Vehicle control method, device, electronic device and storage medium

Abstract

The embodiment of the present invention discloses a vehicle control method, device, electronic device and storage medium. The method includes: obtaining vehicle status data and noise data corresponding to the target vehicle at the current moment; determining the vehicle control data at the next moment of the current moment based on the vehicle status data, noise data, and preset trajectory point information corresponding to the current moment; sending the vehicle control data to the controller of the target vehicle so that the target vehicle is controlled by the controller to follow the target planned trajectory. The problem of low vehicle control stability caused by the control of longitudinal speed based on PID control in the prior art is solved, and the vehicle control accuracy and stability are improved, the vehicle following error is reduced, and the safety of the vehicle's automatic driving is ensured.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer processing technology, and more particularly to a vehicle control method, device, electronic device and storage medium. Background Art

[0002] The problem of motion following navigation trajectory of autonomous vehicles has been a topic of increasing attention at home and abroad. Motion following control generally adopts the longitudinal PID control (Proportional-Integral-Derivative control) method. The error between the expected speed and the actual speed is obtained through the sensor signal, and the longitudinal speed is controlled through PID control. However, if there is a large acceleration expectation in both the longitudinal and lateral directions, the longitudinal speed is independently controlled based on this method, and the vehicle is at risk of instability, affecting the stability of the autonomous vehicle. Summary of the invention

[0003] The embodiments of the present invention provide a vehicle control method, device, electronic device and storage medium to improve the accuracy and stability of vehicle control while reducing the driving error of the vehicle following a target planned trajectory, thereby achieving the technical effect of ensuring the safety of vehicle autonomous driving.

[0004] In a first aspect, an embodiment of the present invention provides a vehicle control method, the method comprising:

[0005] Obtain vehicle status data and noise data corresponding to the target vehicle at the current moment;

[0006] Determining vehicle control data at a moment next to the current moment based on the vehicle state data, the noise data, and preset trajectory point information corresponding to the current moment, wherein the vehicle control data includes a longitudinal turning angle, a driving acceleration, and a braking deceleration;

[0007] The vehicle control data is sent to a controller of the target vehicle, so that the target vehicle is controlled by the controller to follow a target planned trajectory.

[0008] In a second aspect, an embodiment of the present invention further provides a vehicle control device, the device comprising:

[0009] A data acquisition module is used to obtain vehicle status data and noise data corresponding to the target vehicle at the current moment;

[0010] A vehicle control data determination module, configured to determine the vehicle control data at a moment next to the current moment based on the vehicle state data, the noise data, and the preset trajectory point information corresponding to the current moment, wherein the vehicle control data includes a longitudinal turning angle, a driving acceleration, and a braking deceleration;

[0011] The vehicle control data sending module is used to send the vehicle control data to the controller of the target vehicle, so that the target vehicle is controlled to follow the target planned trajectory based on the controller.

[0012] In a third aspect, an embodiment of the present invention further provides an electronic device, the device comprising:

[0013] one or more processors;

[0014] a storage device for storing one or more programs,

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle control method as described in any one of the embodiments of the present invention.

[0016] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a vehicle control method as described in any one of the embodiments of the present invention.

[0017] The technical solution of the embodiment of the present invention determines the longitudinal turning angle, driving acceleration and braking deceleration of the next moment after the current moment by acquiring the vehicle status data, noise data and preset trajectory point information corresponding to the target vehicle at the current moment; the longitudinal turning angle, driving acceleration and braking deceleration are sent to the controller of the target vehicle, so that the target vehicle is controlled by the controller to follow the target planned trajectory, which solves the problem of low vehicle control stability caused by longitudinal speed control based on PID control in the prior art, and realizes the determination of the longitudinal turning angle, driving acceleration and braking deceleration of the next moment after the current moment by performing processing on the vehicle status data, noise data and preset trajectory point information corresponding to the target vehicle at the current moment, so as to realize longitudinal and lateral comprehensive control of the vehicle based on the longitudinal turning angle, driving acceleration and braking deceleration, improve the vehicle control accuracy and stability, and reduce the vehicle following the target planned trajectory driving error, thereby achieving the technical effect of ensuring the safety of vehicle automatic driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required to describe the embodiments. Obviously, the drawings introduced are only drawings of a part of the embodiments to be described in the present invention, rather than all the drawings. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A flow chart of a vehicle control method provided in Embodiment 1 of the present invention;

[0020] Figure 2 A schematic diagram of the structure of a vehicle control device provided in Embodiment 2 of the present invention;

[0021] Figure 3 A schematic diagram of the structure of a longitudinal and lateral coupling controller module provided in the second embodiment of the present invention;

[0022] Figure 4 This is a structural block diagram of a vehicle control device provided by Embodiment 3 of the present invention;

[0023] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0025] Embodiment 1

[0026] Figure 1 This is a flow chart of a vehicle control method provided in the first embodiment of the present invention. This embodiment is applicable to the case of controlling the driving of a vehicle. The method can be executed by the vehicle control device in the embodiment of the present invention. The device can be implemented in software and / or hardware. Optionally, it can be implemented by an electronic device. The electronic device can be a mobile terminal, a PC or a server. The device can be configured in a computing device. The vehicle control method provided in this embodiment specifically includes the following steps:

[0027] S110, obtaining vehicle state data and noise data corresponding to the target vehicle at the current moment.

[0028] It should be noted that when the target vehicle follows the target planning trajectory, when it is necessary to obtain the vehicle state data and noise data at each moment in the driving process, the vehicle state data and noise data obtained at any moment can be processed as the vehicle state data and noise data obtained at the current moment, so as to illustrate one of the moments as the current moment. Among them, the target planning trajectory can be understood as the vehicle following trajectory. The vehicle state data may include but is not limited to longitude, latitude, altitude, heading angle, longitudinal speed, lateral speed, yaw angular velocity, acceleration, tire lateral stiffness and yaw moment of inertia. The noise data may include but is not limited to road slope and vehicle mass.

[0029] Specifically, in the process of the target vehicle following the target planning trajectory, the device module deployed on the target vehicle can be used to obtain the vehicle state data and noise data corresponding to the target vehicle at the current moment. For example, the vehicle chassis controller can be used to obtain the braking system feedback information (such as braking pressure, braking deceleration), steering system feedback information (such as steering angle, yaw angular velocity, yaw moment of inertia), and drive system feedback information (such as drive pressure, drive deceleration) at the current moment. The automatic driving perception positioning module can also be used to obtain the positioning information at the current moment. The positioning information may include longitude, latitude, altitude, heading angle, the road and lane where the vehicle is located, etc. The above information can be used as vehicle state data. The Kalman filter can be used to observe the longitudinal and lateral noise of the vehicle, such as the longitudinal and lateral road slopes, as noise data.

[0030] S120. Determine vehicle control data at a moment next to the current moment based on the vehicle state data, the noise data, and preset trajectory point information corresponding to the current moment.

[0031] In order to control the accuracy of the target vehicle following the target planning trajectory and to deal with the situation where the control is deviated at high speed, when obtaining the vehicle state data and noise data corresponding to the target vehicle at the current moment, the control information for controlling the target vehicle, i.e., the vehicle control data, can be obtained based on the processing of each data, wherein the vehicle control data includes the longitudinal turning angle, driving acceleration, and braking deceleration. The target planning trajectory includes several trajectory points, and the information of the trajectory points can be used as preset trajectory point information. Each preset trajectory point information can include global horizontal coordinate X, global vertical coordinate Y, curvature, heading angle, vehicle speed and other information. In practical applications, the preset trajectory point information can be understood as the state information expected to be achieved by the vehicle, and the vehicle state data is the data corresponding to the actual vehicle state.

[0032] Specifically, the trajectory planning module in the target vehicle can be used to obtain the preset trajectory point information corresponding to the current moment, and the data for lateral control of vehicle operation and longitudinal control of vehicle operation can be calculated through the error between the vehicle state data corresponding to the current moment and the preset trajectory point information reached by the expected vehicle state. The interference noise data can be taken into account during the calculation process to obtain the vehicle control data, so that in the process of controlling the vehicle driving based on the vehicle control data, the error between the actual driving state of the target vehicle and the expected vehicle state is extremely small, thereby improving the control accuracy.

[0033] It should be noted that in order to further ensure control accuracy, when the vehicle status data, noise data and preset trajectory point information corresponding to the current moment are obtained, an integrity check is performed on the vehicle status data, noise data and preset trajectory point information, so that when these data are not received, the usable data can be determined in time. For example, the vehicle status data, noise data and preset trajectory point information at the previous moment can be used as the data at the current moment, so as to determine the vehicle control data in time based on the usable data to prevent accidents caused by untimely control.

[0034] Optionally, based on the vehicle status data, noise data, and preset trajectory point information corresponding to the current moment, the vehicle control data for the next moment of the current moment is determined, including: traversing the vehicle status data, noise data and preset trajectory point information corresponding to the current moment to obtain a traversal result; if the traversal result is missing data, the vehicle control data of the moment before the current moment is used as the vehicle control data for the next moment of the current moment; or, if the traversal result is complete data, the vehicle control data is determined based on the vehicle status data, noise data and preset trajectory point information.

[0035] The traversal results include missing data and complete data. Missing data can be understood as at least one indicator item missing in the vehicle status data, noise data, or preset trajectory point information. The indicator item data may include but is not limited to the global horizontal coordinate X, the global vertical coordinate Y, curvature, heading angle, vehicle speed, longitudinal speed, lateral speed, yaw angular velocity, acceleration, tire cornering stiffness, yaw moment of inertia, and vehicle mass.

[0036] In practical applications, the vehicle status data, noise data, and preset track point information corresponding to the current moment can be received in parallel, and all the received information can be traversed to determine whether all the information has been received. If not, the traversal result is data missing. At this time, the vehicle control data of the moment before the current moment can be used as the vehicle control data of the next moment of the current moment, so as to send the vehicle control data to the controller to prevent accidents caused by untimely control. If not, the traversal result is data complete. At this time, the vehicle control data of the next moment of the current moment is determined based on the vehicle status data, noise data, and preset track point information of the current moment.

[0037] It should be noted that when the vehicle control data of the previous moment before the current moment is used as the vehicle control data of the next moment before the current moment, there is already a certain control error. In order to prevent the error from becoming larger and larger, the events of missing data can be counted. Correspondingly, the number of missing data is recorded as the traversal result. When the number of missing data accumulates to a certain threshold, an alarm can be triggered so that the target user can perform corresponding operations on the target vehicle in time based on the alarm, thereby reducing the occurrence of accidents and ensuring the safety of vehicle driving.

[0038] Optionally, if the traversal result corresponding to the current moment is missing data, the number of missing times of the traversal result is accumulated based on the historical cumulative times to obtain the target cumulative times; if the target cumulative times exceeds the preset times, a warning prompt message is generated and sent to the target display interface; when vehicle status data, noise data and preset trajectory point information different from the current moment are received again, and the traversal result is missing data, the target cumulative times are adjusted to the preset value and the historical cumulative times are updated.

[0039] The historical cumulative number can be used to characterize the cumulative number of missing data when the traversal result is missing data.

[0040] In practical applications, if the traversal result corresponding to the current moment is data missing, it can be considered that there is data missing for a certain indicator item, and the number of missing times can be recorded as 1, and the number of missing times can be accumulated on the basis of the historical cumulative times to obtain the accumulated historical cumulative times as the target cumulative times. When the target cumulative times exceed the preset times, an early warning prompt message can be generated and sent to the target display interface to timely remind the target user that a fault may have occurred during the process of the vehicle automatically following the target planning trajectory. For example, assuming that the preset times are 9, if the traversal result before the current moment is data missing for 9 consecutive times, when the traversal result corresponding to the current moment is data missing, the cumulative times at this time are 9+1=10, that is, the target cumulative times are 10, 10>9, then an early warning prompt message is generated, and the target cumulative times can be used as the historical cumulative times again. If the traversal result corresponding to the current moment is data complete, the historical cumulative times that have appeared 9 times in a row can be cleared, that is, 0 can be used as the new historical cumulative times. It can be understood that when the vehicle status data, noise data and preset trajectory point information different from the current moment are received again, and the traversal result is data missing, the target cumulative number can be adjusted to a preset value, and optionally, the preset value can be 0, and the preset value can be used as a new historical cumulative number. In this way, the missing number of missing data is subsequently accumulated based on the new historical cumulative number to obtain the target cumulative number. If the traversal result is that the data is complete, the historical cumulative number is still the preset value.

[0041] It should be noted that in order to control the target vehicle to travel with a very small error with the expected preset trajectory point information, when determining the vehicle control data for the next moment from the current moment based on the vehicle status data, noise data and preset trajectory point information at the current moment, error processing can be performed on the vehicle status data and the preset trajectory point information, and the error between the two can be calculated to control the target vehicle to move and follow in the direction of reducing the error, thereby improving the vehicle control accuracy and stability.

[0042] Optionally, based on the vehicle status data, noise data, and preset trajectory point information corresponding to the current moment, the vehicle control data for the next moment of the current moment is determined, including: determining the vehicle state deviation based on the vehicle status data and the preset trajectory point information; processing the vehicle state deviation, vehicle status data, noise data, and preset trajectory point information based on a preset cost function to obtain vehicle control data.

[0043] In practical applications, the errors between the vehicle state data and the various index items in the preset trajectory point information can be calculated, and the calculated errors of the index item data can be used as vehicle state deviations. For example, longitudinal speed deviation, lateral position deviation, heading angle deviation, etc. The vehicle state deviation, vehicle state data, noise data, and preset trajectory point information can be substituted into a preset cost function. When the cost function obtains the global optimal solution, it can be considered that the vehicle control data is obtained. For example, the cost function may include u=[δ f ,a] T And other parameters. Among them, x represents the vehicle state data vector, represents the longitudinal velocity deviation, v y represents the lateral velocity, r represents the yaw angular velocity, e y Indicates the lateral position deviation, e ψ represents the heading angle deviation. d represents the interference noise data vector, κ ref represents the curvature of the trajectory point, a ref represents the acceleration of the trajectory point, a xdis is the longitudinal disturbance acceleration, a ydis is the lateral disturbance acceleration, represents the yaw angular acceleration disturbance, etc. u represents the vehicle control data vector, δ f represents the longitudinal turning angle, a represents the driving acceleration or braking deceleration, and the cost function can also include: A, B, C, D, E, G matrices. At the same time, in order to prevent the cost function from being infinitely small, a penalty term can be added. It can be calculated by the following formula (1):

[0044]

[0045] Among them, xref Indicates the vehicle state data expected at the current moment, which includes the vehicle state deviation, u ref represents the vehicle control data expected at the next moment of the current moment, y ref represents the expected vehicle state output at the next moment of the current moment. d represents the noise data at the current moment, C is the unit matrix,

[0046]

[0047]

[0048] The D and G matrices are all zero matrices, m represents the vehicle mass, I z represents the yaw moment of inertia, represents the longitudinal acceleration, l f Represents the front axle wheelbase, l r Represents the rear axle wheelbase, C αf Represents the tire cornering stiffness of the front axle, C αr Represents the tire cornering stiffness of the rear axle. The following relationship can be obtained by calculating the above formula (1):

[0049]

[0050]

[0051] It should be noted that after determining the vehicle control data for the next moment of the current moment based on the vehicle state data, noise data, and the preset trajectory point information corresponding to the current moment, the vehicle dynamics model can also be deployed to the controller, and the vehicle dynamics model can be used for predictive control. Even in a high-speed automatic scenario, when the vehicle reaches the boundary of dynamic performance, the vehicle can be controlled to follow the trajectory. The technical solution of this embodiment can be based on the modeling of the longitudinal characteristics and lateral (transverse) characteristics of the vehicle, and the longitudinal and lateral actuator commands can be obtained simultaneously through the solver, so that the vehicle can be controlled to better coordinate steering and drive braking, and the vehicle can be well controlled when the steering and drive or braking mechanisms are working at the same time.

[0052] Optionally, after determining the vehicle control data for the next moment after the current moment based on the vehicle status data, noise data, and preset trajectory point information corresponding to the current moment, it also includes: processing the vehicle status data, noise data, preset trajectory point information and vehicle control data based on a pre-built dynamic model to obtain a vehicle following error; and determining the actual motion trajectory based on the vehicle following error and the target planned trajectory.

[0053] Specifically, the vehicle state data, noise data, preset trajectory point information, and vehicle control data can be processed based on the pre-built dynamic model to obtain the error between the actual vehicle operation state at the next moment and the target planned trajectory, that is, the vehicle following error, and then based on the vehicle following error and the target planned trajectory, the actual movement trajectory of the target vehicle can be obtained. For example, the pre-built dynamic model can be deployed in the controller, and the dynamic model is as follows:

[0054]

[0055] Among them, the state vector That is, vehicle status data, represents the longitudinal velocity deviation, v y represents the lateral velocity, r represents the yaw angular velocity, e y represents the lateral position deviation, e ψ Represents the heading angle deviation; interference vector That is, noisy data, κ ref Represents the curvature of the preset trajectory point, a ref Represents the acceleration of the preset trajectory point, a xdis represents the longitudinal disturbance acceleration, a ydis represents the lateral disturbance acceleration, represents the yaw angular acceleration disturbance. Control vector u = [δ f ,a] T , i.e., vehicle control data, δ f represents the longitudinal turning angle, and a represents the driving acceleration or braking deceleration.

[0056]

[0057]

[0058] The C matrix is ​​the identity matrix, and the D and G matrices are all zero matrices. m represents the mass of the vehicle, I z Represents the yaw moment of inertia. Represents the current longitudinal acceleration. l f Represents the front axle wheelbase, l r Represents the rear axle wheelbase, C αf Represents the tire cornering stiffness of the front axle, C αr Represents the tire cornering stiffness of the rear axle. When the vehicle state deviation, vehicle state data, noise data, and preset trajectory point information at the current moment are input into the dynamic model, the vehicle control data and actual operation data at the next moment of the current moment can be obtained.

[0059] S130, sending the vehicle control data to a controller of the target vehicle, so that the target vehicle is controlled by the controller to follow a target planned trajectory.

[0060] Specifically, the vehicle control data may be sent to a controller of the target vehicle. When the controller receives the vehicle control data, the vehicle may be controlled to update the longitudinal turning angle and the lateral speed so that the target vehicle follows the target planned trajectory.

[0061] In actual applications, during the actual operation of the vehicle, if it is braking operation, the vehicle control data obtained are the longitudinal turning angle and braking deceleration; if it is braking operation, the vehicle control data obtained are the longitudinal turning angle and driving acceleration.

[0062] Optionally, the vehicle control data is sent to the controller of the target vehicle, including: if the vehicle control data includes a longitudinal turning angle and a driving acceleration, the driving acceleration is converted to obtain a driving torque, and the longitudinal turning angle and the driving torque are sent to the controller; or, if the vehicle control data includes a longitudinal turning angle and a braking deceleration, the longitudinal turning angle and the braking deceleration are sent to the controller.

[0063] In this embodiment, if the vehicle control data includes the longitudinal turning angle and the driving acceleration, it can be explained that the vehicle is in a driving state, the driving acceleration can be converted into a driving torque by using a PID controller, and the longitudinal turning angle and the driving torque can be sent to the controller. If the vehicle control data includes the longitudinal turning angle and the braking deceleration, it can be explained that the vehicle is in a braking state, and the longitudinal turning angle and the braking deceleration can be directly sent to the controller.

[0064] The technical solution of this embodiment determines the longitudinal turning angle, driving acceleration and braking deceleration of the next moment after the current moment by acquiring the vehicle status data, noise data and preset trajectory point information corresponding to the target vehicle at the current moment; the longitudinal turning angle, driving acceleration and braking deceleration are sent to the controller of the target vehicle, so that the target vehicle is controlled by the controller to follow the target planned trajectory, which solves the problem of low vehicle control stability caused by longitudinal speed control based on PID control in the prior art, and determines the longitudinal turning angle, driving acceleration and braking deceleration of the next moment after the current moment by processing the vehicle status data, noise data and preset trajectory point information corresponding to the target vehicle at the current moment, so as to realize longitudinal and lateral comprehensive control of the vehicle based on the longitudinal turning angle, driving acceleration and braking deceleration, thereby improving the vehicle control accuracy and stability while reducing the vehicle following the target planned trajectory driving error, thereby achieving the technical effect of ensuring the safety of vehicle automatic driving.

[0065] Embodiment 2

[0066] As an optional embodiment of the above embodiment, in order to make those skilled in the art further understand the technical solution of the embodiment of the present invention, a specific application scenario example is given. For details, please refer to the following specific content.

[0067] For example, see Figure 2 , which can be represented as a schematic diagram of the structure of the vehicle control device. The technical solution of this embodiment can be jointly implemented by the safety logic processing module 210, the trajectory smoothing module 220 and the longitudinal and lateral coupling motion controller 230. The braking system feedback signal, the steering system feedback signal, the drive system feedback signal, the fused positioning information and other information can be used as vehicle status data, and the target discrete trajectory can be used as the target planning trajectory, wherein the braking system feedback signal, the steering system feedback signal and the drive system feedback signal can usually be provided by the vehicle chassis controller, the target discrete trajectory can be provided by the automatic driving system trajectory planning module, and the fused positioning information can usually be provided by the automatic driving perception positioning module. This technical solution can use bus and Ethernet hybrid communication as a method of communication between different modules, transmit signals through the vehicle CAN bus and chassis systems such as the braking system, steering system and drive system, and obtain the planning information and fused positioning information provided by the planning layer through Ethernet or CAN bus. The specific implementation process of each module is described below:

[0068] The safety logic processing module 210 includes an error processing unit 2101, an output processing unit 2102, and a signal watchdog unit 2103. The safety logic processing module 210 is used to detect whether the chassis signal, the planned trajectory information, and the positioning signal are lost through the signal watchdog unit 2103. If lost, the error processing state will be entered. The error processing state can be sent to the error processing unit 2101, and the error processing state can be an error code. The error processing unit 2101 will enter the error processing when the chassis subsystem fails according to the received status information of each chassis subsystem. The processing of safety logic is very important in the high-speed automatic driving scenario. The error processing unit 2101 is the core of the safety logic processing module 210. The error processing unit 2101 is used to receive the actuator status information from the CAN bus and the signal receiving status information from the signal watchdog unit 2103, and perform AND operations on all received signals. If the AND operation result is safe (bool type data true), it means that the traversal result is data complete, and the vehicle control data sent by the longitudinal and lateral coupling motion controller 230 is sent to the output processing unit 2102 as a control signal. If the AND operation result is unsafe (bool type data false), it means that the traversal result is data complete, and the pre-stored vehicle control data of the previous moment can be sent to the output processing unit. The signal watchdog unit 2103 is a counter, which is used to receive signals from the braking system feedback, steering system feedback, drive system feedback, target discrete trajectory, fusion positioning information, etc. If the cumulative number of signal losses exceeds the threshold, an unsafe signal is transmitted to the error processing unit 2101, but when the signal is received again, the number of losses is reset to zero and recalculated. The output processing unit 2102 is used to receive the control signal from the error processing unit 2101, and is responsible for transcoding the control signal into a CAN signal and sending it to the CAN bus in real time. The goal of the trajectory smoothing module 220 is to smooth the trajectory to obtain the curvature. The trajectory smoothing module 220 is added to the trajectory following method as an option. The trajectory smoothing module 220 can adopt the implementation method of polynomial fitting. The technical solution does not limit the specific implementation of the trajectory smoothing module 220. Those skilled in the art are familiar with the implementation method of this module. It only requires that the output reference point sequence is continuous and smooth in position and continuous in curvature.

[0069] The longitudinal and lateral coupling motion controller module 230 is the core of trajectory following. The longitudinal and lateral coupling motion controller module 230 is used to obtain the planned trajectory information, fuse the positioning information and the chassis feedback signal to calculate the vehicle control data such as the longitudinal turning angle, driving acceleration and braking deceleration of the autonomous driving vehicle, and then send this information through the CAN bus to control the chassis's driving motor, braking system and steering wheel, so that the vehicle completes closed-loop automatic control. For example, refer to Figure 3, which can be represented as a schematic diagram of the longitudinal and lateral coupling controller module structure. The longitudinal and lateral coupling motion controller module 230 includes a reference value generator 2301, a Kalman filter 2302, a dynamic parameter updating unit 2303 and an MPC (Model Predictive Control) solver 2304. The reference value generator 2301 is used to generate a target planning trajectory, such as but not limited to the preset follow-up trajectory point sequence information given by the planning module. Each trajectory point information includes information such as global coordinates X, global coordinates Y, curvature, flight phase angle, and vehicle speed. The Kalman filter 2302 is used to observe longitudinal and lateral noise, obtain noise data, and give the noise estimate corresponding to the noise data to the MPC solver 2304. When calculating the vehicle control data, the interference noise is taken into account to further improve the accuracy of the controller. The dynamic parameter updating unit 2303 is used to dynamically calculate the parameters of the MPC. The parameters will be used to update the reference model and constraints of the MPC controller. The parameters include the vehicle speed and the weights of the vehicle control data vector and the vehicle state data vector. The MPC solver 2304 mainly uses mathematical programming methods to solve the abstracted MPC problem. This part can be implemented using an open source solver, or a real-time online solver can be written by itself. The specific implementation method is well known to those in the field and will not be elaborated in detail. After receiving the information provided by the reference value generator 2301, the Kalman filter 2302, and the dynamic parameter update unit 2303, the MPC solver 2304 uses the MPC modeling method and solution method to solve the problem, and obtains the solver state and the solution result. The two outputs are sent to the error processing unit 2101 and the output processing unit 2102 in the safety logic processing module 210 respectively. The solution result is vehicle control data, and the output processing unit 2102 can send the vehicle control data to the controller of the target vehicle and the automatic driving chassis.

[0070] Based on the above scheme, the MPC modeling method and solution method are elaborated in detail. The premise of implementing the MPC control strategy is to establish a reasonable and sufficiently accurate dynamic model for the system. The dynamic model is as follows:

[0071]

[0072] Among them, the state vector That is, vehicle status data, represents the longitudinal velocity deviation, v y represents the lateral velocity, r represents the yaw angular velocity, e y represents the lateral position deviation, e ψ Represents the heading angle deviation; interference vector That is, noisy data, κ ref Represents the curvature of the preset trajectory point, a ref Represents the acceleration of the preset trajectory point, axdis represents the longitudinal disturbance acceleration, a ydis represents the lateral disturbance acceleration, represents the yaw angular acceleration disturbance. Control vector u = [δ f ,a] T , i.e., vehicle control data, δ f represents the longitudinal turning angle, and a represents the driving acceleration or braking deceleration.

[0073]

[0074]

[0075] The C matrix is ​​the identity matrix, and the D and G matrices are all zero matrices. m represents the mass of the vehicle, I z Represents the yaw moment of inertia. Represents the current longitudinal acceleration. l f Represents the front axle wheelbase, l r Represents the rear axle wheelbase, C αf Represents the tire cornering stiffness of the front axle, C αr Represents the tire cornering stiffness of the rear axle. MPC uses the equation of the dynamic model described above as the prediction equation of the vehicle automatic driving system. The reference value generator 2301 provides the vehicle state data reference and the vehicle control data reference to the MPC controller 2304. It can be calculated by the following formula (1):

[0076]

[0077] The following relationship can be obtained by calculating the above formula (1):

[0078]

[0079]

[0080] The technical solution of the present invention involves an MPC control method with a highly abstract feature. Its models and constraints will vary according to specific applications. The differences between different applications are basically shielded and are only related to the parameters and models inside the MPC controller. In other words, different applications (such as whether lateral control uses angle control or torque control) only require updating the corresponding models. This is particularly suitable for situations where vehicle dynamics parameters have a greater impact on vehicle driving state performance in high-speed autonomous driving scenarios, greatly improving the debugging and function iteration efficiency of autonomous driving product developers and having good adaptability to heterogeneous vehicles.

[0081] The technical solution of this embodiment determines the longitudinal turning angle, driving acceleration and braking deceleration of the next moment after the current moment by acquiring the vehicle status data, noise data and preset trajectory point information corresponding to the target vehicle at the current moment; the longitudinal turning angle, driving acceleration and braking deceleration are sent to the controller of the target vehicle, so that the target vehicle is controlled by the controller to follow the target planned trajectory, which solves the problem of low vehicle control stability caused by longitudinal speed control based on PID control in the prior art, and determines the longitudinal turning angle, driving acceleration and braking deceleration of the next moment after the current moment by processing the vehicle status data, noise data and preset trajectory point information corresponding to the target vehicle at the current moment, so as to realize longitudinal and lateral comprehensive control of the vehicle based on the longitudinal turning angle, driving acceleration and braking deceleration, thereby improving the vehicle control accuracy and stability while reducing the vehicle following the target planned trajectory driving error, thereby achieving the technical effect of ensuring the safety of vehicle automatic driving.

[0082] Embodiment 3

[0083] Figure 4 This is a structural block diagram of a vehicle control device provided by Embodiment 3 of the present invention. The device comprises: a data acquisition module 410 , a vehicle control data determination module 420 and a vehicle control data sending module 430 .

[0084] Among them, the data acquisition module 410 is used to obtain the vehicle status data and noise data corresponding to the target vehicle at the current moment; the vehicle control data determination module 420 is used to determine the vehicle control data at the next moment of the current moment based on the vehicle status data, the noise data, and the preset trajectory point information corresponding to the current moment, wherein the vehicle control data includes the longitudinal turning angle, driving acceleration and braking deceleration; the vehicle control data sending module 430 is used to send the vehicle control data to the controller of the target vehicle, so that the target vehicle is controlled to follow the target planned trajectory based on the controller.

[0085] The technical solution of this embodiment determines the longitudinal turning angle, driving acceleration and braking deceleration of the next moment after the current moment by acquiring the vehicle status data, noise data and preset trajectory point information corresponding to the target vehicle at the current moment; the longitudinal turning angle, driving acceleration and braking deceleration are sent to the controller of the target vehicle, so that the target vehicle is controlled by the controller to follow the target planned trajectory, which solves the problem of low vehicle control stability caused by longitudinal speed control based on PID control in the prior art, and determines the longitudinal turning angle, driving acceleration and braking deceleration of the next moment after the current moment by processing the vehicle status data, noise data and preset trajectory point information corresponding to the target vehicle at the current moment, so as to realize longitudinal and lateral comprehensive control of the vehicle based on the longitudinal turning angle, driving acceleration and braking deceleration, thereby improving the vehicle control accuracy and stability while reducing the vehicle following the target planned trajectory driving error, thereby achieving the technical effect of ensuring the safety of vehicle automatic driving.

[0086] On the basis of the above-mentioned device, optionally, the vehicle control data determination module 420 includes a traversal result determination unit, a target processing method determination unit and a data determination unit.

[0087] A traversal result determination unit, used for traversing and processing the vehicle state data, noise data and preset trajectory point information corresponding to the current moment to obtain a traversal result;

[0088] A data determination unit is used to, if the traversal result is data missing, use the vehicle control data of the moment before the current moment as the vehicle control data of the next moment of the current moment; or, if the traversal result is data complete, determine the vehicle control data based on the vehicle status data, the noise data and the preset trajectory point information.

[0089] On the basis of the above-mentioned device, optionally, the data determination unit includes a target cumulative number determination subunit, a warning prompt information sending determination subunit and a historical cumulative number update subunit.

[0090] A target cumulative number determination subunit is used for accumulating the number of missing times of the traversal result based on the historical cumulative number to obtain the target cumulative number if the traversal result corresponding to the current moment is data missing;

[0091] A warning prompt information sending determination subunit is used to generate a warning prompt information and send it to the target display interface if the target cumulative number of times exceeds a preset number;

[0092] The historical cumulative times updating subunit is used to adjust the target cumulative times to a preset value and update the historical cumulative times when the vehicle status data, noise data and preset trajectory point information different from the current moment are received again and the traversal result is that the data is complete.

[0093] On the basis of the above device, optionally, the vehicle control data determination module 420 includes a vehicle state deviation determination unit and a vehicle control data determination unit.

[0094] A vehicle state deviation determining unit, configured to determine a vehicle state deviation based on the vehicle state data and preset trajectory point information;

[0095] The vehicle control data determination unit is used to process the vehicle state deviation, the vehicle state data, the noise data and the preset trajectory point information based on a preset cost function to obtain vehicle control data.

[0096] On the basis of the above device, optionally, the device further includes a dynamic model processing module, and the dynamic model processing module includes a vehicle following error determination unit and an actual motion trajectory determination unit.

[0097] A vehicle following error determination unit, configured to process the vehicle state data, the noise data, the preset trajectory point information and the vehicle control data based on a pre-built dynamics model to obtain a vehicle following error;

[0098] The actual motion trajectory determining unit is used to determine the actual motion trajectory based on the vehicle following error and the target planned trajectory.

[0099] On the basis of the above-mentioned device, optionally, the vehicle control data sending module 430 includes a vehicle control data sending unit.

[0100] A vehicle control data sending unit is used to convert the driving acceleration to obtain the driving torque if the vehicle control data includes a longitudinal turning angle and a driving acceleration, and send the longitudinal turning angle and the driving torque to the controller; or, if the vehicle control data includes a longitudinal turning angle and a braking deceleration, send the longitudinal turning angle and the braking deceleration to the controller.

[0101] The vehicle control device provided in the embodiment of the present invention can execute the vehicle control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0102] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present invention.

[0103] Embodiment 4

[0104] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 5 A block diagram of an exemplary electronic device 50 suitable for implementing exemplary embodiments of the present invention is shown. Figure 5 The electronic device 50 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0105] like Figure 5 As shown, the electronic device 50 is in the form of a general computing device. The components of the electronic device 50 may include but are not limited to: one or more processors or processing units 501, a system memory 502, and a bus 503 connecting different system components (including the system memory 502 and the processing unit 501).

[0106] Bus 503 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0107] The electronic device 50 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 50, including volatile and non-volatile media, removable and non-removable media.

[0108] System memory 502 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 504 and / or cache memory 505. Electronic device 50 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 506 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 503 via one or more data medium interfaces. The memory 502 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the embodiments of the present invention.

[0109] A program / utility 508 having a set (at least one) of program modules 507 may be stored, for example, in the memory 502, such program modules 507 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 507 generally perform the functions and / or methods of the embodiments described herein.

[0110] The electronic device 50 may also communicate with one or more external devices 509 (e.g., keyboards, pointing devices, displays 510, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 50, and / or communicate with any device that enables the electronic device 50 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 511. Furthermore, the electronic device 50 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 512. As shown, the network adapter 512 communicates with other modules of the electronic device 50 through the bus 503. It should be understood that although Figure 5 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 50, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0111] The processing unit 501 executes various functional applications and data processing by running the programs stored in the system memory 502, such as implementing the vehicle control method provided in the embodiment of the present invention.

[0112] Embodiment 5

[0113] Embodiment 5 of the present invention further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute a vehicle control method when executed by a computer processor. The method includes:

[0114] Obtain vehicle status data and noise data corresponding to the target vehicle at the current moment;

[0115] Determining vehicle control data at a moment next to the current moment based on the vehicle state data, the noise data, and preset trajectory point information corresponding to the current moment, wherein the vehicle control data includes a longitudinal turning angle, a driving acceleration, and a braking deceleration;

[0116] The vehicle control data is sent to a controller of the target vehicle, so that the target vehicle is controlled by the controller to follow a target planned trajectory.

[0117] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0118] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0119] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0120] Computer program code for performing the operation of embodiments of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0121] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A vehicle control method, characterized in that: include: Obtain vehicle status data and noise data corresponding to the target vehicle at the current moment; Determining vehicle control data at a moment next to the current moment based on the vehicle state data, the noise data, and preset trajectory point information corresponding to the current moment, wherein the vehicle control data includes a longitudinal turning angle, a driving acceleration, and a braking deceleration; Sending the vehicle control data to the controller of the target vehicle so that the target vehicle is controlled by the controller to follow the target planned trajectory; The determining of the vehicle control data at the next moment of the current moment based on the vehicle state data, the noise data, and the preset track point information corresponding to the current moment includes: Traversing and processing the vehicle state data, noise data and preset trajectory point information corresponding to the current moment to obtain a traversal result; If the traversal result is data missing, the vehicle control data of the moment before the current moment is used as the vehicle control data of the moment after the current moment; or, If the traversal result is that the data is complete, determining vehicle control data based on the vehicle state data, the noise data and the preset trajectory point information; The method further comprises: If the traversal result corresponding to the current moment is data missing, the number of missing times of the traversal result is accumulated based on the historical cumulative times to obtain the target cumulative times; If the target cumulative number exceeds the preset number, a warning prompt message is generated and sent to the target display interface; When vehicle status data, noise data and preset trajectory point information different from the current moment are received again, and the traversal result is that the data is complete, the target cumulative number is adjusted to the preset value, and the historical cumulative number is updated.

2. The method according to claim 1, characterized in that The method of determining the vehicle control data at the next moment of the current moment based on the vehicle state data, the noise data, and the preset track point information corresponding to the current moment further includes: Determining a vehicle state deviation based on the vehicle state data and preset trajectory point information; The vehicle state deviation, the vehicle state data, the noise data and the preset trajectory point information are processed based on a preset cost function to obtain vehicle control data.

3. The method according to claim 1, characterized in that: After determining the vehicle control data at the next moment of the current moment based on the vehicle state data, the noise data, and the preset track point information corresponding to the current moment, the method further includes: Processing the vehicle state data, the noise data, the preset trajectory point information and the vehicle control data based on a pre-built dynamics model to obtain a vehicle following error; Based on the vehicle following error and the target planned trajectory, an actual motion trajectory is determined.

4. The method according to claim 1, characterized in that The step of sending the vehicle control data to the controller of the target vehicle comprises: If the vehicle control data includes a longitudinal turning angle and a driving acceleration, the driving acceleration is converted to obtain a driving torque, and the longitudinal turning angle and the driving torque are sent to the controller; or, If the vehicle control data includes a longitudinal turning angle and a braking deceleration, the longitudinal turning angle and the braking deceleration are sent to the controller.

5. A vehicle control device, characterized in that: include: A data acquisition module is used to obtain vehicle status data and noise data corresponding to the target vehicle at the current moment; A vehicle control data determination module, configured to determine the vehicle control data at a moment next to the current moment based on the vehicle state data, the noise data, and the preset trajectory point information corresponding to the current moment, wherein the vehicle control data includes a longitudinal turning angle, a driving acceleration, and a braking deceleration; A vehicle control data sending module, used for sending the vehicle control data to the controller of the target vehicle, so that the target vehicle is controlled to follow the target planned trajectory based on the controller; The vehicle control data determination module includes: a traversal result determination unit, which is used to traverse and process the vehicle state data, noise data and preset track point information corresponding to the current moment to obtain a traversal result; a data determination unit, which is used to use the vehicle control data of the moment before the current moment as the vehicle control data of the next moment of the current moment if the traversal result is data missing; or, if the traversal result is data complete, determine the vehicle control data based on the vehicle state data, the noise data and the preset track point information; The data determination unit includes: a target cumulative number determination subunit, which is used to accumulate the number of missing times of the traversal result based on the historical cumulative number to obtain the target cumulative number if the traversal result corresponding to the current moment is missing data; a warning prompt information sending determination subunit, which is used to generate a warning prompt information and send it to the target display interface if the target cumulative number exceeds the preset number; a historical cumulative number update subunit, which is used to adjust the target cumulative number to a preset value and update the historical cumulative number when the vehicle status data, noise data and preset trajectory point information different from the current moment are received again and the traversal result is complete data.

6. The device according to claim 5, characterized in that The vehicle control data determination module comprises: A vehicle state deviation determining unit, configured to determine a vehicle state deviation based on the vehicle state data and preset trajectory point information; The vehicle control data determination unit is used to process the vehicle state deviation, the vehicle state data, the noise data and the preset trajectory point information based on a preset cost function to obtain vehicle control data.

7. An electronic device, characterized in that: The device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle control method as described in any one of claims 1-4.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the vehicle control method as described in any one of claims 1 to 4 is implemented.

Images