CN115303262A - Vehicle control method, device, terminal device and computer readable storage medium - Google Patents

Abstract

The present application is applicable to the field of control technology, and provides a vehicle control method, device, terminal device, and computer-readable storage medium, including: during the process of parking the vehicle in the target area, recording the time when the vehicle is parked in the target area. Parking path; in the process of parking the vehicle out of the target area, obtain the parking position of the vehicle in real time; determine the steering wheel angle according to the position deviation between the parking position and the parking path; according to the Steering wheel angle controls the vehicle to park out of the target area along the parking path. Through the above method, the vehicle can be automatically controlled to return along the original road, which improves the intelligence of automatic driving.

Description

Vehicle control method, device, terminal device, and computer-readable storage medium

technical field

The present application belongs to the technical field of control, and in particular relates to a vehicle control method, device, terminal equipment and computer-readable storage medium.

Background technique

With the development of intelligent control technology, the automatic driving function of vehicles is becoming more and more perfect, and the frequency of users' application of it is also increasing. The existing automatic driving function usually controls the vehicle to drive according to a fixed route, or automatically plans a driving route in a wide area. But when the vehicle enters an unknown tight area and cannot exit by making a U-turn, existing autonomous driving functions become powerless. In this case, it is usually switched to manual driving mode, and the driver controls the vehicle to back up. This method relies heavily on the driver's ability to control the vehicle. When the driver is inexperienced or in a state of mental stress, collision accidents are prone to occur. It can be seen that the existing automatic driving function has a low degree of intelligence.

Contents of the invention

Embodiments of the present application provide a vehicle control method, device, terminal equipment, and computer-readable storage medium, which can effectively improve the intelligence level of automatic driving.

In the first aspect, the embodiment of the present application provides a vehicle control method, including:

During the process of parking the vehicle into the target area, recording the parking path of the vehicle into the target area;

Acquiring the parking position of the vehicle in real time during the process of the vehicle parking out of the target area;

determining a steering wheel rotation angle according to a position deviation between the parking out position and the parking in path;

The vehicle is controlled to park out of the target area along the parking path according to the steering wheel angle.

In the embodiment of the present application, since the parking route of the vehicle into the target area is a completed route, it means that the route can be guaranteed to pass, so recording the route is equivalent to saving a reference route. When the vehicle needs to park out of the target area, it is equivalent to using the recorded parking path as a reference path to control the vehicle to park in the target area. When the vehicle enters an unknown narrow area and cannot exit through a U-turn, the above method can automatically control the vehicle to return along the original road, improving the intelligence of automatic driving.

In a possible implementation manner of the first aspect, the target area includes a plurality of first position points, and during the process of parking the vehicle into the target area, recording the parking of the vehicle into the target area path, including:

During the process of the vehicle parking into the target area, each time the vehicle reaches one of the first position points, acquire a three-dimensional point cloud representing the environment where the first position point is located and the position coordinates of the first position point ;

calculating pose transformation data of the vehicle between every two adjacent first position points according to the three-dimensional point cloud of a plurality of the first position points;

The parking path is generated according to the pose transformation data of the vehicle between every two adjacent first location points and the location coordinates of each of the first location points.

In a possible implementation manner of the first aspect, the acquiring the parking position of the vehicle during the process of parking the vehicle out of the target area includes:

During the process of the vehicle parking out of the target area, calculate the pose information of the vehicle in real time;

Data filtering is performed on the pose information to obtain the parked-out position.

In a possible implementation manner of the first aspect, the determining the steering wheel angle according to the position deviation between the parking-out position and the parking-in path includes:

Acquiring gear position information corresponding to the vehicle at the parking position, wherein the gear position information indicates the gear position of the vehicle passing through the parking position during the process of parking into the target area;

If the gear position information indicates forward movement, then determine the steering wheel angle according to the position deviation between the preview point and the parking position, wherein the preview point is a position point in the parking path;

If the gear position information indicates reverse, the steering wheel rotation angle is determined according to the position deviation between the parking-out position and the parking-in path.

In a possible implementation manner of the first aspect, the determining the steering wheel angle according to the position deviation between the preview point and the parking position includes:

calculating a first lateral tracking error, wherein the first lateral tracking error represents a lateral distance from the center of the rear axle of the vehicle at the parking position to the preview point;

calculating a first front wheel angle according to the first lateral tracking error and a first control law, wherein the first control law represents a functional relationship between the first lateral tracking error and the front wheel angle of the vehicle;

The steering wheel angle is determined according to the first front wheel angle.

In a possible implementation manner of the first aspect, the determining the steering wheel angle according to the position deviation between the parking-out position and the parking-in path includes:

calculating a second lateral tracking error, wherein the second lateral tracking error represents the distance from the center of the front axle of the vehicle at the parking position to the parking path;

calculating an angular tracking error representing an angular difference between a heading angle of the vehicle at the parked out position and a heading angle of the vehicle at the second location point;

Calculate the second front wheel rotation angle according to the second lateral tracking error, the angular tracking error and a second control law, wherein the second control law represents the second lateral tracking error, the angular tracking error The functional relationship between the track error and the front wheel angle of the vehicle;

The steering wheel angle is determined according to the second front wheel angle.

In a possible implementation manner of the first aspect, the method further includes:

During the process of the vehicle parking out of the target area, if the gear information corresponding to the current position of the vehicle is different from the gear information corresponding to the previous position, switch according to the gear information corresponding to the current position of the vehicle The gear of the vehicle.

In a second aspect, the embodiment of the present application provides a vehicle control device, including:

a path recording unit, configured to record the parking path of the vehicle into the target area during the process of parking the vehicle into the target area;

a position obtaining unit, configured to obtain the parking position of the vehicle in real time during the process of the vehicle parking out of the target area;

an angle calculation unit, configured to determine a steering wheel rotation angle according to a position deviation between the parking position and the parking path;

A vehicle control unit, configured to control the vehicle to park out of the target area along the parking path according to the steering wheel angle.

In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, The vehicle control method described in any one of the above-mentioned first aspects is realized.

In a fourth aspect, the embodiment of the present application provides a computer-readable storage medium. The embodiment of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and the computer program is processed The vehicle control method described in any one of the above first aspects is realized when the controller is executed.

In a fifth aspect, an embodiment of the present application provides a computer program product, which, when the computer program product is run on a terminal device, causes the terminal device to execute the vehicle control method described in any one of the above first aspects.

It can be understood that, for the beneficial effects of the above-mentioned second aspect to the fifth aspect, reference can be made to the relevant description in the above-mentioned first aspect, and details will not be repeated here.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the accompanying drawings that need to be used in the descriptions of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are only for the present application For some embodiments, those of ordinary skill in the art can also obtain other drawings based on these drawings without paying creative efforts.

FIG. 1 is a schematic diagram of the composition of a vehicle control system provided by an embodiment of the present application;

FIG. 2 is a schematic flow chart of a vehicle control method provided in an embodiment of the present application;

Fig. 3 is a schematic geometrical diagram of the backward preview tracking algorithm provided by the embodiment of the present application;

Fig. 4 is a schematic geometric diagram of the forward error feedback tracking algorithm provided by the embodiment of the present application;

FIG. 5 is a schematic diagram of an application scenario provided by an embodiment of the present application;

Fig. 6 is a structural block diagram of a vehicle control device provided by an embodiment of the present application;

FIG. 7 is a schematic structural diagram of a terminal device provided by an embodiment of the present application.

Detailed ways

In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and/or components, but does not exclude one or more other Presence or addition of features, wholes, steps, operations, elements, components and/or collections thereof.

It should also be understood that the term "and/or" used in the description of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

As used in this specification and the appended claims, the term "if" may be construed, depending on the context, as "when" or "once" or "in response to determining" or "in response to detecting ". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, to mean "once determined" or "in response to the determination" or "once detected [the described condition or event] ]” or “in response to detection of [described condition or event]”.

In addition, in the description of the specification and appended claims of the present application, the terms "first", "second", "third" and so on are only used to distinguish descriptions, and should not be understood as indicating or implying relative importance.

Reference to "one embodiment" or "some embodiments" or the like in the specification of the present application means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in other embodiments," etc. in various places in this specification are not necessarily All refer to the same embodiment, but mean "one or more but not all embodiments" unless specifically stated otherwise.

Firstly, the application background of the embodiment of the present application is introduced. When the vehicle enters an unknown narrow area and cannot turn around and exit, such as parking in a garage or parking space, driving into an alley, or passing through a narrow gap between two workshops, the automatic driving function often becomes powerless. In this case, it is usually switched to manual driving mode, and the driver controls the vehicle to back up. This method relies heavily on the driver's ability to control the vehicle. When the driver is inexperienced or has blind spots, collision accidents are prone to occur. The existing automatic driving function has a low degree of intelligence and cannot meet the driving needs of unknown narrow areas.

In order to solve the above problems, an embodiment of the present application provides a vehicle control method. In this method, when the vehicle is parked in an unknown narrow area, the parking path is recorded; when the vehicle needs to park out of the unknown narrow area, according to the position deviation between the parking position and the recorded parking path, real-time Calculate the steering wheel angle to control the vehicle in real time to get out of the unknown narrow area along the parking path according to the steering wheel angle. The above method can realize automatic driving under complex road conditions, has high control precision, effectively reduces the driving load of the driver, improves the intelligence of the vehicle, and does not need to add additional hardware equipment.

The following describes the vehicle control system involved in the embodiment of the present application. Referring to FIG. 1 , it is a schematic composition diagram of a vehicle control system provided by an embodiment of the present application. As shown in Figure 1, the vehicle control system may include an information acquisition layer, a control layer and an execution layer. Each layer can be connected through CAN bus communication. During the application process, the information acquisition layer sends the acquired data about vehicle driving to the control layer, the control layer plans the driving path (such as the parking path and the parking path) and the required control amount according to the received data, and the execution layer controls the vehicle The associated devices execute the programmed control quantities.

Among them, the information acquisition layer may include various sensors, such as wheel speed sensors, transmission control units, steering wheel angle sensors, obstacle detection sensors, and visual sensors. The wheel speed sensor is used to obtain the rotational speed of the non-driven wheels on both sides of the vehicle, and obtain the midpoint speed of the rear axle after taking the average value. The transmission control unit is used to obtain the forward/reverse gear of the vehicle. The steering wheel angle sensor is used to obtain the steering wheel angle. Obstacle detection sensors (such as cameras, radars, etc.) are used to detect obstacles around the vehicle. Vision sensors are used to obtain environmental information during driving (such as 3D point clouds, 2D images, etc.).

The control layer can include a positioning calculation module, a power-off storage module, a data recording module, a human-computer interaction module, a forward control module, a reverse control module, an actuator handshake module, and an obstacle alarm module. The positioning calculation module is used to calculate the parking position of the vehicle, including the parking positioning unit and the parking positioning unit. See the following embodiments for details. The forward control module is used to calculate the forward control strategy, such as the forward error feedback tracking strategy described in the following embodiments. The retreat control module is used to calculate the retreat control strategy, such as the retreat preview tracking strategy described in the following embodiments.

The execution layer may include power steering (EPS, Electric Power Steering), human-machine interface (HMI, Human Machine Interface) and driving operation devices (such as gear shifter, brake device, throttle, etc.).

Referring to FIG. 2 , it is a schematic flowchart of a vehicle control method provided by an embodiment of the present application. As an example but not a limitation, the method may include the following steps:

S101. During the process of parking the vehicle into the target area, record the parking path of the vehicle into the target area.

The target area in the embodiment of the present application may refer to a narrow area where the vehicle cannot turn around.

In the embodiment of the present application, it may be executed by the parking positioning unit of the positioning calculation module in the control layer described in the above embodiments.

In some embodiments, after the vehicle is started, the driving route can be recorded in real time. When the storage space is full, the latest records overwrite the original records. Usually, the vehicle's return route (ie, the parking route) is the latest parking route. Therefore, this method can not only ensure that the driving data is not lost, but also ensure that the recorded parking route can be called when the vehicle returns.

In other embodiments, the recording function can be enabled by the user through the HMI. For example, the user sends an opening instruction to the execution layer through the HMI, and the execution layer sends the opening instruction to the control layer. After receiving the opening instruction, the human-computer interaction module in the control layer instructs the data recording module to record the driving data received from the information acquisition layer. .

Of course, the above two recording methods can be alternated. For example, after the vehicle is started, the driving path is recorded in real time; when the user turns off the recording function through the HMI, the control layer stops recording the driving path. For another example, after the vehicle is started, the driving route is not recorded by default; when the user enables the recording function through the HMI, the control layer starts to record the driving route.

In some embodiments, the target area includes a plurality of first location points. Ways to record the parking path may include:

During the process of the vehicle parking into the target area, each time a first location point is reached, the three-dimensional point cloud representing the environment where the first location point is located and the location coordinates of the first location point are obtained; according to The three-dimensional point cloud calculates the pose transformation data of the vehicle between every two adjacent first position points; according to the pose transformation data of the vehicle between every two adjacent first position points , and the position coordinates of each first position point to generate the parking path.

One way of setting the first position point is: when the driving distance of the vehicle reaches a preset distance, a first position point is reached. For example, when the vehicle travels more than 10cm, it reaches a first location point, and the effective location coordinates and three-dimensional point cloud of the first location point are recorded, and the current gear information is stored at the same time.

Another way of setting the first position point is: setting the recording period in advance, and recording a first position point every interval of the recording period during the driving time of the vehicle. For example, when the vehicle speed is greater than 10 miles and less than 20 miles, record a first position point every 10s; when the vehicle speed is greater than 20 miles and less than 30 miles, record a first position point every 5s; and so on, for Set different recording periods for different vehicle speeds.

In the embodiment of the present application, the 3D point cloud may be acquired by lidar. The 3D point cloud can also be acquired by cameras mounted on the vehicle. For example, select a camera (or binocular camera, or depth camera) with an intersecting field of view on the vehicle body, and perform parameter calibration on it in advance; during driving, use the calibrated camera to obtain the 3D point cloud of the environment. Every time a first position point is reached, a frame of three-dimensional point cloud is obtained, that is, two adjacent frames of three-dimensional point cloud correspond to two adjacent first position points.

利用矩阵分解(如SVD分解)计算P和P′的位姿变换数据P′＝R·P+t，R为旋转矩阵，t为位移矩阵。In the embodiment of the present application, the way to calculate the pose transformation data between every two adjacent first position points may be: match the ORB features of two adjacent frames of 3D point clouds, assuming that the two frames match A set of feature points is obtained as:

Use matrix decomposition (such as SVD decomposition) to calculate the pose transformation data P'=R·P+t of P and P', where R is the rotation matrix and t is the displacement matrix.

Through the above method, as long as the coordinates of an initial position are obtained, the parking trajectory can be obtained according to the sequentially obtained pose transformation data between adjacent position points.

It should be noted that in the embodiment of the present application, the recorded parking path may refer to the recorded discrete data, including the respective position coordinates of multiple first position points, and the pose transformation between every two adjacent position points data. The recorded parking path may also be a curve, which is fitted according to the respective position coordinates of a plurality of first position points and the pose transformation data between every two adjacent position points.

Optionally, while acquiring the pose data of each first position point, the gear position information of the vehicle at each first position point can also be recorded. If the reverse gear is recorded as -1, the non-reverse gear is recorded as 1. Of course, different forward gears can also be recorded as different data, such as the first gear is recorded as 1, the second gear is recorded as 2, and so on. The recording form of the gear position information is not specifically limited here. The purpose of recording the gear position information is to adjust different control strategies during the subsequent process of the vehicle parking out of the target area.

S102. During the process of the vehicle parking out of the target area, acquire the parking position of the vehicle in real time.

In the embodiment of the present application, it may be executed by the parking out positioning unit of the positioning calculation module in the control layer described in the above embodiments.

In some embodiments, during the process of the vehicle parking out of the target area, the pose information of the vehicle is calculated in real time, and the pose information is recorded as the parking position of the vehicle. The specific method is as follows:

(1) First, the vehicle motion satisfies the formula of Ackermann steering and rigid body circular motion:

In the formula: v _r is the midpoint velocity of the rear axle, ω is the yaw rate, R is the turning radius, δ _f is the turning radius of the front wheel, and L is the wheelbase. Among them, ω is unknown data, R and L are known parameters of the vehicle, and δ _f and v _r are data that can be obtained through sensors. Simplifying the above formula, the yaw rate can be calculated as:

In the formula: i is the angular transmission ratio of the steering wheel.

(2) Secondly, according to the geometric relationship of vehicle movement, the longitudinal and abscissa coordinates of the midpoint of the rear axle are further obtained as follows:

In the formula: T _s is the discrete calculation cycle (the time interval between every two adjacent position points), ω _k and θ _k are the yaw rate and heading angle at time k, respectively, and x _k and y _k are respectively The vertical and horizontal coordinates relative to the starting point; v _l and v _r are the wheel speeds of the left and right non-driving wheels respectively.

In practical applications, it is considered that the vehicle speed is not constant when the vehicle is parked out of the target area, and the data of vehicle speed and yaw rate have certain noises. If the above calculation method is followed, the calculated berth out position has low accuracy. In order to improve the accuracy of real-time positioning, in the embodiment of the present application, data filtering is performed on the above-mentioned calculated pose information, and the filtered pose information is recorded as the parking position. Optionally, an extended Kalman filter may be used for data filtering processing. Specifically, on the basis of the above steps (1) and (2), add the filtering process of step (3), as follows:

(3) Extended Kalman filter

In the formula: v _{x, k+1} , v _{y, k+1} are the lateral and longitudinal vehicle speeds at k+1 time respectively, a _x and a _y are the lateral and longitudinal accelerations respectively, W and V are process noise and measurement noise respectively. Among them, W is the given data, and V is equivalent to a matrix composed of ω calculated by the above steps.

Through the above data filtering processing, the noise data can be effectively filtered out, and the positioning accuracy can be effectively improved.

S103. Determine a steering wheel rotation angle according to a position deviation between the parking-out position and the parking-in path.

In this step, the recorded parking path can be regarded as a reference path. Existing navigation methods can be used to calculate the position deviation between the parking position and the reference path, so as to determine the steering wheel angle, and then realize the control of the vehicle.

S104. Control the vehicle to park out of the target area along the parking path according to the steering wheel angle.

In some embodiments, during the process of the vehicle parking out of the target area, the vehicle control method further includes: if the gear information corresponding to the current position of the vehicle is different from the gear information corresponding to the previous position, then according to The gear position information corresponding to the current position of the vehicle switches the gear position of the vehicle.

Exemplarily, as shown in FIG. 5 , during the process of parking the vehicle into the target area, the vehicle moves forward from the starting point of parking to the reverse position; and the vehicle moves backward from the shift position to the end point of parking. Correspondingly, during the process of parking the vehicle out of the target area, the vehicle first advances and then retreats. When the vehicle reaches the shift position, the vehicle gear is changed from the forward gear to the reverse gear.

In the embodiment described in FIG. 2 above, since the parking route of the vehicle into the target area is a completed route, it means that the route can be guaranteed to pass, so recording the route is equivalent to saving a reference route. When the vehicle needs to park out of the target area, it is equivalent to using the recorded parking path as a reference path to control the vehicle to park in the target area. When the vehicle enters an unknown narrow area and cannot exit through a U-turn, the above method can automatically control the vehicle to return along the original road, improving the intelligence of automatic driving.

For the above step S103, in some embodiments, the same algorithm can be used to calculate the steering wheel angle when the vehicle is parked out of the target area, whether it is moving forward or backward.

However, due to the fact that the geometric relationship between the vehicle and the parking path is different during the forward and backward process of the vehicle, if the steering wheel angle is calculated according to the same algorithm, the accuracy of the calculation result may be low, and it is impossible to guarantee the accurate positioning of the vehicle. Go back the same way.

In order to improve the control accuracy, in one embodiment, the parking path is divided into forward and reverse segmented paths, and different algorithms are set for different segmented paths. Specifically, S103 may include the following steps:

I. Obtain gear position information corresponding to the vehicle at the parking position, wherein the gear position information indicates the gear position of the vehicle passing through the parking position during the process of parking into the target area.

As described in the above embodiment, the recorded parking path may refer to the recorded discrete data, or may be a fitted curve. When the park-in path refers to discrete data, correspondingly, in step I, the position point in the park-in path that matches the park-out position may be a first position point closest to the park-out position. When the park-in path refers to the fitted curve, the position point in the park-in path that matches the park-out position can be a position point closest to the fitted curve (the position point is not necessarily the first location point).

When the location point in the parking path that matches the parking location is the first location point, the gear information corresponding to the parking location is the gear information of the first location point. When the location point matching the parking location in the parking path is not the first location point, the parking path can be divided into a forward sub-path and a backward sub-path according to the gear information corresponding to each first location point, and then It is determined whether the parked out position belongs to the forward sub-path or the reversed sub-path, so as to determine the gear information corresponding to the parked out position.

II. If the gear position information indicates forward movement, then determine the steering wheel angle according to the position deviation between the preview point and the parking position, wherein the preview point is a position point in the parking path .

In this step, the gear position information indicates forward movement, in other words, the vehicle is in the forward state when it reaches the current position during the process of parking into the target area. Correspondingly, during the process of the vehicle parking out of the target area, the vehicle should be in the backward state when it reaches the current position. In this case, the steering geometry is satisfied between the vehicle and the parking path, and the steering wheel angle is determined by using the reverse preview tracking algorithm. Specifically, step II may include:

calculating a first lateral tracking error, wherein the first lateral tracking error represents a lateral distance from the center of the rear axle of the vehicle at the parking position to the preview point;

calculating a first front wheel angle according to the first lateral tracking error and a first control law, wherein the first control law represents a functional relationship between the first lateral tracking error and the front wheel angle of the vehicle;

The steering wheel angle is determined according to the first front wheel angle.

Referring to FIG. 3 , it is a schematic geometrical diagram of the backward preview tracking algorithm provided by the embodiment of the present application. As shown in Figure 3, considering the relationship between the wheel rotation angle and the preview point (g _x , g _y ) in the parking path, the preview point starts from the center of the rear axle of the vehicle, and the distance to the parking path is l _d (default value). At the same time, the lateral distance from the center of the rear axle of the vehicle to the preview point (g _x , g _y ) is defined as the first lateral tracking error e _ld , and the triangular geometric relationship is:

The preview distance l _d is positively correlated with the speed of the midpoint v of the rear axle:

l _d =k·v

In the formula: k is the calibration parameter. The front wheel rotation angle of the vehicle is:

δ＝tan ^-1 (L/R)

Combining the above equations, the first control law is obtained as

In the formula: δ ₁ represents the first front wheel angle of the vehicle.

Based on the above-mentioned first control law, the front wheel rotation angle of the vehicle can be calculated in real time according to the first lateral tracking error and related data. Since there is a definite conversion relationship between the vehicle front wheel angle and the steering wheel angle, the steering wheel angle can be determined according to the calculated vehicle front wheel angle.

Exemplarily, the information acquisition layer sends the rear axle midpoint speed, the position coordinates of the current position and the vehicle attitude data obtained in real time to the control layer; the control layer calculates the first lateral tracking error in real time according to the received data, and then According to the first lateral tracking error and the first control law, the first front wheel angle is calculated in real time, and converted into the steering wheel angle, and sent to the execution layer; the execution layer controls the steering wheel rotation according to the received steering wheel angle, and according to the information acquisition layer Real-time feedback of the steering wheel angle data to determine whether the steering wheel is in place.

III. If the gear position information indicates reverse, then determine the steering wheel angle according to the position deviation between the parking out position and the parking in path.

In this step, the gear position information indicates the reverse, in other words, the vehicle is in the reverse state when it reaches the current position during the process of parking into the target area. Correspondingly, when the vehicle is parked out of the target area, the vehicle should be in the forward state when it reaches the current position. In this case, the ideal Ackermann steering relationship is satisfied between the vehicle and the parking path, and the forward error feedback tracking algorithm is used to determine the steering wheel angle. Specifically, step III may include:

calculating a second lateral tracking error, wherein the second lateral tracking error represents the distance from the center of the front axle of the vehicle at the parking position to the parking path;

calculating an angular tracking error representing an angular difference between a heading angle of the vehicle at the parked out position and a heading angle of the vehicle at the second location point;

Calculate the second front wheel rotation angle according to the second lateral tracking error, the angular tracking error and a second control law, wherein the second control law represents the second lateral tracking error, the angular tracking error The functional relationship between the track error and the front wheel angle of the vehicle;

The steering wheel angle is determined according to the second front wheel angle.

Referring to FIG. 4 , it is a schematic geometric diagram of the forward error feedback tracking algorithm provided by the embodiment of the present application. As shown in FIG. 4 , the ideal Ackermann steering relationship tan(δ)=L/R is satisfied between the vehicle and the parking path. The distance from the center of the front axle of the vehicle to the desired trajectory is defined as the second lateral tracking error e _f , and the angular tracking error at the front wheel of the vehicle can be expressed as θ _e = θ-θ _c , where θ and θ _c are respectively The course angle recorded in the berthing path and the course angle recorded in the berthing path are combined with the above two equations to obtain the second control law:

In the formula, δ2 is the _second front wheel angle of the vehicle.

It should be noted that the XY coordinate system shown in FIG. 4 may be set based on the starting position of the mooring. In other words, the subsequent real-time calculated data are all based on the starting position of the mooring. For example, θ _c is equivalent to the change value of the heading angle of the vehicle at the current position relative to the initial position of unparking.

Based on the above second control law, the second front wheel rotation angle can be calculated in real time according to the second lateral tracking error, angular tracking error and related data. Since there is a definite conversion relationship between the front wheel angle of the vehicle and the steering wheel angle, the steering wheel angle can be determined according to the calculated vehicle front wheel angle.

Exemplarily, the information acquisition layer sends the real-time obtained midpoint speed of the rear axle, the position coordinates of the current position and the vehicle attitude data to the control layer; the control layer calculates the second lateral tracking error and angle in real time according to the received data Tracking error, and then according to the second lateral tracking error, angular tracking error and the first control law, calculate the second front wheel angle in real time, and convert it into steering wheel angle, and send it to the execution layer; The rotation angle controls the rotation of the steering wheel, and judges whether the steering wheel is in place according to the steering wheel rotation angle data fed back in real time by the information acquisition layer.

In the above embodiment, according to the change of the gear position, the parking route is divided into a forward sub-route and a reverse sub-route. Through segmental control of different sub-paths, the steering wheel angle can be calculated more accurately to achieve precise control of the vehicle.

For example, refer to FIG. 5 , which is a schematic diagram of an application scenario provided by an embodiment of the present application. The application scenario shown in (a) in FIG. 5, in this application scenario, the vehicle backs up and parks into the target area. During the process of parking the vehicle out of the target area, it is enough to control the vehicle to call the forward strategy to park out. The application scenario shown in (b) in Figure 5, in this application scenario, in the process of parking into the target area, the vehicle first advances from the starting point of parking into the shift position, then switches to the reverse gear, and continues to move from The shift position is reversed to the park end point. Correspondingly, in the process of parking out of the vehicle, the forward strategy is first called to control the vehicle to park from the parking end point to the shift position, and the gear is switched to the reverse gear at the shift position, and then the reverse strategy is called to control the vehicle from the shift position Park out to the start point of park in.

In some application situations, when the vehicle successfully returns to the starting point of parking, the control system can prompt the user to complete the parking out through the HMI, so as to instruct the user to switch to the manual driving mode.

In the embodiment of the present application, since the parking route of the vehicle into the target area is a completed route, it means that the route can be guaranteed to pass, so recording the route is equivalent to saving a reference route. When the vehicle needs to park out of the target area, it is equivalent to using the recorded parking path as a reference path to control the vehicle to park in the target area. When the vehicle enters an unknown narrow area and cannot exit through a U-turn, the above method can automatically control the vehicle to return along the original road, improving the intelligence of automatic driving.

Further, in the embodiment of the present application, the parking path is divided into forward and reverse segmented paths, and different control algorithms are set for different segmented paths. The calculation accuracy of the rotation angle of the reverse disc is effectively improved, thereby improving the control accuracy of the vehicle.

It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present application.

Corresponding to the vehicle control method described in the above embodiments, FIG. 6 is a structural block diagram of a vehicle control device provided by the embodiment of the present application. For convenience of description, only the parts related to the embodiment of the present application are shown.

Referring to Figure 6, the device includes:

a path recording unit 61, configured to record the parking path of the vehicle into the target area during the process of parking the vehicle into the target area;

A position acquiring unit 62, configured to acquire the parking position of the vehicle in real time during the process of the vehicle parking out of the target area;

An angle calculation unit 63, configured to determine the steering wheel angle according to the position deviation between the parking position and the parking path;

The vehicle control unit 64 is configured to control the vehicle to park out of the target area along the parking path according to the steering wheel angle.

Optionally, the target area includes a plurality of first location points, and the path recording unit 61 is also used for:

During the process of the vehicle parking into the target area, each time a first location point is reached, a three-dimensional point cloud representing the environment where the first location point is located and the location coordinates of the first location point are acquired;

calculating pose transformation data of the vehicle between every two adjacent first position points according to the three-dimensional point cloud of a plurality of the first position points;

The parking path is generated according to the pose transformation data of the vehicle between every two adjacent first location points and the location coordinates of each first location point.

Optionally, the location acquisition unit 62 is also used for:

During the process of the vehicle parking out of the target area, calculate the pose information of the vehicle in real time;

Data filtering is performed on the pose information to obtain the parked-out position.

Optionally, the angle calculation unit 63 is also used for:

Acquiring gear position information corresponding to the vehicle at the parking position, wherein the gear position information indicates the gear position of the vehicle passing through the parking position during the process of parking into the target area;

If the gear position information indicates forward movement, then determine the steering wheel angle according to the position deviation between the preview point and the parking position, wherein the preview point is a position point in the parking path;

If the gear position information indicates reverse, the steering wheel rotation angle is determined according to the position deviation between the parking-out position and the parking-in path.

Optionally, the angle calculation unit 63 is also used for:

calculating a first lateral tracking error, wherein the first lateral tracking error represents a lateral distance from the center of the rear axle of the vehicle at the parking position to the preview point;

calculating a first front wheel angle according to the first lateral tracking error and a first control law, wherein the first control law represents a functional relationship between the first lateral tracking error and the front wheel angle of the vehicle;

The steering wheel angle is determined according to the first front wheel angle.

Optionally, the angle calculation unit 63 is also used for:

calculating a second lateral tracking error, wherein the second lateral tracking error represents the distance from the center of the front axle of the vehicle at the parking position to the parking path;

calculating an angular tracking error representing an angular difference between a heading angle of the vehicle at the parked out position and a heading angle of the vehicle at the second location point;

Calculate the second front wheel rotation angle according to the second lateral tracking error, the angular tracking error and a second control law, wherein the second control law represents the second lateral tracking error, the angular tracking error The functional relationship between the track error and the front wheel angle of the vehicle;

The steering wheel angle is determined according to the second front wheel angle.

Optionally, the vehicle control unit 64 is also used for:

During the process of the vehicle parking out of the target area, if the gear information corresponding to the current position of the vehicle is different from the gear information corresponding to the previous position, switch according to the gear information corresponding to the current position of the vehicle The gear of the vehicle.

It should be noted that the information interaction and execution process between the above-mentioned devices/units are based on the same concept as the method embodiment of the present application, and its specific functions and technical effects can be found in the method embodiment section. I won't repeat them here.

In addition, the vehicle control device shown in FIG. 6 may be a software unit, a hardware unit, or a combination of software and hardware built into an existing terminal device, or it may be integrated into the terminal device as an independent pendant, or it may be Exists as an independent terminal device.

Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used for illustration. In practical applications, the above-mentioned functions can be assigned to different functional units, Completion of modules means that the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit, and the above-mentioned integrated units may adopt hardware It can also be implemented in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the above system, reference may be made to the corresponding process in the foregoing method embodiments, and details will not be repeated here.

FIG. 7 is a schematic structural diagram of a terminal device provided by an embodiment of the present application. As shown in FIG. 7, the terminal device 7 of this embodiment includes: at least one processor 70 (only one is shown in FIG. 7), a processor, a memory 71, and stored in the memory 71 and can be processed in the at least one processor A computer program 72 running on the processor 70, when the processor 70 executes the computer program 72, implements the steps in any of the above embodiments of the vehicle control method.

The terminal device may be computing devices such as desktop computers, notebooks, palmtop computers, and cloud servers. The terminal device may include, but not limited to, a processor and a memory. Those skilled in the art can understand that FIG. 7 is only an example of the terminal device 7, and does not constitute a limitation on the terminal device 7. It may include more or less components than those shown in the figure, or combine some components, or different components. , for example, may also include input and output devices, network access devices, and so on.

The so-called processor 70 can be a central processing unit (Central Processing Unit, CPU), and the processor 70 can also be other general processors, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit , ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.

The storage 71 may be an internal storage unit of the terminal device 7 in some embodiments, such as a hard disk or memory of the terminal device 7 . The memory 71 may also be an external storage device of the terminal device 7 in other embodiments, such as a plug-in hard disk equipped on the terminal device 7, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, flash memory card (Flash Card), etc. Further, the memory 71 may also include both an internal storage unit of the terminal device 7 and an external storage device. The memory 71 is used to store operating system, application program, boot loader (Boot Loader), data and other programs, such as the program code of the computer program. The memory 71 can also be used to temporarily store data that has been output or will be output.

The embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in each of the foregoing method embodiments can be realized.

An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the foregoing method embodiments when executed.

If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the procedures in the methods of the above embodiments in the present application can be completed by instructing related hardware through computer programs, and the computer programs can be stored in a computer-readable storage medium. The computer program When executed by a processor, the steps in the above-mentioned various method embodiments can be realized. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program codes to a device/terminal device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory ( RAM, Random Access Memory), electrical carrier signals, telecommunication signals, and software distribution media. Such as U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunication signals under legislation and patent practice.

In the above-mentioned embodiments, the descriptions of each embodiment have their own emphases, and for parts that are not detailed or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

In the embodiments provided in this application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the device/terminal device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units Or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still implement the foregoing embodiments Modifications to the technical solutions described in the examples, or equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the application, and should be included in the Within the protection scope of this application.

Claims (10)

1. A vehicle control method, characterized in that, comprising: During the process of parking the vehicle into the target area, recording the parking path of the vehicle into the target area; Acquiring the parking position of the vehicle in real time during the process of the vehicle parking out of the target area; determining a steering wheel rotation angle according to a position deviation between the parking out position and the parking in path; The vehicle is controlled to park out of the target area along the parking path according to the steering wheel angle. 2. The vehicle control method according to claim 1, wherein the target area includes a plurality of first position points, and during the process of parking the vehicle into the target area, it is recorded that the vehicle parks into the target Parking routes for the area, including: During the process of the vehicle parking into the target area, each time the vehicle reaches one of the first position points, acquire a three-dimensional point cloud representing the environment where the first position point is located and the position coordinates of the first position point ; calculating pose transformation data of the vehicle between every two adjacent first position points according to the three-dimensional point cloud of a plurality of the first position points; The parking path is generated according to the pose transformation data of the vehicle between every two adjacent first location points and the location coordinates of each of the first location points. 3. The vehicle control method according to claim 1, wherein the acquiring the parking position of the vehicle in real time during the process of the vehicle parking out of the target area comprises: During the process of the vehicle parking out of the target area, calculate the pose information of the vehicle in real time; Data filtering is performed on the pose information to obtain the parked-out position. 4. The vehicle control method according to claim 1, wherein the determining the steering wheel angle according to the position deviation between the parking position and the parking path comprises: Acquiring gear position information corresponding to the parking position of the vehicle, wherein the gear position information indicates the gear position when the vehicle passes the parking position during the process of parking into the target area; If the gear position information indicates forward movement, then determine the steering wheel angle according to the position deviation between the preview point and the parking position, wherein the preview point is a position point in the parking path; If the gear position information indicates reverse, the steering wheel rotation angle is determined according to the position deviation between the parking-out position and the parking-in path. 5. The vehicle control method according to claim 4, wherein the determining the steering wheel angle according to the position deviation between the preview point and the parking position comprises: calculating a first lateral tracking error, wherein the first lateral tracking error represents a lateral distance from the center of the rear axle of the vehicle at the parking position to the preview point; calculating a first front wheel angle according to the first lateral tracking error and a first control law, wherein the first control law represents a functional relationship between the first lateral tracking error and the front wheel angle of the vehicle; The steering wheel angle is determined according to the first front wheel angle. 6. The vehicle control method according to claim 4, wherein the determining the steering wheel angle according to the position deviation between the parking position and the parking path comprises: calculating a second lateral tracking error, wherein the second lateral tracking error represents the distance from the center of the front axle of the vehicle at the parking position to the parking path; calculating an angular tracking error representing an angular difference between a heading angle of the vehicle at the parked out position and a heading angle of the vehicle at the second location point; Calculate the second front wheel rotation angle according to the second lateral tracking error, the angular tracking error and a second control law, wherein the second control law represents the second lateral tracking error, the angular tracking error The functional relationship between the track error and the front wheel angle of the vehicle; The steering wheel angle is determined according to the second front wheel angle. 7. The vehicle control method according to claim 4, further comprising: During the process of the vehicle parking out of the target area, if the gear information corresponding to the current position of the vehicle is different from the gear information corresponding to the previous position, switch according to the gear information corresponding to the current position of the vehicle The gear of the vehicle. 8. A vehicle control device, characterized in that it comprises: a path recording unit, configured to record the parking path of the vehicle into the target area during the process of parking the vehicle into the target area; a position obtaining unit, configured to obtain the parking position of the vehicle in real time during the process of the vehicle parking out of the target area; an angle calculation unit, configured to determine a steering wheel rotation angle according to a position deviation between the parking position and the parking path; A vehicle control unit, configured to control the vehicle to park out of the target area along the parking path according to the steering wheel angle. 9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and operable on the processor, characterized in that, when the processor executes the computer program, the computer program according to claim The method described in any one of 1 to 7. 10. A computer-readable storage medium storing a computer program, wherein the computer program implements the method according to any one of claims 1 to 7 when executed by a processor.

Images