CN112009499B

CN112009499B - Automatic vehicle driving control method and device

Info

Publication number: CN112009499B
Application number: CN202010963363.0A
Authority: CN
Inventors: 吕传龙; 李凯伦; 关书伟
Original assignee: Beijing Rockwell Technology Co Ltd
Current assignee: Beijing Rockwell Technology Co Ltd
Priority date: 2020-09-14
Filing date: 2020-09-14
Publication date: 2022-01-18
Anticipated expiration: 2040-09-14
Also published as: CN112009499A

Abstract

The embodiment of the disclosure discloses a vehicle automatic driving control method and device, relates to the technical field of vehicle control, and mainly aims to reduce the driving risk of automatic driving. The main technical scheme of the embodiment of the disclosure comprises the following steps: determining feasible track data of the vehicle, and sending the feasible track data to the longitudinal controller, the transverse controller and the transverse and longitudinal controller; acquiring a desired acceleration determined by the longitudinal controller based on the feasible trajectory data, a desired angle determined by the lateral controller based on the feasible trajectory data, and a desired acceleration and a desired angle determined by the lateral-longitudinal controller based on the feasible trajectory data; selecting a target expected acceleration and a target expected angle from the expected acceleration determined by the longitudinal controller, the expected angle determined by the transverse controller and the expected acceleration and the expected angle determined by the transverse and longitudinal controllers; and controlling the vehicle to run based on the target desired acceleration and the target desired angle.

Description

Automatic vehicle driving control method and device

Technical Field

The embodiment of the disclosure relates to the technical field of vehicle control, in particular to a vehicle automatic driving control method and device.

Background

The automatic driving vehicle, which can not only free the driver but also reduce the traffic accident rate, has become one of the future development trends of vehicles.

Currently, vehicle motion control is a key link for automatic driving of a vehicle, and is generally completed by a transverse controller and a longitudinal controller. The transverse controller and the longitudinal controller involved in the transverse and longitudinal control in the existing automatic driving are independent.

Because the transverse and longitudinal controls are independent of each other, the current transverse and longitudinal controls can have sudden failure of the transverse or longitudinal controller or unstable output. As long as one of the transverse controller and the longitudinal controller has sudden failure or unstable output, the whole control module of the vehicle directly fails, which brings huge driving risks to the automatic driving of the vehicle and is difficult to ensure the life safety of personnel in the vehicle.

Disclosure of Invention

In view of this, embodiments of the present disclosure provide a method and an apparatus for controlling automatic driving of a vehicle, and mainly aim to reduce driving risk of automatic driving. The main technical scheme comprises:

in a first aspect, an embodiment of the present disclosure provides a vehicle automatic driving control method, including:

determining feasible track data of a vehicle, and sending the feasible track data to a longitudinal controller, a transverse controller and a transverse-longitudinal controller, wherein the feasible track data is data for guiding vehicle running, which is planned for the vehicle by an automatic driving system of the vehicle by combining a high-precision map and perception information of the vehicle;

obtaining a desired acceleration determined by the longitudinal controller based on the feasible trajectory data, a desired angle determined by the lateral controller based on the feasible trajectory data, and a desired acceleration and a desired angle determined by the lateral longitudinal controller based on the feasible trajectory data;

selecting a target expected acceleration and a target expected angle from the expected acceleration determined by the longitudinal controller, the expected angle determined by the transverse controller and the expected acceleration and the expected angle determined by the transverse and longitudinal controllers;

and controlling the vehicle to run based on the target expected acceleration and the target expected angle.

In a second aspect, an embodiment of the present disclosure provides a vehicle automatic driving control apparatus, including:

the system comprises a determining unit, a longitudinal controller, a transverse controller and a longitudinal controller, wherein the determining unit is used for determining feasible track data of a vehicle and sending the feasible track data to the longitudinal controller, the transverse controller and the transverse controller, and the feasible track data is data which is used for guiding the vehicle to run and is planned for the vehicle by an automatic driving system of the vehicle by combining a high-precision map and perception information of the vehicle;

an acquisition unit configured to acquire a desired acceleration determined by the longitudinal controller based on the feasible trajectory data, a desired angle determined by the lateral controller based on the feasible trajectory data, and a desired acceleration and a desired angle determined by the lateral longitudinal controller based on the feasible trajectory data;

a selecting unit, configured to select a target desired acceleration and a target desired angle from the desired acceleration determined by the longitudinal controller, the desired angle determined by the lateral controller, and the desired acceleration and the desired angle determined by the lateral-longitudinal controller;

a control unit for controlling the vehicle to travel based on the target desired acceleration and the target desired angle.

In a third aspect, embodiments of the present disclosure provide a vehicle autopilot control system, the system comprising:

a longitudinal controller, a lateral-longitudinal controller, and the vehicle automatic driving control device of the second aspect;

the longitudinal controller is used for determining expected acceleration based on the feasible track data sent by the vehicle automatic driving control device and sending the determined expected acceleration to the vehicle automatic driving control device;

the transverse controller is used for determining a desired angle based on the feasible track data sent by the vehicle automatic driving control device and sending the determined desired angle to the vehicle automatic driving control device;

and the transverse and longitudinal controller is used for determining expected acceleration and an expected angle based on the feasible track data sent by the vehicle automatic driving control device and sending the determined expected acceleration and the determined expected angle to the vehicle automatic driving control device.

In a fourth aspect, an embodiment of the present disclosure provides a storage medium including a stored program, wherein the apparatus on which the storage medium is controlled to execute the vehicle automatic driving control method of the first aspect when the program runs.

In a fifth aspect, embodiments of the present disclosure provide a human-computer interaction device, which includes a storage medium coupled with one or more processors configured to execute program instructions stored in the storage medium; the program instructions when executed perform the vehicle automatic driving control method of the first aspect.

With the above technical solution, embodiments of the present disclosure provide a method and an apparatus for controlling automatic driving of a vehicle, which first determine feasible trajectory data of the vehicle, and send the feasible trajectory data to a longitudinal controller, a lateral controller, and a lateral-longitudinal controller. And acquiring a desired acceleration determined by the longitudinal controller based on the feasible trajectory data, a desired angle determined by the transverse controller based on the feasible trajectory data and a desired acceleration and a desired angle determined by the transverse-longitudinal controller based on the feasible trajectory data, and selecting a target desired acceleration and a target desired angle from the desired acceleration determined by the longitudinal controller, the desired angle determined by the transverse controller and the desired acceleration and the desired angle determined by the transverse-longitudinal controller. And finally, controlling the vehicle to run based on the target expected acceleration and the target expected angle. Therefore, the scheme provided by the embodiment of the disclosure integrates the expected acceleration determined by the longitudinal controller, the expected angle determined by the transverse controller and the expected acceleration and the expected angle determined by the transverse and longitudinal controllers, and determines the expected acceleration and the expected angle required for finally controlling the vehicle to run, so that the normal operation of the whole driving control system can be ensured even if any one of the three controllers fails or goes wrong, and the driving risk of automatic driving is reduced.

The foregoing description is only an overview of the embodiments of the present disclosure, and in order to make the technical means of the embodiments of the present disclosure more clearly understood, the embodiments of the present disclosure may be implemented in accordance with the content of the description, and in order to make the foregoing and other objects, features, and advantages of the embodiments of the present disclosure more clearly understood, the following detailed description of the embodiments of the present disclosure is given.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the embodiments of the present disclosure. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

fig. 1 shows a flowchart of a vehicle automatic driving control method provided by an embodiment of the present disclosure;

FIG. 2 illustrates a flow chart of another method of vehicle autopilot control provided by an embodiment of the present disclosure;

fig. 3 shows a block diagram of the components of a vehicle automatic driving control device provided by an embodiment of the present disclosure;

fig. 4 is a block diagram showing the components of another vehicle automatic driving control apparatus provided by the embodiment of the present disclosure;

fig. 5 shows a block diagram of the vehicle automatic driving control system provided by the embodiment of the disclosure.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

In a first aspect, an embodiment of the present disclosure provides a vehicle automatic driving control method, as shown in fig. 1, the method mainly includes:

101. and determining feasible track data of the vehicle, and sending the feasible track data to the longitudinal controller, the transverse controller and the transverse-longitudinal controller.

In practical application, the feasible trajectory data of the vehicle can be determined by an automatic driving system planning module of the vehicle, and the feasible trajectory data is data for guiding the vehicle to run, which is planned for the vehicle by the automatic driving system of the vehicle by combining a high-precision map and perception information of the vehicle and is a basis for automatic driving of the vehicle.

The specific process of determining the feasible trajectory data of the vehicle can comprise the following steps from one step to three:

the method comprises the steps of firstly, determining inherent road data in a first preset range around a vehicle according to current position information of the vehicle and a high-precision map.

The current location information of the vehicle can be determined using multi-sensor fusion and it can characterize the specific location where the vehicle is currently located. The multi-sensors may include, but are not limited to, GNSS (Global Navigation Satellite System), inertial Navigation elements, encoders, and the like.

The high-precision map is preset and comprises data information such as barrier information, traffic lights, height and speed limits, traffic signs and the like which are measured in advance in a road.

After determining the current position information of the vehicle, the current position information may be matched into a high-precision map to locate the current position of the vehicle in the high-precision map, and road intrinsic data within a first preset range around the vehicle may be determined based on the current position of the vehicle. The road inherent data is data measured in advance in a high-precision map, influences the determination of the feasible track of the vehicle, and is an important basis for determining the feasible track data of the vehicle. Alternatively, the road intrinsic data may not include, but is not limited to, at least one of the following: barrier information, traffic lights, height and speed limits, and traffic signs.

It should be noted that the first preset range described herein may be determined based on the service requirement. For example, it may be determined according to the visual range of the driver or the minimum distance for safe driving. Optionally, the first preset range is a range of 100-200 meters centered on the current position of the vehicle.

And secondly, determining current road condition data in a second preset range around the vehicle according to the current position information of the vehicle and the perception information acquired by the sensor arranged on the vehicle.

The current position information of the vehicle can be determined by adopting multi-sensor fusion, and the specific position of the vehicle at present can be represented. The multi-sensors may include, but are not limited to, GNSS (Global Navigation Satellite System), inertial Navigation elements, encoders, and the like.

The perception information is acquired by a sensor arranged on the vehicle. Wherein the sensor may comprise at least one of: camera, millimeter wave radar, laser radar. The perception information is information on a relationship between a vehicle and an obstacle such as a vehicle and a pedestrian in the vicinity of the vehicle, which is perceived by a sensor of the vehicle.

After the current position information of the vehicle is determined, the current position information and the perception information can be matched, and the current road condition data in a second preset range around the vehicle is determined based on the current position of the vehicle. The current road condition data can embody the position of obstacles and a vehicle body around the vehicle, influence the determination of the feasible track of the vehicle and are an important basis for determining the feasible track data of the vehicle. Alternatively, the current road condition data may not include, but is not limited to, obstacle information, such as obstacles around the vehicle and the posture of the vehicle body.

It should be noted that the second preset range described herein may be determined based on the service requirement. For example, it may be determined according to the visual range of the driver or the minimum distance for safe driving. Optionally, the second preset range is a range of 100-200 meters centered on the current position of the vehicle. The second predetermined range may be the same as the first predetermined range, or may be different from the first predetermined range. For example, when the sensing distance of the sensor of the vehicle is small, the second preset range may be smaller than the first preset range. For example, when it is required to more accurately know the feasible trajectory data of the vehicle, the second preset range is the same as the first preset range.

And thirdly, determining the feasible track data based on the inherent road data and the current road condition data.

The inherent data of the road can embody inherent objects and inherent required information in the road, such as barrier information, traffic lights, height and speed limits, traffic signs and other information. And the current road condition data can embody the information of surrounding obstacles and the pose data of the vehicle body in the current road where the vehicle is located. The data of the inherent road and the current road condition can determine where the vehicle can pass through the current road, and the passing speed is, that is, the data of the feasible track of the vehicle can be determined, so as to provide a basis for the running of the vehicle.

The following describes a process of determining feasible trajectory data based on inherent road data and current road condition data, and the process includes the following steps: determining a plurality of path points, reference control parameters corresponding to each path point and vehicle passing time points based on the inherent data of the road and the current road condition data, wherein the plurality of path points are points on the same path; and determining the plurality of path points, the reference control parameters corresponding to each path point and the vehicle passing time point as feasible track data.

A plurality of path points determined based on the inherent data of the road and the current road condition data belong to points on the same path, and the path points not only avoid the marked obstacles in the high-precision map, but also avoid the obstacles in the current road condition. In order to ensure that the vehicles can safely pass through each path point, each path point has its own reference control parameter and vehicle passing time point. Wherein the reference control parameters are used to define with which control the vehicle passes its corresponding waypoint. The reference control parameter may include, but is not limited to, at least one of: front wheel slip angle, steering wheel angle, lateral velocity, longitudinal velocity, acceleration, path curvature.

In practical applications, after the feasible trajectory data is determined, the feasible trajectory data needs to be sent to the longitudinal controller, the lateral controller and the transverse-longitudinal controller respectively, so that the longitudinal controller, the lateral controller and the transverse-longitudinal controller can calculate the feasible trajectory data.

102. Desired accelerations determined by the longitudinal controller based on the feasible trajectory data, desired angles determined by the lateral controller based on the feasible trajectory data, and desired accelerations and desired angles determined by the lateral longitudinal controller based on the feasible trajectory data are obtained.

In practical application, the longitudinal controller, the transverse controller and the transverse-longitudinal controller are three controllers which are independent from each other, the transverse-longitudinal controller and the longitudinal controller are standby for each other, and the transverse-longitudinal controller and the transverse controller are standby for each other.

The longitudinal controller adopts a neural network PID (Proportional Integral Derivative) control algorithm to determine the expected acceleration of the current vehicle through the position information of the current vehicle and the front vehicle in the feasible track data and the speed information of the current vehicle and the front vehicle. Wherein, the proportional, integral and differential coefficients inside the PID control algorithm are adjusted by using a BP (Back Propagation) neural network. The longitudinal motion of the vehicle can be controlled by a desired acceleration.

The transverse controller adopts an LQR (Linear Quadratic Regulator) control algorithm, and obtains an expected angle meeting a minimum constraint condition according to a vehicle dynamic model by inputting the transverse deviation, the transverse deviation change rate, the course deviation and the course deviation change rate of the position information of the current vehicle and a target point (the position of the target point is determined by a plurality of path points). Wherein the desired angle may be a steering wheel angle or a front wheel slip angle by which lateral movement of the vehicle may be controlled.

The transverse and longitudinal controllers adopt an MPC (Model Predictive Control) Control algorithm, and obtain an expected acceleration and an expected angle which meet cost functions and dynamic constraint conditions according to a vehicle dynamic Model through position information (the position of a target point is determined through a plurality of path points) of a current vehicle and the target point in the feasible trajectory data and speed information. Wherein the desired angle may be a steering wheel angle or a front wheel slip angle by which lateral movement of the vehicle may be controlled. The longitudinal motion of the vehicle can be controlled by a desired acceleration.

After the three controllers obtain their respective parameters, their respective corresponding parameters are obtained, so that the desired acceleration determined by the longitudinal controller based on the feasible trajectory data, the desired angle determined by the lateral controller based on the feasible trajectory data, and the desired acceleration and the desired angle determined by the lateral-longitudinal controller based on the feasible trajectory data can be obtained.

103. And selecting a target expected acceleration and a target expected angle from the expected acceleration determined by the longitudinal controller, the expected angle determined by the transverse controller and the expected acceleration and the expected angle determined by the transverse-longitudinal controller.

The longitudinal controller, the transverse controller and the transverse and longitudinal controller are three independent controllers, the transverse and longitudinal controllers are standby for each other, and the transverse and longitudinal controllers are standby for each other. Because of the backup relationship, redundancy exists between the desired acceleration and the desired angle, and in order to realize the most effective automatic driving control of the vehicle, the better desired acceleration and desired angle are selected from the redundant desired acceleration and desired angle for controlling the vehicle.

The following describes a specific implementation process of the target desired acceleration and the target desired angle, which at least includes the following steps one to three:

determining a plurality of parameter sets according to the expected acceleration determined by the longitudinal controller, the expected angle determined by the transverse controller and the expected acceleration and the expected angle determined by the transverse and longitudinal controllers, wherein each parameter set comprises one expected acceleration and one expected angle, and the expected acceleration and/or the expected angle included in different parameter sets are different.

To ensure that three controller-determined parameters can be covered, the determined plurality of parameter sets should include the following parameter sets: one parameter set includes a desired acceleration determined by the longitudinal controller and a desired angle determined by the lateral controller; one parameter set includes a desired acceleration determined by the longitudinal controller and a desired angle determined by the lateral longitudinal controller; one parameter set includes a desired angle determined by the lateral control and a desired acceleration determined by the lateral-longitudinal controller; one parameter set includes the desired acceleration and the desired angle determined by the lateral-longitudinal controller.

And secondly, generating at least one expected control quantity corresponding to each parameter group based on the expected acceleration and the expected angle included in each parameter group.

At least one desired control quantity corresponding to each parameter set is estimated based on a desired acceleration and a desired angle corresponding to the parameter set. Wherein the generation process is determined by the reference control parameters corresponding to each path point and the vehicle passing time point and the expected acceleration and the expected angle in the parameter group.

The at least one desired control quantity corresponding to a parameter set may comprise at least one of: an error between the desired front wheel slip angle and the parametric front wheel slip angle, an error between the control desired acceleration and the reference acceleration, a centroid slip angle (which is determined using the longitudinal and lateral velocities at the next time predicted using the current decision control amount), a predicted steering wheel angle at the next time, a predicted acceleration at the next time, a predicted curvature of the path.

And thirdly, selecting expected acceleration and an expected angle included in one parameter group as the target expected acceleration and the target expected angle based on at least one expected control quantity corresponding to each parameter group.

Each parameter set has at least one corresponding desired control quantity, and in order to be able to select an optimal parameter set, the following steps one to two are required to perform the processing:

step one, determining the weight sum of at least one expected control quantity corresponding to each parameter group.

In order to comprehensively evaluate at least one desired control quantity corresponding to each parameter set, a weighted sum of the at least one desired control quantity corresponding to each parameter set needs to be determined, and the parameters in each parameter set are evaluated by the weighted sum.

The method for determining the weighted sum of at least one expected control quantity corresponding to the parameter group at least comprises the following steps:

first, the sum of weights is calculated by the following formula for at least one desired control amount corresponding to each of the parameter groups;

wherein the content of the first and second substances,

characterizing a weighted sum of the jth parameter set;

a weight coefficient characterizing the ith desired control quantity;

characterizing the ith desired control quantity; n characterizes the total number of desired control quantities for the jth parameter set.

It should be noted that, in this method, the weight coefficient of each desired controlled variable may be determined based on the degree of importance of the desired controlled variable to the driving safety of the vehicle.

Illustratively, 7 expected control quantities correspond to one parameter group, where the 7 expected control quantities are as follows:

wherein the content of the first and second substances,

=

error between the desired front wheel slip angle and the parametric front wheel slip angle;

to control the error between the desired acceleration and the reference acceleration;

respectively the longitudinal and lateral velocities predicted at the next time using the current control amount to be determined,

is the centroid slip angle;

to predict the steering wheel angle at the next moment,

in order to predict the acceleration at the next moment,

to predict the jerk at the next moment,

is the curvature of the predicted path.

By substituting the 7 desired control amounts into the above equation, the weight sum corresponding to the parameter group can be obtained.

Secondly, calculating the weight sum according to the following formula for at least one expected control quantity corresponding to each parameter group;

wherein the content of the first and second substances,

characterizing a weighted sum of the jth parameter set;

characterizing the ith desired control quantity; n denotes theTotal number of desired control quantities for the j parameter sets.

And secondly, selecting the expected acceleration and the expected angle included in the weight and the parameter group which meets the preset screening condition as the target expected acceleration and the target expected angle.

The preset screening condition may be determined based on the service requirement. For example, the preset filtering condition may be a weight sum minimum or a weight sum maximum.

For example, the desired acceleration and the desired angle included in the set of weights and the largest parameter are selected as the target desired acceleration and the target desired angle.

The target desired acceleration and the target desired angle are more suitable for the vehicle control requirements because the target desired acceleration and the target desired angle are obtained by integrating three controllers, namely a longitudinal controller, a transverse controller and a transverse-longitudinal controller. Even if any one of the longitudinal controller, the lateral controller, and the lateral-longitudinal controller fails, a target desired acceleration and a target desired angle that satisfy a control requirement of the vehicle can be determined, thereby reducing a driving risk of automatic driving.

104. And controlling the vehicle to run based on the target expected acceleration and the target expected angle.

After the target desired acceleration and the target desired angle are determined, there may be a vehicle actuator that performs control of the vehicle in accordance with the target desired acceleration and the target desired angle.

The embodiment of the disclosure provides a vehicle automatic driving control method, which includes firstly determining feasible track data of a vehicle and sending the feasible track data to a longitudinal controller, a transverse controller and a transverse and longitudinal controller. And acquiring a desired acceleration determined by the longitudinal controller based on the feasible trajectory data, a desired angle determined by the transverse controller based on the feasible trajectory data and a desired acceleration and a desired angle determined by the transverse-longitudinal controller based on the feasible trajectory data, and selecting a target desired acceleration and a target desired angle from the desired acceleration determined by the longitudinal controller, the desired angle determined by the transverse controller and the desired acceleration and the desired angle determined by the transverse-longitudinal controller. And finally, controlling the vehicle to run based on the target expected acceleration and the target expected angle. Therefore, the scheme provided by the embodiment of the disclosure integrates the expected acceleration determined by the longitudinal controller, the expected angle determined by the transverse controller and the expected acceleration and the expected angle determined by the transverse and longitudinal controllers, and determines the expected acceleration and the expected angle required for finally controlling the vehicle to run, so that the normal operation of the whole driving control system can be ensured even if any one of the three controllers fails or goes wrong, and the driving risk of automatic driving is reduced.

In a second aspect, according to the method in the first aspect, another embodiment of the present disclosure further provides a vehicle automatic driving control method, as shown in fig. 2, the method mainly includes:

201. and determining the inherent data of the road in a first preset range around the vehicle according to the current position information of the vehicle and the high-precision map.

202. And determining current road condition data in a second preset range around the vehicle according to the current position information of the vehicle and the perception information acquired by the sensor arranged on the vehicle.

203. And determining a plurality of path points, reference control parameters corresponding to each path point and vehicle passing time points based on the inherent road data and the current road condition data, wherein the path points are points on the same path.

204. And determining the plurality of path points, the reference control parameters corresponding to each path point and the vehicle passing time point as the feasible track data.

205. And sending the feasible track data to a longitudinal controller, a transverse controller and a transverse and longitudinal controller.

206. Desired accelerations determined by the longitudinal controller based on the feasible trajectory data, desired angles determined by the lateral controller based on the feasible trajectory data, and desired accelerations and desired angles determined by the lateral longitudinal controller based on the feasible trajectory data are obtained.

207. Determining whether a difference between the desired acceleration determined by the lateral-longitudinal controller and the desired acceleration determined by the longitudinal controller is greater than a first threshold; if so, execute 208 and 209; otherwise, 211 is executed.

Further, in order to reduce the processing amount of selecting the target desired acceleration and the target desired angle and eliminate the undesired desired acceleration that does not meet the requirement in time, after the parameters determined by the three controllers are obtained, it is necessary to determine whether the difference between the desired acceleration determined by the lateral and longitudinal controllers and the desired acceleration determined by the longitudinal controller is greater than a first threshold.

When the difference between the expected acceleration determined by the transverse and longitudinal controllers and the expected acceleration determined by the longitudinal controller is larger than the first threshold value, it is indicated that one of the transverse and longitudinal controllers has a fault, 208 is executed to send an alarm prompt and prompt a driver to perform fault detection on the controllers in time.

Further, when it is determined that the difference between the desired acceleration determined by the lateral-longitudinal controller and the desired acceleration determined by the longitudinal controller is greater than the first threshold value, it is necessary to determine the desired acceleration that can be used in the automatic driving control in order to ensure that the vehicle can normally travel, step 209 is executed.

208. And sending an alarm prompt.

In practical applications, the manner of the alarm prompt may be determined based on the service requirement. For example, the alarm information is displayed in a car machine or played in a voice mode in the car machine. In another example, alarm information is sent to a terminal designated by the driver.

209. Determining a desired acceleration that differs minimally from a second threshold value among the desired acceleration determined by the lateral-longitudinal controller and the desired acceleration determined by the longitudinal controller.

Determining a desired acceleration which is the smallest difference from the second threshold value among the desired acceleration determined by the lateral-longitudinal controller and the desired acceleration determined by the longitudinal controller, the desired acceleration being determined by the non-failed controller.

210. The desired acceleration that is the least different from the second threshold is chosen as the target desired acceleration, 211.

In order to reduce the subsequent processing procedure of selecting the target expected acceleration, the expected acceleration determined by the fault controller is directly eliminated, and the expected acceleration with the minimum difference with the second threshold value is directly selected as the target expected acceleration.

211. Determining whether a difference between the desired angle determined by the lateral-longitudinal controller and the desired angle determined by the lateral controller is greater than a third threshold; if so, 212 and 213 are performed; otherwise, 214 is performed.

Further, in order to reduce the processing amount of selecting the target desired acceleration and the target desired angle and reject the undesired desired angle that does not meet the requirement in time, after the parameters determined by the three controllers are obtained, it is necessary to determine whether the difference between the desired angle determined by the lateral-longitudinal controller and the desired angle determined by the lateral controller is greater than a third threshold.

And when the difference between the expected angle determined by the transverse and longitudinal controller and the expected angle determined by the transverse controller is larger than a third threshold value, if the problem that one of the transverse and longitudinal controllers and the transverse controller has a fault is solved, executing 212 to give an alarm prompt and prompt a driver to perform fault detection on the controller in time.

In addition, when it is determined that the difference between the desired angle determined by the lateral-longitudinal controller and the desired angle determined by the lateral controller is greater than the third threshold value, and it is necessary to determine the desired angle that can be used in the automatic driving control in order to ensure that the vehicle can normally travel, step 213 is performed.

212. And sending an alarm prompt.

213. Determining a desired angle that is the smallest difference from a fourth threshold value among the desired angle determined by the lateral-longitudinal controller and the desired angle determined by the lateral controller.

And determining the expected angle with the smallest difference from the fourth threshold value in the expected angle determined by the transverse and longitudinal controllers and the expected angle determined by the longitudinal controller, wherein the expected angle is determined by the controller without the fault.

214. The desired angle with the smallest difference from the fourth threshold is chosen as the target desired angle and 220 is performed.

In order to reduce the subsequent processing procedure of selecting the target desired angle, the desired angle determined by the fault controller is directly eliminated, and the desired angle with the smallest difference from the fourth threshold value is directly selected as the target desired angle.

215. And determining a plurality of parameter sets according to the expected acceleration determined by the longitudinal controller, the expected angle determined by the transverse controller and the expected acceleration and the expected angle determined by the transverse-longitudinal controller, wherein each parameter set comprises one expected acceleration and one expected angle, and the expected acceleration and/or the expected angle are different in different parameter sets.

It should be noted that, if the target desired angle and the target desired acceleration are directly determined in the above-mentioned steps 207-214, the step 215 is not required to be executed, and the step 219 may be directly executed.

216. Generating at least one expected control quantity corresponding to each parameter group respectively based on the expected acceleration and the expected angle included in each parameter group;

217. determining the weight sum of at least one expected control quantity corresponding to each parameter group;

218. and selecting the expected acceleration and the expected angle included in the weight and the parameter group which meets the preset screening condition as the target expected acceleration and the target expected angle.

219. And controlling the vehicle to run based on the target expected acceleration and the target expected angle.

220. If the target desired angle or target desired acceleration is directly determined, then in grouping the sets of parameters, the target desired angle or target desired acceleration is directly used to group with the parameters determined by the controller for which no fault is determined, and 215 is performed.

In a third aspect, according to the method shown in fig. 1 or fig. 2, another embodiment of the present disclosure further provides a vehicle automatic driving control apparatus, as shown in fig. 3, the apparatus mainly includes:

the determining unit 31 is used for determining feasible track data of the vehicle and sending the feasible track data to the longitudinal controller, the transverse controller and the transverse and longitudinal controller;

an acquisition unit 32 configured to acquire a desired acceleration determined by the longitudinal controller based on the feasible trajectory data, a desired angle determined by the lateral controller based on the feasible trajectory data, and a desired acceleration and a desired angle determined by the lateral longitudinal controller based on the feasible trajectory data;

a first selecting unit 33, configured to select a target desired acceleration and a target desired angle from the desired acceleration determined by the longitudinal controller, the desired angle determined by the lateral controller, and the desired acceleration and the desired angle determined by the lateral-longitudinal controller;

a control unit 34 for controlling the vehicle to run based on the target desired acceleration and the target desired angle.

Embodiments of the present disclosure provide a vehicle automatic driving control apparatus that first determines feasible trajectory data of a vehicle and transmits the feasible trajectory data to a longitudinal controller, a lateral controller, and a lateral-longitudinal controller. And acquiring a desired acceleration determined by the longitudinal controller based on the feasible trajectory data, a desired angle determined by the transverse controller based on the feasible trajectory data and a desired acceleration and a desired angle determined by the transverse-longitudinal controller based on the feasible trajectory data, and selecting a target desired acceleration and a target desired angle from the desired acceleration determined by the longitudinal controller, the desired angle determined by the transverse controller and the desired acceleration and the desired angle determined by the transverse-longitudinal controller. And finally, controlling the vehicle to run based on the target expected acceleration and the target expected angle. Therefore, the scheme provided by the embodiment of the disclosure integrates the expected acceleration determined by the longitudinal controller, the expected angle determined by the transverse controller and the expected acceleration and the expected angle determined by the transverse and longitudinal controllers, and determines the expected acceleration and the expected angle required for finally controlling the vehicle to run, so that the normal operation of the whole driving control system can be ensured even if any one of the three controllers fails or goes wrong, and the driving risk of automatic driving is reduced.

In some embodiments, as shown in fig. 4, the first selecting unit 33 includes:

a first determining module 331, configured to determine a plurality of parameter sets according to the desired acceleration determined by the longitudinal controller, the desired angle determined by the lateral controller, and the desired acceleration and the desired angle determined by the lateral-longitudinal controller, where each of the parameter sets includes one desired acceleration and one desired angle, and the desired acceleration and/or the desired angle included in different parameter sets are different;

a generating module 332, configured to generate at least one expected control amount corresponding to each of the parameter groups based on the expected acceleration and the expected angle included in each of the parameter groups;

a selecting module 333, configured to select, based on at least one expected control quantity corresponding to each of the parameter groups, an expected acceleration and an expected angle included in one of the parameter groups as the target expected acceleration and the target expected angle.

In some embodiments, as shown in fig. 4, the selecting module 333 is configured to determine a weighted sum of at least one desired control quantity corresponding to each parameter set; and selecting the expected acceleration and the expected angle included in the weight and the parameter group which meets the preset screening condition as the target expected acceleration and the target expected angle.

In some embodiments, as shown in fig. 4, the selecting module 333 is configured to calculate the weight sum by the following formula for at least one desired control quantity corresponding to each parameter set;

wherein the content of the first and second substances,

characterizing a weighted sum of the jth parameter set;

a weight coefficient characterizing the ith desired control quantity;

In some embodiments, as shown in fig. 4, the determining unit 31 includes:

the second determining module 311 is configured to determine inherent road data in a first preset range around the vehicle according to the current position information of the vehicle and the high-precision map;

a third determining module 312, configured to determine current road condition data in a second preset range around the vehicle according to the current location information of the vehicle and sensing information collected by a sensor disposed in the vehicle;

a fourth determining module 313, configured to determine the feasible trajectory data based on the inherent road data and the current road condition data.

In some embodiments, as shown in fig. 4, the fourth determining module 313 is configured to determine a plurality of waypoints, a reference control parameter corresponding to each waypoint, and a vehicle passing time point based on the inherent road data and the current road condition data, where the plurality of waypoints are points on the same path; and determining the plurality of path points, the reference control parameters corresponding to each path point and the vehicle passing time point as the feasible track data.

In some embodiments, as shown in fig. 4, the apparatus further comprises:

a first judgment unit 35 for judging whether a difference between the desired acceleration determined by the lateral-longitudinal controller and the desired acceleration determined by the longitudinal controller is larger than a first threshold value; if yes, an alarm prompt is sent.

In some embodiments, as shown in fig. 4, the apparatus further comprises:

a second selecting unit 36, configured to determine, when the first determining unit 35 determines that the difference between the desired acceleration determined by the lateral-longitudinal controller and the desired acceleration determined by the longitudinal controller is greater than the first threshold, a desired acceleration having a smallest difference from a second threshold among the desired acceleration determined by the lateral-longitudinal controller and the desired acceleration determined by the longitudinal controller; selecting the desired acceleration with the minimum difference from the second threshold value as a target desired acceleration.

In some embodiments, as shown in fig. 4, the apparatus further comprises:

a second judgment unit 37 for judging whether a difference between the desired angle determined by the lateral-longitudinal controller and the desired angle determined by the lateral controller is larger than a third threshold; if yes, an alarm prompt is sent.

In some embodiments, as shown in fig. 4, the apparatus further comprises:

a third selecting unit 38, configured to determine, when the second selecting unit 36 determines that the difference between the desired angle determined by the lateral controller and the desired angle determined by the lateral controller is greater than a third threshold, a desired angle with a smallest difference from a fourth threshold, from among the desired angle determined by the lateral controller and the desired angle determined by the lateral controller; and selecting the expected angle with the minimum difference with the fourth threshold value as a target expected angle.

The vehicle automatic driving control device provided by the embodiment of the third aspect may be configured to execute the vehicle automatic driving control method provided by the embodiment of the first aspect or the second aspect, and the related meanings and specific implementations may refer to the related descriptions in the embodiment of the first aspect or the second aspect, and will not be described in detail here.

In a fourth aspect, according to the apparatus shown in fig. 3 or 4, another embodiment of the present disclosure further provides a vehicle automatic driving control system, as shown in fig. 5, the system mainly includes:

a longitudinal controller 41, a lateral controller 42, a lateral longitudinal controller 43, and a vehicle automatic driving control device 44 according to the third aspect;

the longitudinal controller 41 is configured to determine a desired acceleration based on the feasible trajectory data sent by the vehicle automatic driving control device 44, and send the determined desired acceleration to the vehicle automatic driving control device 44;

the lateral controller 42 is configured to determine a desired angle based on the feasible trajectory data sent by the vehicle automatic driving control device 44, and send the determined desired angle to the vehicle automatic driving control device 44;

the lateral-longitudinal controller 43 is configured to determine a desired acceleration and a desired angle based on the feasible trajectory data sent from the vehicle automatic driving control device 44, and send the determined desired acceleration and desired angle to the vehicle automatic driving control device 44.

Embodiments of the present disclosure provide a vehicle automatic driving control system in which a vehicle automatic driving control apparatus first determines feasible trajectory data of a vehicle and transmits the feasible trajectory data to a longitudinal controller, a lateral controller, and a lateral-longitudinal controller. And acquiring a desired acceleration determined by the longitudinal controller based on the feasible trajectory data, a desired angle determined by the transverse controller based on the feasible trajectory data and a desired acceleration and a desired angle determined by the transverse-longitudinal controller based on the feasible trajectory data, and selecting a target desired acceleration and a target desired angle from the desired acceleration determined by the longitudinal controller, the desired angle determined by the transverse controller and the desired acceleration and the desired angle determined by the transverse-longitudinal controller. And finally, controlling the vehicle to run based on the target expected acceleration and the target expected angle. Therefore, the scheme provided by the embodiment of the disclosure integrates the expected acceleration determined by the longitudinal controller, the expected angle determined by the transverse controller and the expected acceleration and the expected angle determined by the transverse and longitudinal controllers, determines the expected acceleration and the expected angle required by finally controlling the vehicle to run, and can ensure the normal operation of the whole driving control system even if any one of the three controllers fails or goes wrong, thereby reducing the driving risk of automatic driving.

In a fourth aspect, an embodiment of the present disclosure provides a storage medium including a stored program, where the apparatus in which the storage medium is located is controlled to execute the vehicle automatic driving control method according to the first aspect or the second aspect when the program runs.

The storage medium may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

In a fifth aspect, embodiments of the present disclosure provide a human-computer interaction device, which includes a storage medium coupled with one or more processors configured to execute program instructions stored in the storage medium; the program instructions when executed perform the vehicle automatic driving control method of the first aspect or the second aspect.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, embodiments of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A vehicle automatic driving control method, characterized by comprising:

2. The method of claim 1, wherein selecting a target desired acceleration and a target desired angle from the desired acceleration determined by the longitudinal controller, the desired angle determined by the lateral controller, and the desired acceleration and desired angle determined by the lateral-longitudinal controller comprises:

determining a plurality of parameter sets according to the expected acceleration determined by the longitudinal controller, the expected angle determined by the transverse controller and the expected acceleration and the expected angle determined by the transverse and longitudinal controllers, wherein each parameter set comprises one expected acceleration and one expected angle, and the expected acceleration and/or the expected angle included in different parameter sets are different;

generating at least one expected control quantity corresponding to each parameter group respectively based on the expected acceleration and the expected angle included in each parameter group;

and selecting a desired acceleration and a desired angle included in one parameter group as the target desired acceleration and the target desired angle based on at least one desired control quantity corresponding to each parameter group.

3. The method according to claim 2, wherein selecting a desired acceleration and a desired angle included in one of the parameter groups as the target desired acceleration and the target desired angle based on at least one desired control amount corresponding to each of the parameter groups comprises:

determining the weight sum of at least one expected control quantity corresponding to each parameter group;

and selecting the expected acceleration and the expected angle included in the weight and the parameter group which meets the preset screening condition as the target expected acceleration and the target expected angle.

4. The method of claim 3, wherein determining a weighted sum of at least one desired control quantity for each of the sets of parameters comprises:

calculating the weight sum according to the following formula aiming at least one expected control quantity corresponding to each parameter group;

wherein the content of the first and second substances,

characterizing a weighted sum of the jth parameter set;

a weight coefficient characterizing the ith desired control quantity;

5. The method of claim 1, wherein determining feasible trajectory data for the vehicle comprises:

determining inherent road data in a first preset range around the vehicle according to the current position information of the vehicle and a high-precision map;

determining current road condition data in a second preset range around the vehicle according to the current position information of the vehicle and perception information acquired by a sensor arranged on the vehicle;

and determining the feasible track data based on the inherent road data and the current road condition data.

6. The method of claim 5, wherein determining the feasible trajectory data based on the road intrinsic data and the current road condition data comprises:

determining a plurality of path points, reference control parameters corresponding to each path point and vehicle passing time points based on the inherent road data and the current road condition data, wherein the path points are points on the same path;

and determining the plurality of path points, the reference control parameters corresponding to each path point and the vehicle passing time point as the feasible track data.

7. The method of claim 1, further comprising:

determining whether a difference between the desired acceleration determined by the lateral-longitudinal controller and the desired acceleration determined by the longitudinal controller is greater than a first threshold;

if yes, an alarm prompt is sent.

8. The method of claim 7, further comprising:

determining a desired acceleration with a minimum difference from a second threshold value in the desired acceleration determined by the transverse and longitudinal controllers and the desired acceleration determined by the longitudinal controller when the difference between the desired acceleration determined by the transverse and longitudinal controllers and the desired acceleration determined by the longitudinal controller is judged to be larger than the first threshold value;

selecting the desired acceleration with the minimum difference from the second threshold value as a target desired acceleration.

9. The method of claim 1, further comprising:

determining whether a difference between the desired angle determined by the lateral-longitudinal controller and the desired angle determined by the lateral controller is greater than a third threshold;

if yes, an alarm prompt is sent.

10. The method of claim 9, further comprising:

determining a desired angle with a smallest difference from a fourth threshold value in the desired angle determined by the transverse and longitudinal controller and the desired angle determined by the transverse and longitudinal controller when the difference between the desired angle determined by the transverse and longitudinal controller and the desired angle determined by the transverse and longitudinal controller is judged to be larger than the third threshold value;

and selecting the expected angle with the minimum difference with the fourth threshold value as a target expected angle.

11. An automatic driving control apparatus for a vehicle, characterized in that the apparatus comprises:

12. A vehicle autopilot control system comprising: a longitudinal controller, a lateral longitudinal controller, and the vehicle automatic driving control apparatus according to claim 11;

13. The system of claim 12, wherein the first selecting unit comprises:

a first determining module, configured to determine a plurality of parameter sets according to the desired acceleration determined by the longitudinal controller, the desired angle determined by the lateral controller, and the desired acceleration and the desired angle determined by the lateral-longitudinal controller, where each of the parameter sets includes one desired acceleration and one desired angle, and the desired acceleration and/or the desired angle included in different parameter sets are different;

the generating module is used for generating at least one expected control quantity corresponding to each parameter group respectively based on the expected acceleration and the expected angle included in each parameter group;

and the selecting module is used for selecting the expected acceleration and the expected angle included in one parameter group as the target expected acceleration and the target expected angle based on at least one expected control quantity corresponding to each parameter group.

14. A storage medium characterized by comprising a stored program, wherein a device on which the storage medium is stored is controlled to execute the vehicle automatic driving control method according to any one of claims 1 to 10 when the program is executed.

15. A human-computer interaction device, characterized in that the device comprises a storage medium, and one or more processors, the storage medium being coupled to the processors, the processors being configured to execute program instructions stored in the storage medium; the program instructions when executed perform the vehicle autopilot control method of any one of claims 1 to 10.