WO2022218036A1 - Vehicle control method and apparatus, storage medium, electronic device and vehicle - Google Patents

Abstract

A vehicle control method, a vehicle control apparatus (30), a storage medium, an electronic device (700, 1900) and a vehicle, so as to optimize the planning of a vehicle traveling trajectory and improve the performance of autonomous driving. The vehicle control method comprises: during a vehicle traveling process, acquiring a planned trajectory sequence and a vehicle state matrix of a vehicle that correspond to a first control moment (11), wherein the planned trajectory sequence is obtained on the basis of an artificial potential field planning algorithm, and the vehicle state matrix is obtained on the basis of a vehicle dynamics model; according to the planned trajectory sequence and the vehicle state matrix, constructing an objective function taking a control sequence as an argument (12), wherein the objective function carries a target constraint condition for the control sequence; performing secondary planning processing on the objective function, so as to obtain a target control sequence capable of minimizing the function value of the objective function and meeting the target constraint condition (13); and after the first control moment, controlling the vehicle according to the target control sequence (14).

Description

Vehicle control method, device, storage medium, electronic device, and vehicle

CROSS-REFERENCE TO RELATED APPLICATIONS

This application is based on the Chinese patent application with the application number of 202110402428.9 and the filing date of April 14, 2021, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is incorporated herein by reference.

technical field

The present disclosure relates to the field of vehicles, and in particular, to a vehicle control method, device, storage medium, electronic device, and vehicle.

Background technique

At present, the artificial potential field method is generally used for automatic driving path planning, but in the process of constructing the artificial potential field, although the field surface can be smoothed, the planned trajectory usually cannot meet the needs of automatic driving trajectory smoothness and vehicle control smoothness. That is, the trajectory obtained by planning exceeds the range of vehicle tracking, which is a hidden danger in autonomous driving scenarios. It will not only make the vehicle's automatic control unstable, such as shaking, but also easily cause the vehicle to emit dangerous autonomous behaviors, which cannot guarantee driving safety.

SUMMARY OF THE INVENTION

The purpose of the present disclosure is to provide a vehicle control method, device, storage medium, electronic device and vehicle, so as to optimize the planning of the vehicle's driving trajectory and improve the automatic driving performance.

In order to achieve the above object, according to a first aspect of the present disclosure, a vehicle control method is provided, the method comprising:

During the driving of the vehicle, a planned trajectory sequence and a vehicle state matrix of the vehicle corresponding to the first control moment are obtained, the planned trajectory sequence is obtained based on an artificial potential field planning algorithm, and the vehicle state matrix is obtained based on a vehicle dynamics model;

According to the planned trajectory sequence and the vehicle state matrix, construct an objective function with a control sequence as an independent variable, and the objective function has objective constraints for the control sequence;

performing quadratic programming processing on the objective function to obtain an objective control sequence that can minimize the function value of the objective function and satisfy the objective constraint condition;

After the first control time, the vehicle is controlled according to the target control sequence.

Optionally, the planned trajectory sequence includes planned positions obtained by planning for each control moment in the discrete time sequence, the discrete time sequence includes a specified number of control moments starting from the second control moment, and the second The control time is the next control time after the first control time.

Optionally, the planned trajectory sequence is obtained by:

acquiring environmental information around the vehicle, where the environmental information at least includes obstacle information;

constructing an artificial potential field according to the environmental information;

Taking the position of the vehicle at the first control moment as the starting point, and taking the target position as the end point, according to the attraction and repulsion at each position in the artificial potential field, the artificial potential field planning algorithm is used to sequentially target the The planned positions are generated at each control instant in the discrete time series to obtain the planned trajectory sequence.

Optionally, the vehicle state matrix includes vehicle state information predicted for each control moment in a discrete time series, the discrete time series includes a specified number of control moments starting from the second control moment, and the first The second control time is the next control time of the first control time.

Optionally, the vehicle state matrix is obtained by:

Obtain the vehicle state information of the vehicle during the historical driving process as the historical vehicle state;

According to the historical vehicle state, the vehicle state information of the vehicle at each control moment in the discrete time series is predicted by using a vehicle dynamics model, so as to obtain the vehicle state matrix.

Optionally, the vehicle state information includes vehicle position information, vehicle heading information and vehicle speed information.

Optionally, the target constraints include at least one of the following:

The steering wheel angle of the vehicle is within the preset angle range;

The rotation rate of the steering wheel of the vehicle is within the first preset rate interval;

The vehicle acceleration is within the preset acceleration range;

The rate of change of the vehicle acceleration is within the second preset rate interval.

Optionally, the control sequence includes control parameters for each control moment in the discrete time sequence, the discrete time sequence includes a specified number of control moments starting from a second control moment, and the second control moment is The next control time of the first control time.

Optionally, construct the objective function J(U) according to the following formula:

J(U)=(XR) ^T Q(XR)+U ^T WU

Umin≤U≤Umax

ΔUmin≤ΔU≤ΔUmax

Wherein, X is the vehicle state matrix, R is the planned trajectory sequence, U is the control sequence, Q is the first preset weight matrix, W is the second preset weight matrix, Umin≤U≤Umax and ΔUmin ≤ΔU≤ΔUmax is the target constraint condition, where the Umin is the lower control limit of the control parameter, the Umax is the upper control limit of the control parameter, and the ΔU is the control parameter before the adjacent one. , the parameter change amount between the last two control moments, the ΔUmin is the lower limit of the change of the control parameter between the adjacent two control moments, and the ΔUmax is the control parameter in the adjacent front, The upper limit of change between the last two control moments.

Optionally, the control parameters include a first control parameter for the steering wheel angle and/or a second control parameter for the accelerator pedal.

Optionally, the target control sequence includes target control parameters corresponding to a second control moment, and the second control moment is the next control moment of the first control moment;

The controlling the vehicle according to the target control sequence after the first control time includes:

At the second control time, the vehicle is controlled according to the target control parameter.

According to a second aspect of the present disclosure, there is provided a vehicle control device comprising:

an acquisition module, configured to acquire a planned trajectory sequence and a vehicle state matrix of the vehicle corresponding to the first control moment during the driving process of the vehicle, the planned trajectory sequence is obtained based on an artificial potential field planning algorithm, and the vehicle state matrix is based on the vehicle Kinetic model acquisition;

a function construction module, configured to construct an objective function with a control sequence as an independent variable according to the planned trajectory sequence and the vehicle state matrix, and the objective function has objective constraints for the control sequence;

a processing module, configured to perform quadratic programming processing on the objective function, so as to obtain an objective control sequence that can minimize the function value of the objective function and satisfy the objective constraint condition;

and a control module, configured to control the vehicle according to the target control sequence after the first control time.

Optionally, the planned trajectory sequence includes planned positions obtained by planning for each control moment in the discrete time sequence, the discrete time sequence includes a specified number of control moments starting from the second control moment, and the second The control time is the next control time after the first control time.

Optionally, the planned trajectory sequence is obtained by:

acquiring environmental information around the vehicle, where the environmental information at least includes obstacle information;

constructing an artificial potential field according to the environmental information;

Taking the position of the vehicle at the first control moment as the starting point, and taking the target position as the end point, according to the attraction and repulsion at each position in the artificial potential field, the artificial potential field planning algorithm is used to sequentially target the The planned positions are generated at each control instant in the discrete time series to obtain the planned trajectory sequence.

Optionally, the vehicle state matrix includes vehicle state information predicted for each control moment in a discrete time series, the discrete time series includes a specified number of control moments starting from the second control moment, and the first The second control time is the next control time of the first control time.

Optionally, the vehicle state matrix is obtained by:

Obtain the vehicle state information of the vehicle during the historical driving process as the historical vehicle state;

According to the historical vehicle state, the vehicle state information of the vehicle at each control moment in the discrete time series is predicted by using a vehicle dynamics model, so as to obtain the vehicle state matrix.

Optionally, the vehicle state information includes vehicle position information, vehicle heading information and vehicle speed information.

Optionally, the target constraints include at least one of the following:

The steering wheel angle of the vehicle is within the preset angle range;

The rotation rate of the steering wheel of the vehicle is within the first preset rate interval;

The vehicle acceleration is within the preset acceleration range;

The rate of change of the vehicle acceleration is within the second preset rate interval.

Optionally, the control sequence includes control parameters for each control moment in the discrete time sequence, the discrete time sequence includes a specified number of control moments starting from a second control moment, and the second control moment is The next control time of the first control time.

Optionally, construct the objective function J(U) according to the following formula:

J(U)=(XR) ^T Q(XR)+U ^T WU

Umin≤U≤Umax

ΔUmin≤ΔU≤ΔUmax

Wherein, X is the vehicle state matrix, R is the planned trajectory sequence, U is the control sequence, Q is the first preset weight matrix, W is the second preset weight matrix, Umin≤U≤Umax and ΔUmin ≤ΔU≤ΔUmax is the target constraint condition, where the Umin is the lower control limit of the control parameter, the Umax is the upper control limit of the control parameter, and the ΔU is the control parameter before the adjacent one. , the parameter change amount between the last two control moments, the ΔUmin is the lower limit of the change of the control parameter between the adjacent two control moments, and the ΔUmax is the control parameter in the adjacent front, The upper limit of change between the last two control moments.

Optionally, the control parameters include a first control parameter for the steering wheel angle and/or a second control parameter for the accelerator pedal.

Optionally, the target control sequence includes target control parameters corresponding to a second control moment, and the second control moment is the next control moment of the first control moment;

The control module is configured to control the vehicle according to the target control parameter at the second control moment.

According to a third aspect of the present disclosure, there is provided a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the steps of the method described in the first aspect of the present disclosure.

According to a fourth aspect of the present disclosure, there is provided an electronic device, comprising:

a memory on which a computer program is stored;

A processor for executing the computer program in the memory to implement the steps of the method in the first aspect of the present disclosure.

According to a fifth aspect of the present disclosure, there is provided a vehicle, the vehicle comprising: an environment perception component, a domain controller, and an actuator;

The environment perception component is used for acquiring environment information around the vehicle, and sending the environment information to the domain controller;

The domain controller is configured to execute the method described in the first aspect of the present disclosure, and send a control instruction to the executor;

The executor is used to execute the control instruction received from the domain controller.

Optionally, the environment perception component includes at least one of the following: a camera, a millimeter-wave radar, a lidar, and an ultrasonic radar.

Through the above technical solution, during the driving process of the vehicle, the planned trajectory sequence and the vehicle state matrix of the vehicle corresponding to the first control moment are obtained, wherein the planned trajectory sequence is preliminarily planned based on the artificial potential field planning algorithm, and then, according to the planned trajectory sequence and vehicle state matrix, construct an objective function with the control sequence as an independent variable and with objective constraints, and perform quadratic programming processing on the objective function to obtain the minimum function value of the objective function and satisfy the objective constraints. and control the vehicle according to the target control sequence after the first control time. Therefore, after the preliminary planning of the vehicle's driving trajectory based on the artificial potential field, the quadratic planning method is further used to optimize the preliminary planned trajectory, so that the advantages of the artificial potential field planning algorithm can be retained, and the advantages of the artificial potential field planning algorithm can be used. The characteristics of quadratic programming optimize the problem of insufficient smoothness in artificial potential field planning, while taking into account the driving comfort, and overall achieve the effect of improving automatic driving performance.

Other features and advantages of the present disclosure will be described in detail in the detailed description that follows.

Description of drawings

The accompanying drawings are used to provide a further understanding of the present disclosure, and constitute a part of the specification, and together with the following detailed description, are used to explain the present disclosure, but not to limit the present disclosure. In the attached image:

FIG. 1 is a flowchart of a vehicle control method provided according to an embodiment of the present disclosure;

2 is a schematic diagram of generating a planning trajectory sequence based on an artificial potential field planning algorithm;

3 is a block diagram of a vehicle control device provided according to an embodiment of the present disclosure;

4 is a block diagram of an electronic device according to an exemplary embodiment;

Fig. 5 is a block diagram of an electronic device according to an exemplary embodiment.

Detailed ways

The specific embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, but not to limit the present disclosure.

FIG. 1 is a flowchart of a vehicle control method provided according to an embodiment of the present disclosure. As shown in FIG. 1 , the vehicle control method may include the following steps 11 to 14 .

In step 11, during the running process of the vehicle, the planned trajectory sequence and the vehicle state matrix of the vehicle corresponding to the first control moment are obtained.

In the present disclosure, the first control moment represents the current control moment, and the purpose of the present disclosure is to plan the subsequent planning trajectory sequence according to the artificial potential field planning algorithm at the current control moment (ie, the first control moment), and based on Plan the trajectory sequence, use the mathematical method of quadratic programming to further optimize the trajectory, in order to obtain a smoother and more comfortable planning result, and control the driving of the vehicle through the control sequence to make the actual driving trajectory of the vehicle as much as possible. Fit the optimized planning results. Here, the subsequent control of the vehicle actually includes at least the control of the next control time at the first control time. When the next control time is reached subsequently, the next control time becomes the current control time, and the next control time will continue to be used as the new first control time, and a series of steps provided by the present disclosure will be re-executed. Therefore, with the method provided by the present disclosure, an optimal solution suitable for the current vehicle condition can be planned in real time according to the current vehicle condition, and the overall performance of the vehicle in automatic driving can be improved.

Referring to the above idea, the planned trajectory sequence may include planned positions obtained by planning for each control moment in the discrete time sequence. Wherein, the discrete time series includes a specified number of control times starting from the second control time, and the second control time is the next control time after the first control time.

Illustratively, the planned trajectory sequence may be obtained based on an artificial potential field planning algorithm. Based on the artificial potential field planning algorithm, the planned trajectory sequence can be obtained in the following ways:

Obtain environmental information around the vehicle;

According to the environmental information, construct an artificial potential field;

Taking the position of the vehicle at the first control moment as the starting point and the target position as the end point, according to the attraction and repulsion at each position in the artificial potential field, the artificial potential field planning algorithm is used to sequentially target each control moment in the discrete time series. Generate planning positions to obtain a sequence of planning trajectories.

The environment information may include various information that can reflect the surrounding environment of the vehicle, for example, information related to the road the vehicle travels on, information about other vehicles around the vehicle, and information about obstacles around the vehicle. It should be noted that, since vehicle obstacle avoidance is the most basic condition to ensure vehicle safety, the environmental information should at least include obstacle information.

For example, an environment perception component may be provided on the vehicle, and the above-mentioned environment information is acquired through the environment perception component. The environment perception component may be composed of sensors, for example, the environment perception component may include, but is not limited to, at least one of the following: a camera, a millimeter-wave radar, a lidar, and an ultrasonic radar.

After the environmental information is acquired, according to the environmental information, an artificial potential field corresponding to the current environment can be constructed based on a commonly used artificial potential field construction method. The artificial potential field includes a gravitational field and a repulsive force field. The destination the vehicle is about to reach has a gravitational force on the vehicle, which guides the vehicle to move toward it (similar to the heuristic function in the A* algorithm), and the obstacle repulses the vehicle to prevent the vehicle from happening with it. Collision, the artificial potential field can be constructed based on the above ideas. While completing the construction of the artificial potential field, based on the idea that the resultant force experienced by the vehicle at each position on the artificial potential field is equal to the sum of all repulsive and gravitational forces at that position, the resultant force experienced by the vehicle at each position in the artificial potential field Also knowable. For example, the schematic diagram of the constructed artificial potential field can be shown in Figure 2, in which the gravitational force and the repulsive force are represented by the gradient of color. The repulsion force is the largest, the end point of the vehicle should have the largest gravitational force, and the obstacle repulsion force should also be large. In Figure 2, position A is used to represent the starting point (the largest repulsion force), and position B is used to represent the end point that the vehicle expects to reach (the largest gravitational force), including 4 a circular obstacle (see the four circular areas in Figure 2). It should be noted that the multiple black dots (small circles) between position A and position B in the figure represent trajectory points, not the composition of the force field.

Based on the constructed artificial potential field, take the current position of the vehicle (that is, the position at the first control moment) as the starting point, and take the target position as the end point, according to the attraction and repulsion at each position in the artificial potential field, use The artificial potential field planning algorithm sequentially generates planned positions for each control moment in the discrete time series to obtain the planned trajectory sequence. According to the potential field constructed above, a shortest path that can reach the end point can be determined, and each control moment in the discrete time sequence in the path has a corresponding planned position point. Illustratively, the generated planned trajectory sequence can be represented by a set of black dots between position A and position B in FIG. 2 .

In the process of obtaining the planned trajectory sequence, it can be considered that a control parameter for the current control moment is simulated based on the current position of the vehicle. It is assumed that after using the control parameter for control at the current control moment, the vehicle should reach a new location at the next control moment. position, if the new position is close to the black area, the new control parameters at the next control moment should be set based on the idea of making the vehicle as close to the white area as possible at the next control moment, and so on and so forth, you can obtain When planning the trajectory sequence, at the same time, a series of control parameters (corresponding to each control moment in the discrete time series) that can obtain the planned trajectory sequence will also be obtained together. Wherein, the control parameter represents a parameter capable of changing the driving state of the vehicle, and may include, for example, a control parameter for the steering wheel angle and/or a control parameter for the accelerator pedal.

Similar to the planned trajectory sequence, the vehicle state matrix may include vehicle state information predicted for each control moment in the discrete time series.

Illustratively, the vehicle state matrix may be obtained based on a vehicle dynamics model. Based on the vehicle kinematics model, the vehicle state matrix can be obtained in the following ways:

Obtain the vehicle status information of the vehicle during the historical driving process as the historical vehicle status;

According to the historical vehicle state, the vehicle dynamic model is used to predict the vehicle state information of the vehicle at each control moment in the discrete time series to obtain the vehicle state matrix.

As described above, while generating the planned trajectory sequence, a series of control parameters that can obtain the planned trajectory sequence can be obtained at the same time. The vehicle dynamics model can predict the vehicle state information of the vehicle at the next control time based on the vehicle state information of the vehicle at a certain control time and before this time and the control parameters for this control time.

For example, the historical vehicle state may include vehicle state information at the first control moment. For another example, in addition to the vehicle state information at the first control time, the historical vehicle state may also include vehicle state information at several control times before the first control time.

Based on the above functions of the vehicle dynamics model, according to the historical vehicle state and a series of control parameters that can obtain the planned trajectory sequence, the vehicle state information predicted for each control moment in the discrete time series can be obtained to form a vehicle state matrix. .

The vehicle state information may include vehicle position information, vehicle heading information, and vehicle speed information. Besides, the vehicle state information may also include change information of the above-mentioned information, for example, position change, derivative of position change, heading change, vehicle speed change, and the like.

Referring to Fig. 1, in step 12, an objective function with the control sequence as an independent variable is constructed according to the planned trajectory sequence and the vehicle state matrix.

Among them, the objective function has objective constraints on the control sequence.

Illustratively, the objective constraints may include, but are not limited to, at least one of the following:

The steering wheel angle of the vehicle is within the preset angle range;

The rotation rate of the steering wheel of the vehicle is within the first preset rate interval;

The vehicle acceleration is within the preset acceleration range;

The rate of change of the vehicle acceleration is within the second preset rate interval.

In the process of controlling the vehicle, it is not only necessary to consider the optimality of the vehicle's trajectory planning, but also the user's actual riding experience, and the user's comfort during the ride should be guaranteed. Therefore, it is necessary to turn the vehicle and accelerate Constraints are set in terms of aspects to avoid the occurrence of too fast changes in steering and acceleration.

For example, the objective function J(U) can be constructed according to the following formula:

J(U)=(XR) ^T Q(XR)+U ^T WU

Umin≤U≤Umax

ΔUmin≤ΔU≤ΔUmax

Among them, X is the vehicle state matrix, R is the planned trajectory sequence, U is the control sequence, Q is the first preset weight matrix, W is the second preset weight matrix, Umin≤U≤Umax and ΔUmin≤ΔU≤ΔUmax are the targets Constraints, where Umin is the control lower limit of the control parameter, Umax is the control upper limit of the control parameter, ΔU is the parameter change of the control parameter between the adjacent two control moments, and ΔUmin is the control parameter in the adjacent ΔUmax is the upper limit of the change of the control parameters between the two adjacent control moments before and after. Wherein, similar to the above-mentioned planned trajectory sequence and vehicle state matrix, the control sequence may include control parameters for each control moment in the discrete time sequence. By way of example, the control parameters include a first control parameter for the steering wheel angle and/or a second control parameter for the accelerator pedal.

In step 13, a quadratic programming process is performed on the objective function to obtain an objective control sequence that can minimize the function value of the objective function and satisfy objective constraints.

For example, quadratic programming processing can be performed on the objective function by methods such as effective set method and interior point method.

In step 14, after the first control time, the vehicle is controlled according to the target control sequence.

Wherein, the target control sequence includes target control parameters corresponding to the second control moment.

Illustratively, step 14 may include the following steps:

At the second control moment, the vehicle is controlled according to the target control parameter.

At the first control time, a target control sequence for the first control time is generated based on steps 11 to 13, and the target control sequence contains at least target control parameters corresponding to the second control time, so that when the second control time is reached, the The vehicle is controlled according to the target control parameters.

At the same time, since the second control time has become the current control time, the second control time in the current process can continue to be used as the first control time in the next process, and the above steps 11 to 14 are executed again, so as to , and can also generate new target control parameters for control at a new second control time, and so on and so forth, during the driving process of the vehicle, the subsequent control parameters are continuously revised to optimize the vehicle's driving trajectory.

Through the above technical solution, during the driving process of the vehicle, the planned trajectory sequence and the vehicle state matrix of the vehicle corresponding to the first control moment are obtained, wherein the planned trajectory sequence is preliminarily planned based on the artificial potential field planning algorithm, and then, according to the planned trajectory sequence and vehicle state matrix, construct an objective function with the control sequence as an independent variable and with objective constraints, and perform quadratic programming processing on the objective function to obtain the minimum function value of the objective function and satisfy the objective constraints. and control the vehicle according to the target control sequence after the first control time. Therefore, after the preliminary planning of the vehicle's driving trajectory based on the artificial potential field, the quadratic planning method is further used to optimize the preliminary planned trajectory, so that the advantages of the artificial potential field planning algorithm can be retained, and the advantages of the artificial potential field planning algorithm can be used. The characteristics of quadratic programming optimize the problem of insufficient smoothness in artificial potential field planning, while taking into account the driving comfort, and overall achieve the effect of improving automatic driving performance.

FIG. 3 is a block diagram of a vehicle control apparatus provided according to an embodiment of the present disclosure. As shown in Figure 3, the device 30 includes:

The obtaining module 31 is configured to obtain the planned trajectory sequence and the vehicle state matrix of the vehicle corresponding to the first control moment during the driving process of the vehicle, the planned trajectory sequence is obtained based on the artificial potential field planning algorithm, and the vehicle state matrix is obtained based on the vehicle dynamics model;

The function construction module 32 is used for constructing an objective function with the control sequence as an independent variable according to the planned trajectory sequence and the vehicle state matrix, and the objective function has objective constraints for the control sequence;

The processing module 33 is used to perform quadratic programming processing on the objective function, so as to obtain an objective control sequence that can minimize the function value of the objective function and satisfy the objective constraint condition;

The control module 34 is configured to control the vehicle according to the target control sequence after the first control time.

Optionally, the planned trajectory sequence includes planned positions obtained by planning for each control time in the discrete time sequence, and the discrete time sequence includes a specified number of control times starting from the second control time, and the second control time is the first control time. The next control moment of the moment.

Optionally, the planned trajectory sequence is obtained by:

Obtain environmental information around the vehicle, which includes at least obstacle information;

According to the environmental information, construct an artificial potential field;

Taking the position of the vehicle at the first control moment as the starting point and the target position as the end point, according to the attraction and repulsion at each position in the artificial potential field, the artificial potential field planning algorithm is used to sequentially target each control moment in the discrete time series. Generate planning positions to obtain a sequence of planning trajectories.

Optionally, the vehicle state matrix includes vehicle state information predicted for each control moment in the discrete time series, the discrete time series includes a specified number of control moments starting from the second control moment, and the second control moment is the first control moment. The next control time of the control time.

Optionally, the vehicle state matrix is obtained by:

Obtain the vehicle status information of the vehicle during the historical driving process as the historical vehicle status;

According to the historical vehicle state, the vehicle dynamic model is used to predict the vehicle state information of the vehicle at each control moment in the discrete time series to obtain the vehicle state matrix.

Optionally, the vehicle state information includes vehicle position information, vehicle heading information and vehicle speed information.

Optionally, the objective constraints include at least one of the following:

The steering wheel angle of the vehicle is within the preset angle range;

The rotation rate of the steering wheel of the vehicle is within the first preset rate interval;

The vehicle acceleration is within the preset acceleration range;

The rate of change of the vehicle acceleration is within the second preset rate interval.

Optionally, the control sequence includes control parameters for each control moment in the discrete time sequence, the discrete time sequence includes a specified number of control moments starting from the second control moment, and the second control moment is the next time the first control moment. A moment of control.

Optionally, construct the objective function J(U) according to the following formula:

J(U)=(XR) ^T Q(XR)+U ^T WU

Umin≤U≤Umax

ΔUmin≤ΔU≤ΔUmax

Among them, X is the vehicle state matrix, R is the planned trajectory sequence, U is the control sequence, Q is the first preset weight matrix, W is the second preset weight matrix, Umin≤U≤Umax and ΔUmin≤ΔU≤ΔUmax are the targets Constraints, where Umin is the control lower limit of the control parameter, Umax is the control upper limit of the control parameter, ΔU is the parameter change of the control parameter between the adjacent two control moments, and ΔUmin is the control parameter in the adjacent ΔUmax is the upper limit of the change of the control parameters between the two adjacent control moments before and after.

Optionally, the control parameters include a first control parameter for the steering wheel angle and/or a second control parameter for the accelerator pedal.

Optionally, the target control sequence includes target control parameters corresponding to the second control moment, and the second control moment is the next control moment of the first control moment;

The control module 34 is configured to control the vehicle according to the target control parameter at the second control moment.

Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.

The present disclosure also provides a vehicle including: an environment perception component, a domain controller, and an actuator;

The environment perception component is used to obtain the environment information around the vehicle and send the environment information to the domain controller;

The domain controller is configured to execute the vehicle control method of any embodiment of the present disclosure, and send a control instruction to the actuator;

The executor is used to execute the control instructions received from the domain controller.

For example, the environment perception component may include at least one of the following: a camera, a millimeter-wave radar, a lidar, and an ultrasonic radar.

FIG. 4 is a block diagram of an electronic device 700 according to an exemplary embodiment. As shown in FIG. 4 , the electronic device 700 may include: a processor 701 and a memory 702 . The electronic device 700 may also include one or more of a multimedia component 703 , an input/output (I/O) interface 704 , and a communication component 705 .

Wherein, the processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned vehicle control method. The memory 702 is used to store various types of data to support operations on the electronic device 700, such data may include, for example, instructions for any application or method operating on the electronic device 700, and application-related data, Such as contact data, messages sent and received, pictures, audio, video, and so on. The memory 702 can be implemented by any type of volatile or non-volatile storage device or their combination, such as static random access memory (Static Random Access Memory, SRAM for short), electrically erasable programmable read-only memory ( Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (Read-Only Memory, ROM for short), magnetic memory, flash memory, magnetic disk or optical disk. Multimedia components 703 may include screen and audio components. Wherein the screen can be, for example, a touch screen, and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in memory 702 or transmitted through communication component 705 . The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 704 provides an interface between the processor 701 and other interface modules, and the above-mentioned other interface modules may be a keyboard, a mouse, a button, and the like. These buttons can be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or more of them The combination is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module and so on.

In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), digital signal processors (Digital Signal Processor, DSP for short), digital signal processing devices (Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic components The implementation is used to execute the above-mentioned vehicle control method.

In another exemplary embodiment, there is also provided a computer-readable storage medium including program instructions, the program instructions implementing the steps of the above-mentioned vehicle control method when executed by a processor. For example, the computer-readable storage medium can be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to complete the above-mentioned vehicle control method.

FIG. 5 is a block diagram of an electronic device 1900 according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. 5 , the electronic device 1900 includes a processor 1922 , which may be one or more in number, and a memory 1932 for storing computer programs executable by the processor 1922 . A computer program stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor 1922 may be configured to execute the computer program to perform the vehicle control method described above.

In addition, the electronic device 1900 may also include a power supply assembly 1926, which may be configured to perform power management of the electronic device 1900, and a communication component 1950, which may be configured to enable communication of the electronic device 1900, eg, wired or wireless communication. Additionally, the electronic device 1900 may also include an input/output (I/O) interface 1958 . Electronic device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server ^™ , Mac OS X ^™ , Unix ^™ , Linux ^™ , and the like.

In another exemplary embodiment, there is also provided a computer-readable storage medium including program instructions, the program instructions implementing the steps of the above-mentioned vehicle control method when executed by a processor. For example, the computer-readable storage medium can be the above-mentioned memory 1932 including program instructions, and the above-mentioned program instructions can be executed by the processor 1922 of the electronic device 1900 to implement the above-mentioned vehicle control method.

In another exemplary embodiment, there is also provided a computer program product comprising a computer program executable by a programmable apparatus, the computer program having, when executed by the programmable apparatus, for performing the above The code section of the vehicle control method.

The preferred embodiments of the present disclosure have been described above in detail with reference to the accompanying drawings. However, the present disclosure is not limited to the specific details of the above-mentioned embodiments. Various simple modifications can be made to the technical solutions of the present disclosure within the scope of the technical concept of the present disclosure. These simple modifications all fall within the protection scope of the present disclosure.

In addition, it should be noted that each specific technical feature described in the above-mentioned specific implementation manner may be combined in any suitable manner under the circumstance that there is no contradiction. In order to avoid unnecessary repetition, various possible combinations are not described in the present disclosure.

In addition, the various embodiments of the present disclosure can also be arbitrarily combined, as long as they do not violate the spirit of the present disclosure, they should also be regarded as the contents disclosed in the present disclosure.

Claims (16)

1. A vehicle control method, characterized in that the method comprises:

   During the driving of the vehicle, a planned trajectory sequence and a vehicle state matrix of the vehicle corresponding to the first control moment are obtained, the planned trajectory sequence is obtained based on an artificial potential field planning algorithm, and the vehicle state matrix is obtained based on a vehicle dynamics model;

   According to the planned trajectory sequence and the vehicle state matrix, construct an objective function with a control sequence as an independent variable, and the objective function has objective constraints for the control sequence;

   performing quadratic programming processing on the objective function to obtain an objective control sequence that can minimize the function value of the objective function and satisfy the objective constraint condition;

   After the first control time, the vehicle is controlled according to the target control sequence.
2. The method according to claim 1, wherein the planned trajectory sequence comprises planned positions obtained by planning for each control moment in the discrete time series, and the discrete time series comprises a specified number of times starting from the second control moment and the second control time is the next control time of the first control time.
3. The method according to claim 2, wherein the planned trajectory sequence is obtained by:

   acquiring environmental information around the vehicle, where the environmental information at least includes obstacle information;

   constructing an artificial potential field according to the environmental information;

   Taking the position of the vehicle at the first control moment as the starting point, and taking the target position as the end point, according to the attraction and repulsion at each position in the artificial potential field, the artificial potential field planning algorithm is used to sequentially target the The planned positions are generated at each control instant in the discrete time series to obtain the planned trajectory sequence.
4. The method according to claim 1, wherein the vehicle state matrix includes vehicle state information predicted for each control moment in a discrete time series, and the discrete time series includes a specified time starting point at the second control moment and the second control time is the next control time of the first control time.
5. The method according to claim 4, wherein the vehicle state matrix is obtained by:

   Obtain the vehicle state information of the vehicle during the historical driving process as the historical vehicle state;

   According to the historical vehicle state, the vehicle state information of the vehicle at each control moment in the discrete time series is predicted by using a vehicle dynamics model, so as to obtain the vehicle state matrix.
6. The method of claim 4, wherein the vehicle state information includes vehicle position information, vehicle heading information, and vehicle speed information.
7. The method according to claim 1, wherein the target constraints include at least one of the following:

   The steering wheel angle of the vehicle is within the preset angle range;

   The rotation rate of the steering wheel of the vehicle is within the first preset rate interval;

   The vehicle acceleration is within the preset acceleration range;

   The rate of change of the vehicle acceleration is within the second preset rate interval.
8. The method according to claim 1, wherein the control sequence includes control parameters for each control moment in the discrete time series, and the discrete time series includes a specified number of control moments starting from the second control moment , and the second control time is the next control time of the first control time.
9. The method according to claim 8, wherein the objective function J(U) is constructed according to the following formula:

   J(U)=(XR) ^T Q(XR)+U ^T WU

   Umin≤U≤Umax

   ΔUmin≤ΔU≤ΔUmax

   Wherein, X is the vehicle state matrix, R is the planned trajectory sequence, U is the control sequence, Q is the first preset weight matrix, W is the second preset weight matrix, Umin≤U≤Umax and ΔUmin ≤ΔU≤ΔUmax is the target constraint condition, where the Umin is the lower control limit of the control parameter, the Umax is the upper control limit of the control parameter, and the ΔU is the control parameter before the adjacent one. , the parameter change amount between the last two control moments, the ΔUmin is the lower limit of the change of the control parameter between the adjacent two control moments, and the ΔUmax is the control parameter in the adjacent front, The upper limit of change between the last two control moments.
10. The method according to claim 8, wherein the control parameters include a first control parameter for steering wheel angle and/or a second control parameter for accelerator pedal.
11. The method according to claim 1, wherein the target control sequence comprises a target control parameter corresponding to a second control moment, the second control moment being the next control moment of the first control moment;

    The controlling the vehicle according to the target control sequence after the first control time includes:

    At the second control time, the vehicle is controlled according to the target control parameter.
12. A vehicle control device, characterized in that the device comprises:

    an acquisition module, configured to acquire a planned trajectory sequence and a vehicle state matrix of the vehicle corresponding to the first control moment during the driving process of the vehicle, the planned trajectory sequence is obtained based on an artificial potential field planning algorithm, and the vehicle state matrix is based on the vehicle Kinetic model acquisition;

    a function construction module, configured to construct an objective function with a control sequence as an independent variable according to the planned trajectory sequence and the vehicle state matrix, and the objective function has objective constraints for the control sequence;

    a processing module, configured to perform quadratic programming processing on the objective function, so as to obtain an objective control sequence that can minimize the function value of the objective function and satisfy the objective constraint condition;

    and a control module, configured to control the vehicle according to the target control sequence after the first control time.
13. A computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the following steps are implemented:

    During the driving of the vehicle, a planned trajectory sequence and a vehicle state matrix of the vehicle corresponding to the first control moment are obtained, the planned trajectory sequence is obtained based on an artificial potential field planning algorithm, and the vehicle state matrix is obtained based on a vehicle dynamics model;

    According to the planned trajectory sequence and the vehicle state matrix, construct an objective function with a control sequence as an independent variable, and the objective function has objective constraints for the control sequence;

    Carrying out quadratic programming processing to the objective function to obtain the objective control sequence that can minimize the function value of the objective function and satisfy the objective constraint condition;

    After the first control time, the vehicle is controlled according to the target control sequence.
14. An electronic device, comprising:

    a memory on which a computer program is stored;

    A processor for executing the computer program in the memory to implement the following steps:

    During the driving of the vehicle, a planned trajectory sequence and a vehicle state matrix of the vehicle corresponding to the first control moment are obtained, the planned trajectory sequence is obtained based on an artificial potential field planning algorithm, and the vehicle state matrix is obtained based on a vehicle dynamics model;

    According to the planned trajectory sequence and the vehicle state matrix, construct an objective function with a control sequence as an independent variable, and the objective function has objective constraints for the control sequence;

    performing quadratic programming processing on the objective function to obtain an objective control sequence that can minimize the function value of the objective function and satisfy the objective constraint condition;

    After the first control time, the vehicle is controlled according to the target control sequence.
15. A vehicle, characterized in that the vehicle comprises: an environment perception component, a domain controller and an actuator;

    The environment perception component is used for acquiring environment information around the vehicle, and sending the environment information to the domain controller;

    The domain controller is used to perform the following steps:

    During the driving of the vehicle, a planned trajectory sequence and a vehicle state matrix of the vehicle corresponding to the first control moment are obtained, the planned trajectory sequence is obtained based on an artificial potential field planning algorithm, and the vehicle state matrix is obtained based on a vehicle dynamics model;

    According to the planned trajectory sequence and the vehicle state matrix, construct an objective function with a control sequence as an independent variable, and the objective function has objective constraints for the control sequence;

    Performing quadratic programming processing on the objective function to obtain an objective control sequence that can minimize the function value of the objective function and satisfy the objective constraint condition;

    After the first control time, the vehicle is controlled according to the target control sequence; and,

    sending a control command to the executor;

    The executor is used to execute the control instruction received from the domain controller.
16. The vehicle of claim 15, wherein the environment perception component comprises at least one of the following: a camera, a millimeter-wave radar, a lidar, and an ultrasonic radar.

Images