehicle at respective prediction time points in the prediction time domain after the current time, and the predicted longitudinal speeds may be sorted according to a chronological order of the prediction time points to obtain a predicted longitudinal speed sequence of the vehicle in the prediction time domain.

The prediction time domain refers to a period of time after the current time, where the period of time may include N prediction time points, and a preset time interval exists between two adjacent prediction time points.

The preset time interval is preset, and the value of the preset time interval can be set according to actual requirements. For example, the prediction time domain may include 25 prediction time points, and the time interval between two adjacent prediction time points may be 1 second. For another example, the prediction time domain may include 10 prediction time points, and a time interval between two adjacent prediction time points may be 2 seconds.

In some exemplary embodiments, in order to accurately control the longitudinal direction of the vehicle, the time length of the prediction time domain and the value of the time interval between the prediction time points may also be determined in combination with the current speed of the vehicle at the current time.

And 102, aiming at each prediction time point, determining longitudinal control parameter information of the model prediction controller of the vehicle at the prediction time point according to the predicted longitudinal speed at the prediction time point.

In other exemplary embodiments, after the predicted longitudinal speed at each predicted time point is determined, for each predicted time point, the longitudinal control parameter information corresponding to the predicted longitudinal speed at the predicted time point is determined based on the correspondence relationship between the longitudinal speed and the longitudinal control parameter information that is stored in advance, and the determined longitudinal control parameter information is used as the longitudinal control parameter information at the predicted time point.

The longitudinal control parameter information may include a first penalty weight for applying to the state quantity error, a second penalty weight for applying to the control quantity, and a second penalty weight for applying to the control quantity increment.

Step 103, determining a longitudinal control quantity sequence of a prediction time domain according to the longitudinal control parameter information, the longitudinal model in the model prediction controller and the expected track of the vehicle, wherein the longitudinal control quantity sequence comprises: the vertical control amount at each predicted time point.

The Model Predictive Controller (MPC) is used for predicting longitudinal models, expected trajectories and longitudinal vehicle state parameters of the vehicle at the current time in the Model Predictive controller to obtain longitudinal Control quantities at each prediction time point in a prediction time domain, so that automatic driving Control processing is performed on the vehicle according to the longitudinal Control quantity at the first prediction time point in the prediction time domain.

The model predictive controller adopts an advanced process control strategy to carry out prediction processing. For example, a sequence of control quantities is randomly determined, and a predicted trajectory is determined based on the sequence of control quantities; performing one adjustment on the control quantity sequence based on the predicted track and the expected track; the above process is repeated until the difference between the predicted trajectory and the desired trajectory satisfies a specified condition.

It should be noted that the longitudinal model may also be referred to as a longitudinal state quantity equation model, and the longitudinal model is used for predicting longitudinal vehicle state parameters of the vehicle. Specifically, after a first longitudinal vehicle state parameter and a corresponding longitudinal control amount are input to the longitudinal model, the longitudinal model may predict a second longitudinal vehicle state parameter into which the vehicle enters after the longitudinal control amount is applied to the vehicle under the first longitudinal vehicle state parameter.

The longitudinal vehicle state parameters in the present embodiment may include longitudinal displacement, longitudinal speed, longitudinal moment, and the like.

The longitudinal control amount in the present embodiment may include a drive control amount and/or a brake control amount, among others.

The state quantity error is an error between the desired state quantity and the predicted state quantity at the prediction time point.

The desired trajectory refers to a trajectory that the vehicle can reach in the prediction time domain when planning the vehicle.

The predicted track refers to a track determined by predicting the running state of the vehicle at each predicted time point in the predicted time domain by combining the actual running condition of the vehicle at the current time and according to the predicted running state of the vehicle at each predicted time point.

And 104, performing longitudinal control of automatic driving on the vehicle according to the longitudinal control quantity at the first prediction time point in the prediction time domain.

In some exemplary embodiments of the present disclosure, after determining the longitudinal control amount sequence of the vehicle in the prediction time domain, the longitudinal control amount at the first prediction time point in the prediction time domain may be taken as the longitudinal control amount of the vehicle at the next time, and the vehicle may be longitudinally controlled at the next time based on the longitudinal control amount.

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

In some exemplary embodiments, the time interval between the current time and the next time is the same as the time interval between the adjacent predicted time points. When the longitudinal control is performed at the next time, since the next time is the first predicted time point in the predicted time domain, the longitudinal control quantity at the first predicted time point in the predicted time domain can be used as the longitudinal control quantity used for the longitudinal control of the vehicle at the next time.

According to the longitudinal control method of the vehicle, when the vehicle is subjected to longitudinal control of automatic driving, the predicted longitudinal control parameters of the model prediction controller of the vehicle at the predicted time points in the predicted time domain are determined by combining the predicted longitudinal speeds of the vehicle at the predicted time points in the predicted time domain after the current time, the longitudinal control quantity at each predicted time point in the predicted time domain is determined by combining the longitudinal control parameter information, the longitudinal model in the model prediction controller and the expected track of the vehicle, and the longitudinal control quantity at the first predicted time point in the predicted time domain is based on the longitudinal control quantity, so that the vehicle is subjected to longitudinal control. Therefore, the longitudinal control quantity for longitudinally controlling the vehicle is accurately determined by combining the predicted longitudinal speed at each predicted time point in the prediction time domain, the accuracy and the stability of the longitudinal control of the vehicle are improved, and the safety of automatic driving of the vehicle can be further improved.

In some embodiments, in order to accurately determine the vertical control parameter information at each prediction time point in the prediction time domain, one possible implementation manner of the foregoing step 102, as shown in fig. 2, may include:

step 201, according to the predicted longitudinal speed at the prediction time point, determining a first penalty weight of the state quantity error of the model predictive controller of the vehicle at the prediction time point.

In some example embodiments, the longitudinal control parameter may include a first penalty weight. The first penalty weight is a penalty weight applied to the state quantity error at the prediction time point by the model predictive controller of the vehicle to carry out model predictive control on the longitudinal model.

In the related art, penalty weights applied by the model predictive controller to state quantity errors at each prediction time point are generally fixed, however, since the longitudinal model is generally linear, the corresponding longitudinal speed at the prediction time point in the optimization process may be negative, and in fact, no matter how large the longitudinal control quantity (such as braking force) of the vehicle is, the longitudinal speed of the vehicle may not be negative, which is a limitation of the linear model, and if the model predictive controller of the vehicle strictly limits the longitudinal speed to a non-negative number in the optimization solution process, the solution may fail. In order to enable the longitudinal control quantity to be accurately determined subsequently and improve the safety of automatic driving control, in some embodiments, for each predicted time point, whether the predicted longitudinal speed of the vehicle at the predicted time point is greater than zero or not can be judged, and in the case that the predicted longitudinal speed at the predicted time point is greater than or equal to zero, the penalty weight of the state quantity error at the predicted time point is greater than zero. In some examples, the penalty weight of the state quantity error at the prediction time point may be set to a preset value greater than zero, wherein the preset value is an empirical value obtained from a plurality of experiments.

In other embodiments, the penalty weight for the state quantity error at the prediction time point is equal to zero in case the predicted longitudinal speed at the prediction time point is less than zero.

Step 202, obtaining second penalty weights preset for the longitudinal control quantity at the prediction time points, wherein the second penalty weights at different prediction time points are the same.

And step 203, acquiring third penalty weights preset for the control quantity increment at the forecasting time points, wherein the third penalty weights at different forecasting time points are the same.

And 204, generating longitudinal control parameter information of the model predictive controller of the vehicle at the predictive time point according to the first penalty weight, the second penalty weight and the third penalty weight.

In some exemplary embodiments, in order to accurately determine the predicted longitudinal speed sequence of the vehicle in the predicted time domain, one possible implementation of the foregoing step 101, as shown in fig. 3, may include:

in step 301, the current longitudinal speed of the vehicle at the current time is obtained.

Step 302, obtaining an expected longitudinal acceleration sequence of the vehicle in a prediction time domain, wherein the expected longitudinal acceleration sequence comprises: the desired longitudinal acceleration at each predicted point in time.

Step 303, determining a predicted longitudinal speed sequence of the vehicle in a predicted time domain according to the current longitudinal speed and the expected longitudinal acceleration sequence.

In some exemplary embodiments, the current longitudinal speed and the sequence of desired longitudinal speeds may be input into a longitudinal speed prediction model to be passed through the longitudinal speed prediction model to derive a sequence of predicted longitudinal speeds of the vehicle in a prediction horizon.

In some exemplary embodiments, in order to accurately determine the predicted longitudinal speed sequence in the prediction time domain, the determining a predicted longitudinal speed sequence of the vehicle in the prediction time domain according to the current longitudinal speed and the expected longitudinal acceleration sequence may include, as shown in fig. 4:

step 401, for the ith prediction time point, determining the predicted longitudinal speed at the ith prediction time point according to the expected longitudinal acceleration and the current longitudinal speed at the ith prediction time point, wherein the initial value of i is 1.

The ith prediction time point refers to the ith prediction time point in a plurality of prediction time points which are arranged in the prediction time domain according to the time sequence.

Step 402, add 1 to i.

And 403, under the condition that i is less than or equal to N, determining the predicted longitudinal speed at the ith prediction time point according to the expected longitudinal acceleration at the ith prediction time point and the predicted longitudinal speed at the (i-1) th prediction time point, and skipping to 402, wherein N is the total number of the prediction time points in the prediction time domain.

In some exemplary embodiments, the above-described calculating the predicted longitudinal speed V at the i-th predicted time _i The calculation formula of (a) is as follows:

wherein, a in the formula _r Representing the expected acceleration at the r-th predicted time point, wherein the value of r is 1 to i, v in the formula _cur The current longitudinal velocity is represented, where t in the formula represents the time interval between predicted time points.

For example, in the case where the time interval t between the prediction time points is 1 second, the above calculation formula of calculating the predicted longitudinal speed at the i-th prediction time may be expressed as:

the predicted longitudinal speed at the ith prediction time is the longitudinal speed obtained by the vehicle when the vehicle runs at the current longitudinal speed according to the expected longitudinal speed corresponding to the prediction time at the previous i prediction time points.

Wherein, it can be understood that, in the case that i is greater than N, the process is ended directly.

In some embodiments of the present disclosure, in order to accurately determine the longitudinal control quantity sequence of the prediction time domain, one possible implementation manner of the step 104 may include, as shown in fig. 5:

step 501, longitudinal vehicle state parameters of the vehicle at the current moment are determined, and initial longitudinal control quantity of the vehicle at each prediction time point is determined.

In some exemplary embodiments, the initial longitudinal control amount of the vehicle at each predicted time point may be determined based on the longitudinal vehicle state parameter of the vehicle at the current time.

In other exemplary embodiments, initial longitudinal control amounts that are preset for the vehicle at respective predicted time points in advance may be acquired.

It is to be understood that the initial longitudinal control amounts at the respective predicted time points may be the same, or may be different from each other, or may be partially the same, and this embodiment is not particularly limited to this, and is accurate in the actual situation.

And 502, determining the predicted longitudinal vehicle state parameters at each prediction time point according to the longitudinal vehicle state parameters, the initial longitudinal control quantity at each prediction time point and the longitudinal model.

In some exemplary embodiments, one possible implementation manner of determining the predicted longitudinal vehicle state parameter at each predicted time point according to the longitudinal vehicle state parameter, the initial longitudinal control amount at each predicted time point, and the longitudinal model may be as follows: determining a predicted longitudinal vehicle state parameter at the ith prediction time point by using the initial longitudinal control quantity and the current longitudinal vehicle state parameter at the ith prediction time point based on the longitudinal model aiming at the ith prediction time point, wherein the initial value of i is 1; adding 1 to i; and under the condition that i is less than or equal to N, determining the predicted longitudinal vehicle state parameter at the ith predicted time point according to the expected longitudinal acceleration at the ith predicted time point and the predicted longitudinal vehicle state parameter at the (i-1) th predicted time point, and skipping to the step of adding 1 to i, wherein N is the total number of predicted time points in the predicted time domain.

Step 503, constructing an objective function according to the predicted longitudinal vehicle state parameters at each predicted time point, the expected longitudinal vehicle state parameters at each predicted time point in the expected track and the longitudinal control parameter information.

Wherein, the formula of the objective function J is exemplified as follows:

wherein Y in the formula _i Representing the predicted longitudinal vehicle state parameter at the ith prediction time point; y in the formula _ri Representing the expected longitudinal vehicle state parameter at the ith prediction time point; q _i A first penalty weight corresponding to the state quantity error at the ith prediction time point is represented; u shape _i Indicating the ith predictionAn initial longitudinal control quantity at a point in time; delta U _i Indicating a control amount increment at the ith prediction time point; r ₁ Representing a second penalty weight; r ₂ Representing a third penalty weight; t represents transposition; n denotes the total number of prediction time points in the prediction time domain.

And step 504, adjusting the initial longitudinal control quantity at each prediction time point according to the numerical value of the objective function to obtain the longitudinal control quantity at each prediction time point.

That is, after the objective function is determined, the optimal solution of the objective function can be solved through rolling optimization to obtain the longitudinal control quantity at each prediction time point.

And 505, determining a longitudinal control quantity sequence according to the longitudinal control quantity at each predicted time point.

In an embodiment of the present disclosure, after the longitudinal control quantities at the respective predicted time points are obtained, the longitudinal control quantities may be sorted according to the time sequence of the predicted time points to obtain a longitudinal control quantity sequence.

In order to realize the above embodiments, the embodiments of the present disclosure also provide a longitudinal control device of a vehicle.

Fig. 6 is a schematic diagram according to a sixth embodiment of the present disclosure, which provides a longitudinal control apparatus of a vehicle.

As shown in fig. 6, the longitudinal control apparatus 600 of the vehicle may include a first determination module 601, a second determination module 602, a third determination module 603, and a control module 604, wherein:

a first determining module 601, configured to determine a predicted longitudinal speed sequence of a predicted time domain of the vehicle after the current time, where the predicted longitudinal speed sequence includes: predicted longitudinal velocity at each predicted time point.

A second determining module 602, configured to determine, for each predicted time point, longitudinal control parameter information of a model predictive controller of the vehicle at the predicted time point according to the predicted longitudinal speed at the predicted time point.

A third determining module 603, configured to determine a longitudinal control quantity sequence of a prediction time domain according to the longitudinal control parameter information, the longitudinal model in the model prediction controller, and the expected trajectory of the vehicle, where the longitudinal control quantity sequence includes: the vertical control amount at each predicted time point.

And the control module 604 is used for performing longitudinal control on automatic driving of the vehicle according to the longitudinal control quantity at the first predicted time point in the predicted time domain.

In one embodiment of the present disclosure, as shown in fig. 7, the longitudinal control apparatus 700 of the vehicle may include: a first determining module 701, a second determining module 702, a third determining module 703 and a control module 704, wherein the first determining module 701 may include: a first obtaining unit 7011, a second obtaining unit 7012, and a determining unit 7013.

It should be noted that, for a detailed description of the control module 704, reference may be made to the description of the control module 604 in fig. 6, and a description thereof is omitted here.

In an embodiment of the disclosure, the second determining module 702 is specifically configured to: determining a first penalty weight of a state quantity error of a model predictive controller of the vehicle at the prediction time point according to the predicted longitudinal speed at the prediction time point; acquiring second punishment weights preset for longitudinal control quantity at the prediction time points, wherein the second punishment weights at different prediction time points are the same; acquiring third punishment weights preset for control quantity increments at the prediction time points, wherein the third punishment weights at different prediction time points are the same; and generating longitudinal control parameter information of the model predictive controller of the vehicle at the prediction time point according to the first penalty weight, the second penalty weight and the third penalty weight.

In one embodiment of the present disclosure, in a case where the predicted longitudinal speed at the predicted time point is greater than or equal to zero, the penalty weight of the state quantity error at the predicted time point is greater than zero, and in a case where the predicted longitudinal speed at the predicted time point is less than zero, the penalty weight of the state quantity error at the predicted time point is equal to zero.

In one implementation of the present disclosure, the first determining module 701 includes:

a first obtaining unit 7011 is configured to obtain a current longitudinal speed of the vehicle at a current time.

Second obtaining unit 7012, configured to obtain a desired longitudinal acceleration sequence of the vehicle in the prediction time domain, where the desired longitudinal acceleration sequence includes: the desired longitudinal acceleration at each predicted point in time.

A determining unit 7013 configured to determine a predicted longitudinal speed sequence of the vehicle in a predicted time domain according to the current longitudinal speed and the expected longitudinal acceleration sequence

In an embodiment of the present disclosure, the determining unit 7013 is specifically configured to: aiming at the ith prediction time point, determining the predicted longitudinal speed at the ith prediction time point according to the expected longitudinal acceleration and the current longitudinal speed at the ith prediction time point, wherein the initial value of i is 1; adding 1 to i; and under the condition that i is less than or equal to N, determining the predicted longitudinal speed at the ith predicted time point according to the expected longitudinal acceleration at the ith predicted time point and the predicted longitudinal speed at the (i-1) th predicted time point, and turning to the step of adding 1 to i, wherein N is the total number of predicted time points in the predicted time domain.

In an embodiment of the present disclosure, the third determining module 703 is specifically configured to: determining longitudinal vehicle state parameters of the vehicle at the current moment, and determining initial longitudinal control quantity of the vehicle at each predicted time point; determining the predicted longitudinal vehicle state parameters at each predicted time point according to the longitudinal vehicle state parameters, the initial longitudinal control quantity at each predicted time point and the longitudinal model; constructing an objective function according to the predicted longitudinal vehicle state parameters at each predicted time point, the expected longitudinal vehicle state parameters at each predicted time point in the expected track and the longitudinal control parameter information; adjusting the initial longitudinal control quantity at each prediction time point according to the numerical value of the objective function to obtain the longitudinal control quantity at each prediction time point; and determining a longitudinal control quantity sequence according to the longitudinal control quantity at each predicted time point.

It should be noted that the explanation of the longitudinal direction control method for the vehicle is also applicable to the longitudinal direction control device for the vehicle in this embodiment, and the embodiment is not described again.

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

FIG. 8 illustrates a schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 8, the electronic device 800 may include a computing unit 801 that may perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The calculation unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.

A number of components in the device 800 are connected to the I/O interface 805, including: an input unit 806, such as a keyboard, a mouse, or the like; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, or the like; and a communication unit 809 such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

Computing unit 801 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 801 executes the respective methods and processes described above, such as the longitudinal control method of the vehicle. For example, in some embodiments, the longitudinal control method of the vehicle may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and/or installed onto device 800 via ROM 802 and/or communications unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the longitudinal control method of the vehicle described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the longitudinal control method of the vehicle in any other suitable manner (e.g., by means of firmware).

Various implementations of the devices and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), devices on a 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 that are executable and/or interpretable on a programmable device 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 device, at least one input device, and at least one output device.

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

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution apparatus, device, or apparatus. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor device, apparatus, 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 apparatus and techniques described herein may 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 apparatus and techniques described here can be implemented in a computing device 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 apparatus and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the device 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), the internet, and blockchain networks.

The computer device may include a client and a server. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server 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 as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may be a cloud server, a server of a distributed device, or a server combining a blockchain.

In one embodiment of the present disclosure, the present disclosure also provides an autonomous vehicle including the electronic device exemplified in fig. 8.

It should be noted that the electronic device is configured to execute the longitudinal control method of the vehicle according to the embodiment of the present disclosure. 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 disclosure may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

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

Claims

1. A longitudinal control method of a vehicle, comprising:

determining a predicted longitudinal speed sequence of the vehicle in a predicted time domain after a current time, wherein the predicted longitudinal speed sequence comprises: predicted longitudinal velocities at respective predicted time points;

for each prediction time point, determining longitudinal control parameter information of a model prediction controller of the vehicle at the prediction time point according to the predicted longitudinal speed at the prediction time point;

determining a longitudinal control quantity sequence of the prediction time domain according to the longitudinal control parameter information, a longitudinal model in the model predictive controller and the expected track of the vehicle, wherein the longitudinal control quantity sequence comprises: longitudinal control amounts at respective predicted time points;

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

2. The method of claim 1, wherein said determining longitudinal control parameter information of a model predictive controller of the vehicle at the predicted time point based on the predicted longitudinal speed at the predicted time point comprises:

determining a first penalty weight of a state quantity error of a model predictive controller of the vehicle at the prediction time point according to the predicted longitudinal speed at the prediction time point;

acquiring second penalty weights preset for the longitudinal control quantity at the prediction time point, wherein the second penalty weights at different prediction time points are the same;

acquiring third penalty weights preset for control quantity increments at the prediction time points, wherein the third penalty weights at different prediction time points are the same;

and generating longitudinal control parameter information of the model predictive controller of the vehicle at the predictive time point according to the first penalty weight, the second penalty weight and the third penalty weight.

3. The method according to claim 1 or 2, wherein in the case where the predicted longitudinal speed at the predicted time point is greater than or equal to zero, the penalty weight for the state quantity error at the predicted time point is greater than zero, and in the case where the predicted longitudinal speed at the predicted time point is less than zero, the penalty weight for the state quantity error at the predicted time point is equal to zero.

4. The method of claim 1, wherein the determining a predicted longitudinal speed sequence for a predicted time domain of the vehicle after a current time comprises:

acquiring the current longitudinal speed of the vehicle at the current moment;

acquiring a desired longitudinal acceleration sequence of the vehicle in the prediction time domain, wherein the desired longitudinal acceleration sequence comprises: a desired longitudinal acceleration at each of the predicted time points;

and determining a predicted longitudinal speed sequence of the vehicle in the prediction time domain according to the current longitudinal speed and the expected longitudinal acceleration sequence.

5. The method of claim 4, wherein said determining a predicted sequence of longitudinal velocities of the vehicle within the prediction time domain from the current longitudinal velocity and the desired sequence of longitudinal accelerations comprises:

for an ith prediction time point, determining a predicted longitudinal speed at the ith prediction time point according to the expected longitudinal acceleration and the current longitudinal speed at the ith prediction time point, wherein the initial value of i is 1;

performing plus 1 processing on the i;

and under the condition that i is less than or equal to N, determining the predicted longitudinal speed at the ith predicted time point according to the expected longitudinal acceleration at the ith predicted time point and the predicted longitudinal speed at the (i-1) th predicted time point, and turning to the step of adding 1 to i, wherein N is the total number of the predicted time points in the predicted time domain.

6. The method of claim 1, wherein said determining a sequence of longitudinal control quantities in the prediction horizon from the longitudinal control parameter information, a longitudinal model in the model predictive controller, and a desired trajectory of the vehicle comprises:

determining longitudinal vehicle state parameters of the vehicle at the current moment, and determining initial longitudinal control quantity of the vehicle at each predicted time point;

determining the predicted longitudinal vehicle state parameters at each predicted time point according to the longitudinal vehicle state parameters, the initial longitudinal control quantity at each predicted time point and the longitudinal model;

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

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

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

7. A longitudinal control apparatus of a vehicle, comprising:

a first determination module configured to determine a predicted longitudinal speed sequence of the vehicle in a predicted time domain after a current time, wherein the predicted longitudinal speed sequence comprises: predicted longitudinal velocities at respective predicted time points;

a second determination module, configured to determine, for each of the predicted time points, longitudinal control parameter information of a model predictive controller of the vehicle at the predicted time point according to a predicted longitudinal speed at the predicted time point;

a third determining module, configured to determine a longitudinal control quantity sequence of the prediction time domain according to the longitudinal control parameter information, a longitudinal model in the model predictive controller, and a desired trajectory of the vehicle, where the longitudinal control quantity sequence includes: longitudinal control amounts at respective predicted time points;

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

8. The apparatus of claim 7, wherein the second determining module is specifically configured to:

acquiring a third penalty weight preset for the control quantity increment at the prediction time point, wherein the third penalty weights at different prediction time points are the same;

9. The apparatus according to claim 7 or 8, wherein in the case where the predicted longitudinal speed at the predicted time point is greater than or equal to zero, the penalty weight of the state quantity error at the predicted time point is greater than zero, and in the case where the predicted longitudinal speed at the predicted time point is less than zero, the penalty weight of the state quantity error at the predicted time point is equal to zero.

10. The apparatus of claim 7, wherein the first determining means comprises:

a first acquisition unit configured to acquire a current longitudinal speed of the vehicle at the current time;

a second obtaining unit configured to obtain a desired longitudinal acceleration sequence of the vehicle within the prediction time domain, wherein the desired longitudinal acceleration sequence includes: a desired longitudinal acceleration at each of the predicted time points;

a determining unit configured to determine a predicted longitudinal velocity sequence of the vehicle within the prediction time domain according to the current longitudinal velocity and the expected longitudinal acceleration sequence.

11. The apparatus according to claim 10, wherein the determining unit is specifically configured to:

performing plus 1 processing on the i;

12. The apparatus of claim 7, wherein the third determining module is specifically configured to:

13. An electronic device, comprising:

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 any one of claims 1-6.

14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-6.

15. A computer program product comprising a computer program which, when executed by a processor, carries out the steps of the method of any one of claims 1-6.

16. An autonomous vehicle comprising: the electronic device of claim 13.