Method for controlling parking-out direction in automatic parking and electronic equipment

Abstract

The invention provides a parking direction control method in automatic parking and electronic equipment. The method comprises the following steps: in response to vehicle power-on, recording vehicle positioning data in real time; in response to stopping of the vehicle, determining front and back parking directions of the vehicle based on vehicle forward direction data acquired from the vehicle positioning data; determining whether the type of the current parking space of the vehicle is a vertical parking space or a horizontal parking space based on a vehicle course angle obtained from the vehicle positioning data and constraint conditions; when the current parking space of the vehicle is the vertical parking space, determining the left and right parking directions of the vehicle based on the front and back parking directions of the vehicle and the vehicle course angle; when the current parking space of the vehicle is a horizontal parking space, determining the left and right parking directions of the vehicle according to the leftward or rightward offset distance of the vehicle obtained from the vehicle positioning data; and controlling the vehicle to park based on the determined front-back parking direction of the vehicle, the current parking space type of the vehicle and the left-right parking direction of the vehicle. The reliability and precision of automatic parking can be effectively improved.

Description

Technical Field

[0001] This application belongs to the technical field of intelligent driving, and particularly relates to the technical field of vehicle position control in automatic parking. Background Art

[0002] Currently, with the improvement of the intelligence level of automobiles, the automatic parking system has gradually become one of the important functions of vehicles. Its technical goal is to help drivers complete the parking operation and improve convenience and safety. However, for existing automatic parking systems, when a vehicle performs an automatic exit from a parking space, the following problems still exist:

[0003] 1. The vehicle positioning is not accurate enough

[0004] Existing systems mainly rely on a single wheel pulse sensor or IMU (Inertial Measurement Unit) for vehicle positioning. This method may be affected by the accumulation of sensor errors, resulting in insufficient accuracy of position and attitude estimation. Especially in complex environments, vehicle positioning errors will have a greater impact on parking decisions.

[0005] 2. The determination of parking direction and type is not comprehensive

[0006] Existing technologies usually only rely on the relative position of the vehicle body and the parking space in the determination of parking type and direction, lacking a comprehensive analysis of vehicle attitude and trajectory data. This may lead to misjudgment or incorrect recommended exit directions when the parking space is limited, affecting the actual parking effect.

[0007] 3. Lack of effective utilization of environmental perception information

[0008] When determining the exit direction in the current automatic parking system, the influence of the surrounding environment of the parking space (such as obstacles, drivable areas, etc.) is often ignored, resulting in a decrease in parking safety. In addition, the data fusion of visual perception and ultrasonic detection in existing systems is relatively simple, and multi-source information cannot be fully utilized to optimize the exit decision.

[0009] 4. Problems of data interruption and system restart

[0010] After the vehicle loses power or the system restarts, existing systems cannot retain the previous positioning data, resulting in the need to re-establish a positioning reference, increasing the parking waiting time and reducing the user experience. Summary of the Invention

[0011] This application provides a method for controlling the exit direction in automatic parking and an electronic device, which are used to improve the reliability and accuracy of automatic parking.

[0012] In a first aspect, an embodiment of the present application provides a method for controlling the parking-out direction in automatic parking, including: in response to the vehicle being powered on, real-time recording vehicle positioning data; in response to the vehicle stopping, obtaining vehicle forward direction data from the vehicle positioning data, and determining the front and rear parking-out directions of the vehicle based on the vehicle forward direction data; obtaining the vehicle heading angle from the vehicle positioning data, and determining whether the vehicle's current parking space type is a vertical parking space or a horizontal parking space based on the constraint conditions of the vehicle heading angle: when the vehicle's current parking space is a vertical parking space, determining the left and right parking-out directions of the vehicle based on the vehicle's front and rear parking-out directions and the vehicle heading angle; when the vehicle's current parking space is a horizontal parking space, obtaining the distance by which the vehicle deviates to the left or right from the vehicle positioning data, and determining the left and right parking-out directions of the vehicle based on the distance by which the vehicle deviates to the left or right; controlling the vehicle to park based on the determined front and rear parking-out directions of the vehicle, the vehicle's current parking space type, and the vehicle's left and right parking-out directions.

[0013] In one implementation of the first aspect, the step of, in response to the vehicle being powered on, real-time recording vehicle positioning data includes: in response to the vehicle being powered on, establishing the vehicle's own coordinate system, and recording the vehicle's initial position and attitude data based on the vehicle's own coordinate system; during the vehicle's driving process, real-time recording vehicle positioning data based on wheel pulse signal interpolation and the heading angle.

[0014] In one implementation of the first aspect, it further includes: in response to the vehicle stopping, converting the real-time recorded vehicle positioning data from the vehicle's own coordinate system to the vehicle's local dynamic coordinate system; wherein, the vehicle's local dynamic coordinate system has the vehicle body center as the origin, the vehicle forward direction as the x-axis, and the vehicle left direction as the y-axis; screening the vehicle positioning data within a preset distance range; wherein, the abscissa of the data points in the screened vehicle positioning data satisfies the abscissa constraint condition composed of the preset distance and the vehicle length, the ordinate satisfies the ordinate constraint condition composed of the preset distance and the vehicle width, and the heading angle satisfies the heading angle constraint condition.

[0015] In one implementation of the first aspect, the step of obtaining vehicle forward direction data from the vehicle positioning data, and determining the front and rear parking-out directions of the vehicle based on the vehicle forward direction data includes: sorting the screened vehicle positioning data in chronological order to form a vehicle positioning data array; respectively obtaining the x coordinates of each vehicle forward direction data from the vehicle positioning data array, and calculating the sum of all x coordinates; determining whether the sum of the x coordinates is greater than 0: if so, determining the vehicle's parking-out direction as forward; if not, determining the vehicle's parking-out direction as backward.

[0016] In an implementation manner of the first aspect, the constraint conditions include: First constraint condition: Whether the index idx1 corresponding to the maximum value θ of the heading angle in the vehicle positioning data array satisfies idx1 < k * l; where l is the length of the vehicle positioning data array and k is a fixed value; Second constraint condition: Whether the maximum value θ of the heading angle in the vehicle positioning data array max satisfies θ max less than the first angle preset value θ 1 ; Third constraint condition: Whether the heading angle θ at the earliest time in the vehicle positioning data array last satisfies θ last less than the second angle preset value θ 2 ; Determining whether the current parking space type of the vehicle is a vertical parking space or a horizontal parking space based on the first constraint condition of the vehicle's heading angle includes: detecting whether the vehicle's heading angle simultaneously satisfies the first constraint condition, the second constraint condition, and the third constraint condition: if so, determining that the current parking space type of the vehicle is a horizontal parking space; if not, determining that the current parking space type of the vehicle is a vertical parking space.

[0017] In an implementation manner of the first aspect, determining the left and right parking out directions of the vehicle based on the front and back parking out directions of the vehicle and the vehicle's heading angle includes: obtaining the maximum value θ of the absolute value of the heading angle in the vehicle positioning data array max1 ; When the parking out direction of the vehicle is forward: if θ max1 is greater than θ 3 , determining that the parking out direction of the vehicle is to the right; if θ max1 is less than -θ 3 , determining that the parking out direction of the vehicle is to the left; if -θ 3 ≤θ max1 ≤θ 3 , determining that the parking out direction of the vehicle is straight ahead; When the parking out direction of the vehicle is backward: if θ max1 is greater than θ 3 , determining that the parking out direction of the vehicle is to the left; if θ max1 is less than -θ 3 , determining that the parking out direction of the vehicle is to the right; if -θ 3 ≤θ max1 ≤θ 3 , determining that the parking out direction of the vehicle is straight ahead, where θ 3 is the third angle preset value.

[0018] In an implementation manner of the first aspect, determining the left and right parking out directions of the vehicle based on the distance by which the vehicle deviates left or right includes: obtaining the maximum value y of the absolute value of the ordinate in the vehicle positioning data array max ; Judging the maximum value y of the absolute value of the ordinate maxIs it greater than 0: If yes, determine the maximum value y of the absolute value of the ordinate max is the distance that the vehicle deviates to the left, and the parking-out direction of the vehicle is to the left; if not, determine the maximum value y of the absolute value of the ordinate max is the distance that the vehicle deviates to the right, and the parking-out direction of the vehicle is to the right.

[0019] In an implementation manner of the first aspect, it further includes: detecting whether the vehicle is automatically parked in: if yes, obtaining vehicle parking-out control parameters based on automatic parking in, and controlling vehicle parking based on the vehicle parking-out control parameters; if not, detecting whether the current parking space where the vehicle is located is a row of parking spaces: if yes, obtaining the type of the parking space detected by the vehicle vision sensor, and controlling vehicle parking based on the type of the parking space detected by the vehicle vision sensor, the determined front and rear parking-out directions of the vehicle, and the left and right parking-out directions of the vehicle; if not, controlling vehicle parking based on the determined front and rear parking-out directions of the vehicle, the type of the current parking space where the vehicle is located, and the left and right parking-out directions of the vehicle.

[0020] In an implementation manner of the first aspect, it further includes: storing the recorded vehicle positioning data and / or storing the determined front and rear parking-out directions of the vehicle, the type of the current parking space where the vehicle is located, and the left and right parking-out directions of the vehicle.

[0021] In an implementation manner of the first aspect, it further includes: identifying an impassable area in the parking-out direction based on a lidar or a vision sensor, and controlling vehicle parking in combination with the impassable area in the parking-out direction.

[0022] In a second aspect, an embodiment of the present application provides an electronic device, where the electronic device includes a processor and a memory; the memory stores program instructions; the processor is configured to run the program instructions to execute the parking-out direction control method in any one of the first aspects of the present application.

[0023] The parking-out direction control method provided by the embodiment of the present application has the following beneficial effects:

[0024] 1. The present application combines information on the vehicle position, vehicle attitude, and heading angle to analyze and determine the parking type (horizontal / vertical) and the parking-out direction (left / right / straight), and accurately distinguishes horizontal and vertical parking spaces according to multiple conditional constraints of the heading angle, improving the robustness of the algorithm, effectively reducing the error rate of parking and parking-out operations, enhancing the reliability and accuracy of automatic parking, and also significantly reducing the driver operation complexity and improving the usage convenience by automatically recommending the parking-out direction and type.

[0025] 2. This application realizes the precise positioning of the vehicle's position and attitude by establishing an OC coordinate system and combining the wheel pulse interpolation method. The data is stored in a rolling update manner and has a power-off protection function to ensure the continuity and reliability of the data.

[0026] 3. This application adopts a coordinate transformation and screening method to convert the absolute coordinate system data into data in the vehicle's local coordinate system, improving the flexibility and accuracy of data processing.

[0027] 4. In this application, visual perception, ultrasonic detection, and environmental information are introduced in the calculation of the parking-out direction and type, ensuring more comprehensive parking-out decisions in complex environments. And the non-parking-out directions are identified through the freespace of ultrasonic and visual detection to further avoid potential risks during the parking-out process.

[0028] 5. This application is applicable to various parking scenarios such as horizontal parking spaces, vertical parking spaces, and complex row parking spaces. It can provide an efficient parking solution in different environments, and has strong compatibility with existing parking assistance systems, facilitating rapid deployment and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It shows the overall flowchart of the parking-out direction control method in automatic parking according to an embodiment of this application.

[0030] Figure 2 It shows the schematic diagram of the principle of establishing a coordinate system and real-time recording of vehicle positioning data in the parking-out direction control method in automatic parking according to an embodiment of this application.

[0031] Figure 3 It shows the flowchart of coordinate system transformation and screening of vehicle positioning data in the parking-out direction control method in automatic parking according to an embodiment of this application.

[0032] Figure 4 It shows the flowchart of determining the front and rear parking-out directions of the vehicle in the parking-out direction control method in automatic parking according to an embodiment of this application.

[0033] Figure 5 It shows the schematic diagram of the principle of determining whether the vehicle's current parking space type is a vertical parking space or a horizontal parking space in the parking-out direction control method in automatic parking according to an embodiment of this application.

[0034] Figure 6 It shows the flowchart of the principle of determining the left and right parking-out directions of the vehicle when the vehicle's current parking space type is a vertical parking space in the parking-out direction control method in automatic parking according to an embodiment of this application.

[0035] Figure 7It shows a principle flowchart for determining the left and right parking-out directions of a vehicle when the current parking space type of the vehicle in the parking-out direction control method in automatic parking according to an embodiment of the present application is a horizontal parking space.

[0036] Figure 8 It shows a principle flowchart for combining automatic parking-in and visual sensors to control vehicle parking in the parking-out direction control method in automatic parking according to an embodiment of the present application.

[0037] Figure 9 It shows a schematic structural diagram of an electronic device according to an embodiment of the present application.

[0038] Element number description

[0039] 100 Electronic device

[0040] 101 Memory

[0041] 102 Processor

[0042] 103 Display

[0043] Steps S100 - S600

[0044] Steps S201 - S202

[0045] Steps S210 - S250

[0046] Steps S310 - S330

[0047] Steps S410 - S430

[0048] Steps S510 - S540

[0049] Steps S610 - S650 Detailed implementation manners

[0050] The following uses specific specific examples to illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific implementation manners, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0051] The purpose of this embodiment is to overcome the problems existing in the existing automatic parking system, such as insufficient positioning accuracy, incomplete determination of the parking-out direction and parking space type, low utilization rate of environmental information, and data interruption. This embodiment provides a method for controlling the parking-out direction in automatic parking, which is a method for determining the parking direction and parking space type based on vehicle positioning, visual perception, and environmental information fusion. The specific objectives include:

[0052] 1. Provide a high-precision vehicle positioning method. Through wheel pulse interpolation and attitude estimation, centimeter-level positioning accuracy is achieved, and through data rolling storage and power-off preservation, the continuity and reliability of data are ensured.

[0053] 2. Provide a method for determining the parking-out direction and type based on vehicle trajectory data and heading angle. Combining statistical analysis, the accuracy and robustness of the determination are improved.

[0054] 3. Realize the fusion of multi-source perception data. In the determination of the parking direction, visual and environmental information are fully utilized, and ultrasonic and visual perception are used to optimize the parking-out decision, improving the safety of the system.

[0055] 4. Optimize the system response speed and user experience, ensure that the vehicle quickly restores positioning data and recommended parking-out directions after power-off restart, reduce operation complexity, and improve the intelligent level of the system.

[0056] Next, the technical solutions in the embodiments of the present application will be described in detail with reference to the attached Figure 1 to the attached Figure 9 , so that those skilled in the art can understand and implement the method for controlling the parking-out direction in automatic parking of this embodiment without creative labor.

[0057] Figure 1 It is shown as the flowchart of the method for controlling the parking-out direction in automatic parking in the embodiments of the present application. As Figure 1 shown, the method for controlling the parking-out direction in automatic parking provided by the embodiments of the present application includes the following steps S100 to S600.

[0058] Step S100, in response to the vehicle being powered on, record the vehicle positioning data in real time;

[0059] Step S200, in response to the vehicle stopping, obtain the vehicle forward direction data from the vehicle positioning data, and determine the front and rear parking-out directions of the vehicle based on the vehicle forward direction data;

[0060] Step S300, obtain the vehicle heading angle from the vehicle positioning data, and determine whether the parking space type where the vehicle is currently located is a vertical parking space or a horizontal parking space based on the constraint conditions of the vehicle heading angle:

[0061] Step S400, when the current parking space of the vehicle is a perpendicular parking space, determine the left and right parking-out directions of the vehicle based on the front and rear parking-out directions of the vehicle and the vehicle's heading angle;

[0062] Step S500, when the current parking space of the vehicle is a parallel parking space, obtain the distance by which the vehicle is offset to the left or right from the vehicle positioning data, and determine the left and right parking-out directions of the vehicle based on the distance by which the vehicle is offset to the left or right;

[0063] Step S600, control the vehicle to park based on the determined front and rear parking-out directions of the vehicle, the type of the current parking space of the vehicle, and the left and right parking-out directions of the vehicle.

[0064] In this embodiment, the method for controlling the parking-out direction in automatic parking combines information on the vehicle position, vehicle attitude, and heading angle, analyzes and determines the parking type (parallel / perpendicular) and the parking-out direction (left / right / straight), accurately distinguishes parallel and perpendicular parking spaces according to multiple conditions of the heading angle, improves the robustness of the algorithm, effectively reduces the error rate of parking and parking-out operations, enhances the reliability and accuracy of automatic parking, and can also significantly reduce the driver's operation complexity and improve the usability by automatically recommending the parking-out direction and type.

[0065] The following combines Att Figure 2 to Att Figure 8 to elaborate in detail on the above steps S100 to S600 of the method for controlling the parking-out direction in automatic parking in this embodiment.

[0066] Step S100, in response to the vehicle being powered on, record the vehicle positioning data in real time.

[0067] Figure 2 Shown is the schematic diagram of establishing a coordinate system and recording the vehicle positioning data in real time in the method for controlling the parking-out direction in automatic parking according to an embodiment of the present application. As Figure 2 shown, in one implementation manner of this embodiment, the recording the vehicle positioning data in real time in response to the vehicle being powered on includes:

[0068] 1) In response to the vehicle being powered on, establish the coordinate system of the vehicle itself, and record the initial position and attitude data of the vehicle based on the coordinate system of the vehicle itself.

[0069] The coordinate system of the vehicle itself (OC coordinate system) is an absolute coordinate system, with the center of the rear axle of the vehicle as the origin, the x-axis pointing in the direction of the vehicle's head, and the y-axis pointing to the left side of the vehicle. The coordinate system of the vehicle itself is used to describe the initial position and attitude data of the vehicle. Among them, when the vehicle starts or is powered on, the vehicle control system can use the data provided by the wheel speed sensors and the data of other sensors (such as accelerometers, gyroscopes, etc.) to jointly establish the coordinate system of the vehicle itself. Specifically, the vehicle control system will determine the axial direction and the origin position of the coordinate system of the vehicle itself according to the rotation of the wheels and the initial attitude of the vehicle, and record the initial position and attitude data.

[0070] Among them, when the vehicle is powered on, the GPS receiver in the vehicle will receive signals from satellites, determine the position information such as the longitude, latitude and altitude of the vehicle, and this position information is transmitted to the vehicle's ECU as the initial position of the vehicle.

[0071] In order to improve the positioning accuracy, the vehicle control system can also perform map matching in combination with high-precision map data. By comparing and correcting the GPS data with the road network information in the map, the position of the vehicle on the road can be determined more accurately.

[0072] In this embodiment, the attitude data of the vehicle is obtained by using the IMU (Inertial Measurement Unit) in the vehicle. Among them, the IMU integrates a combined sensor of an accelerometer and a gyroscope. The accelerometer is used to measure the acceleration changes of the vehicle in various directions, while the gyroscope is used to measure the angular velocity changes of the vehicle around three axes (roll, pitch, yaw). Through these data, the vehicle control system can calculate the attitude information of the vehicle in real time, such as the body tilt angle, the heading angle, etc.

[0073] In addition, it should be noted that in addition to the inertial navigation module, the vehicle can also establish the coordinate system of the vehicle itself through geomagnetic sensors or lane line recognition technologies. These technologies can also provide the current orientation and position of the vehicle, and are more applicable in some environments, such as underground parking lots with weak GPS signals.

[0074] 2) During the vehicle's driving process, the vehicle positioning data is recorded in real time based on the interpolation of the wheel pulse signal and the heading angle.

[0075] The wheel pulse signal is generated by wheel speed sensors installed on the wheels, such as Hall effect sensors, electromagnetic sensors, etc., and is used to measure the rotation speed of the wheels. By interpolating the wheel pulse signal, such as quadratic interpolation, cubic interpolation or higher-order interpolation, the vehicle displacement between two wheel pulse signals can be estimated more accurately, and then the position information of the vehicle (longitude and latitude or plane rectangular coordinates) can be obtained, generating a series of continuous coordinate points of the vehicle position information.

[0076] The heading angle refers to the angle between the vehicle's driving direction and the geographical north direction, usually expressed in degrees (0° to 360°). The heading angle can be obtained by measuring the angular velocity changes of the vehicle around three axes (roll, pitch, yaw) with a gyroscope.

[0077] In this embodiment, a preset positioning accuracy for recording vehicle position information is set. For example, based on wheel pulse signal interpolation and heading angle estimation, the vehicle's position information (x, y, θ) is recorded in real time with an accuracy of 20 centimeters. In this way, by establishing an OC coordinate system and combining with the wheel pulse interpolation method, this embodiment can achieve precise positioning of the vehicle's position, with an accuracy of up to 20 centimeters.

[0078] This embodiment realizes precise positioning of the vehicle's position and attitude by establishing an OC coordinate system and combining with the wheel pulse interpolation method.

[0079] In addition, this embodiment further includes: storing the recorded vehicle positioning data. Among them, the vehicle positioning data is stored in a rolling update manner to implement the power-off preservation function and ensure the continuity and reliability of the data. For example, 150 groups of vehicle positioning data are stored in a rolling manner with a 30-meter window.

[0080] Step S200, in response to the vehicle stopping, obtain the vehicle's forward direction data from the vehicle positioning data, and determine the forward and backward parking out directions of the vehicle based on the vehicle's forward direction data.

[0081] In this embodiment, before obtaining the vehicle's forward direction data from the vehicle positioning data and determining the forward and backward parking out directions of the vehicle based on the vehicle's forward direction data, coordinate transformation and screening of the vehicle positioning data are also included.

[0082] Figure 3 Shown is a flowchart of coordinate transformation and screening of vehicle positioning data in the parking out direction control method for automatic parking in an embodiment of the present application. As Figure 3 shown, in one implementation manner of this embodiment, the following steps S201 and step S202 are further included.

[0083] Step S201, in response to the vehicle stopping, convert the recorded vehicle positioning data from the vehicle's own coordinate system to the vehicle's local dynamic coordinate system; wherein, the vehicle's local dynamic coordinate system takes the center of the vehicle body as the origin, the vehicle's forward direction as the x-axis, and the vehicle's left direction as the y-axis.

[0084] In this embodiment, converting all the position and attitude information in the vehicle positioning data from the absolute coordinate system to the vehicle's current local dynamic coordinate system to form a new data array can improve the flexibility and accuracy of data processing.

[0085] Step S202: Screen the vehicle positioning data within a preset distance range. Among them, for the data points in the screened vehicle positioning data, the abscissa satisfies the abscissa constraint condition composed of the preset distance and the vehicle length, the ordinate satisfies the ordinate constraint condition composed of the preset distance and the vehicle width, and the heading angle satisfies the heading angle constraint condition.

[0086] Among them, the value range of the preset distance is 4m to 8m. For example, when screening the valid data points within 5 meters in the vehicle stop state, the data points (abscissa x, ordinate y, heading angle θ) need to satisfy the following conditions:

[0087] 1) Abscissa constraint condition: -L - 5m < x < L + 5m, where L is the vehicle length;

[0088] 2) Ordinate constraint condition: -W - 5m < y < W + 5m, where W is the vehicle width;

[0089] 3) Heading angle constraint condition:

[0090] Among them, the preset distance and the constraint angle of the heading angle θ can be adjusted according to the adaptability of different vehicles.

[0091] This embodiment adopts a coordinate transformation and screening method to convert the absolute coordinate system data into the data in the vehicle local coordinate system, improving the flexibility and accuracy of data processing.

[0092] After completing the coordinate transformation and screening of the vehicle positioning data, determine the parking out direction and parking space type of the vehicle positioning data after the coordinate transformation and screening.

[0093] Figure 4 Shown is a flowchart of determining the front and rear parking out directions of a vehicle in the parking out direction control method of automatic parking according to an embodiment of the present application. As Figure 4 shown, in one implementation manner of this embodiment, obtaining the vehicle forward direction data from the vehicle positioning data and determining the front and rear parking out directions of the vehicle based on the vehicle forward direction data includes the following steps S210 to step S250.

[0094] Step S210: Sort the screened vehicle positioning data in chronological order to form a vehicle positioning data array;

[0095] Step S220: Respectively obtain the x coordinates of each vehicle forward direction data from the vehicle positioning data array and calculate the sum of all x coordinates;

[0096] Step S230: Determine whether the sum of the x - coordinates is greater than 0. If yes, continue to execute Step S240: Determine that the parking - out direction of the vehicle is forward. If not, continue to execute Step S250: Determine that the parking - out direction of the vehicle is backward.

[0097] Accumulate the x - coordinate values of the upcoming vehicle forward direction to obtain the total sum of the x - coordinates. Judge the positive or negative of the sum of the x - coordinates and check whether the accumulated sum of the x - coordinates is greater than 0. If the total sum of the x - coordinates is greater than 0, determine that the parking - out direction of the vehicle is "forward"; if the total sum of the x - coordinates is not greater than 0, determine that the parking - out direction of the vehicle is "backward".

[0098] In this embodiment, after determining the forward and backward parking - out directions of the vehicle, continue to judge whether the current parking space type of the vehicle is a vertical parking space or a horizontal parking space.

[0099] Step S300: Obtain the vehicle heading angle from the vehicle positioning data, and determine whether the current parking space type of the vehicle is a vertical parking space or a horizontal parking space based on the constraint conditions of the vehicle heading angle.

[0100] Figure 5 Shown is a schematic diagram of the principle of determining whether the current parking space type of the vehicle is a vertical parking space or a horizontal parking space in the parking - out direction control method of automatic parking in an embodiment of the present application. As Figure 5 shown, determining whether the current parking space type of the vehicle is a vertical parking space or a horizontal parking space includes the following steps S310 to S330.

[0101] In an implementation manner of this embodiment, Step S310 includes: The constraint conditions include:

[0102] 1) The first constraint condition: Whether the index idx1 corresponding to the maximum value of the heading angle θ in the vehicle positioning data array satisfies idx1 < k * l; where l is the length of the vehicle positioning data array and k is a fixed value;

[0103] 2) The second constraint condition: Whether the maximum value of the heading angle θ in the vehicle positioning data array max satisfies θ max is less than the first angle preset value θ 1 ;

[0104] 3) The third constraint condition: Whether the heading angle θ at the earliest time in the vehicle positioning data array last satisfies θ last is less than the second angle preset value θ 2 .

[0105] In this embodiment, determining whether the vehicle's current parking space type is a vertical parking space or a horizontal parking space based on the first constraint condition of the vehicle's heading angle includes: detecting whether the vehicle's heading angle simultaneously satisfies the first constraint condition, the second constraint condition, and the third constraint condition: if so, continue to execute step S320: determine that the vehicle's current parking space type is a horizontal parking space; if not, continue to execute step S330: determine that the vehicle's current parking space type is a vertical parking space.

[0106] That is, in this embodiment, if the following three conditions are simultaneously satisfied, it is determined as a horizontal parking space, otherwise it is a vertical parking space:

[0107] First constraint condition: The value range of the fixed value k is 0.1 to 0.4. For example, the value of k is 0.2, that is, the index idx1 corresponding to the maximum value of the heading angle θ in the array satisfies idx1 < 0.2 * l;

[0108] Second constraint condition: The first angle preset value θ 1 The value range is to For example, it is That is, the maximum value of the heading angle θ in the array

[0109] Third constraint condition: The second angle preset value θ 2 The value range is to For example, it is That is, the earliest heading angle in the array

[0110] This embodiment innovatively introduces a multi-condition constraint rule for the heading angle, such as the maximum value of the heading angle, the time index, etc., to accurately distinguish between horizontal and vertical parking spaces, which can improve the robustness of the algorithm. By flexibly configuring the fixed value and the angle preset value, the body size (vehicle length L, vehicle width W) parameters of different vehicle models (such as SUVs, sedans) are dynamically adjusted to ensure that the data within the data screening range is applicable to various body sizes. The threshold value in the heading angle screening condition adapts to the parking space requirements of different vehicle models, ensuring the accuracy and generality of the parking type determination.

[0111] In this embodiment, after determining whether the vehicle's current parking space type is a vertical parking space or a horizontal parking space, the determination of the left and right parking out directions is respectively performed for the vertical parking space and the horizontal parking space. That is, continue to execute step S400 and step S500.

[0112] Step S400: When the current parking space of the vehicle is a perpendicular parking space, determine the left and right parking-out directions of the vehicle based on the front and rear parking-out directions of the vehicle and the vehicle heading angle; Step S500: When the current parking space of the vehicle is a parallel parking space, obtain the distance by which the vehicle deviates left or right from the vehicle positioning data, and determine the left and right parking-out directions of the vehicle based on the distance by which the vehicle deviates left or right; wherein, there is no order of execution between Step S400 and Step S500. It is also possible to first execute Step S500 and then execute Step S400, or to execute Step S400 and Step S500 simultaneously.

[0113] Figure 6 It shows a principle flowchart for determining the left and right parking-out directions of a vehicle when parking in a perpendicular parking space in the parking-out direction control method during automatic parking according to an embodiment of the present application. As Figure 6 shown, in one implementation of this embodiment, when the current parking space type of the vehicle is a perpendicular parking space, the determining the left and right parking-out directions of the vehicle based on the front and rear parking-out directions of the vehicle and the vehicle heading angle includes the following steps S410 to S430.

[0114] Step S410: Obtain the maximum value θ of the absolute value of the heading angle in the vehicle positioning data array max1 ;

[0115] Step S420: When the parking-out direction of the vehicle is forward: If θ max1 is greater than θ 3 , then determine that the parking-out direction of the vehicle is to the right; if θ max1 is less than -θ 3 , then determine that the parking-out direction of the vehicle is to the left; if -θ 3 ≤θ max1 ≤θ 3 , then determine that the parking-out direction of the vehicle is straight ahead;

[0116] Step S430: When the parking-out direction of the vehicle is backward: If θ max1 is greater than θ 3 , then determine that the parking-out direction of the vehicle is to the left; if θ max1 is less than -θ 3 , then determine that the parking-out direction of the vehicle is to the right; if -θ 3 ≤θ max1 ≤θ 3 , then determine that the parking-out direction of the vehicle is straight ahead, where θ 3 is the third angle preset value.

[0117] Among them, the value range of the third angle preset value θ 3 is from to For example, it is taken as That is, in the determination of the left or right parking out of the vertical parking space, the course angle θ corresponding to the maximum absolute value of the course angle in the vehicle positioning data array is taken. max1 , under the condition of forward parking out: θ max1 > Then it is determined as right, Then it is determined as left, otherwise it is determined as straight; under the condition of backward parking out: Then it is determined as left, Then it is determined as right, otherwise it is determined as straight.

[0118] Figure 7 It shows the principle flowchart of determining the left and right parking out directions of the vehicle when the current parking space type of the vehicle is a horizontal parking space in the parking out direction control method of automatic parking in an embodiment of the present application. As Figure 7 shown, in one implementation manner of this embodiment, when the current parking space type of the vehicle is a horizontal parking space, the determining of the left and right parking out directions of the vehicle based on the distance of the vehicle offset to the left or right includes the following steps S510 to step S540.

[0119] Step S510, obtain the maximum value y of the absolute value of the ordinate in the vehicle positioning data array max ;

[0120] Step S520, determine whether the maximum value y of the absolute value of the ordinate max is greater than 0: if so, continue to execute step S530: determine that the maximum value y of the absolute value of the ordinate max is the distance of the vehicle offset to the left, and the parking out direction of the vehicle is left; if not, continue to execute step S540: determine that the maximum value y of the absolute value of the ordinate max is the distance of the vehicle offset to the right, and the parking out direction of the vehicle is right.

[0121] That is, in the determination of the left / right parking out of the horizontal parking space, the maximum value y of the absolute value of the ordinate in the vehicle positioning data array is taken max , y max > 0, then it is determined as left, otherwise right.

[0122] Therefore, in this embodiment, by integrating the information of the vehicle position, attitude and course angle, scientific statistical analysis and determination are carried out on the parking type (horizontal / vertical) and the parking out direction (left / right / straight). Through comprehensive data fusion and multi-condition determination rules, the error rate of parking and parking out operations is reduced, the running safety of the vehicle is improved, and the accuracy and robustness of the determination are enhanced.

[0123] Step S600, control the vehicle to park based on the determined forward and backward parking out directions of the vehicle, the current parking space type of the vehicle, and the left and right parking out directions of the vehicle.

[0124] In this embodiment, the parking-out direction and type are automatically recommended, significantly reducing the operation complexity of the driver, improving the usability, and enhancing the intelligence of the parking system.

[0125] In addition, in this embodiment, visual and environmental information is fully utilized in the determination of the parking direction, and the ultrasonic and visual perception are used to optimize the parking-out decision, realizing the fusion of multi-source perception data and improving the system safety. Figure 8 It shows the principle flowchart of combining automatic parking-in and visual sensors to control vehicle parking in the parking-out direction control method of automatic parking in an embodiment of the present application. As Figure 8 shown, in an implementation manner of this embodiment, the following steps S610 to S650 are further included.

[0126] Step S610, detecting whether the vehicle is in automatic parking-in:

[0127] If yes, continue to execute step S620: obtaining the vehicle parking-out control parameters based on automatic parking-in, and controlling vehicle parking based on the vehicle parking-out control parameters;

[0128] If no, continue to execute step S630: detecting whether the current parking space where the vehicle is located is a row of parking spaces:

[0129] If yes, continue to execute step S640: obtaining the parking space type detected by the vehicle visual sensor, and controlling vehicle parking based on the parking space type detected by the vehicle visual sensor, the determined front and rear parking-out directions of the vehicle, and the left and right parking-out directions of the vehicle; that is, visual data is preferentially used in the scenarios of horizontal or vertical row of parking spaces to ensure the reliability of the decision.

[0130] If no, continue to execute step S650: controlling vehicle parking based on the determined front and rear parking-out directions of the vehicle, the type of the current parking space where the vehicle is located, and the left and right parking-out directions of the vehicle.

[0131] In this embodiment, vehicle parking can be directly controlled based on the determined front and rear parking-out directions of the vehicle, the type of the current parking space where the vehicle is located, and the left and right parking-out directions of the vehicle, or the parking data priority can be pre-configured, and vehicle parking can be controlled according to the parking data priority. When automatic parking ends, the confidence parking-in type is determined, and at the same time, the parking-out direction is optimized in real time to prompt the driver with the best parking-out method that can be selected.

[0132] When it is determined that an automatic parking-out operation needs to be performed, the perception data priority is sensed, and the following data is preferentially trusted to obtain the final parking-out direction and parking space type during parking:

[0133] 1) When automatically parking in, the preferred confidence parking-in type. If it is determined that the current vehicle performed a parking-in operation in a parking space before and it was an automatic parking-in, then preferably use the parking-in type obtained based on the automatic parking-in as the parameter for this parking-out.

[0134] 2) For adjacent horizontal or vertical parking spaces, the preferred confidence parking space type detected visually. If it is determined that it is not an automatic parking-in, then further determine whether there is a parking space type detected visually for the current vehicle. If there is, then preferably use the parking space type detected visually and use it as the parameter for this parking-out.

[0135] 3) In other cases, use the calculation results of vehicle positioning and trajectory analysis obtained through the above steps S100 to S600. If none of the above situations occur, then directly determine and execute the parking-out based on the parking-out direction and parking space type obtained in step S600.

[0136] In this embodiment, during the automatic parking-in process, the preferred confidence parking-in type is used, and for adjacent parking spaces, the preferred confidence visual recognition result is used. Combining the calculation results of step S600 to optimize the output decision can improve the accuracy of parking space type judgment.

[0137] In this embodiment, visual perception, ultrasonic detection, and environmental information are introduced in the calculation of the parking-out direction and type to achieve the fusion of multi-source perception data. In the determination of the parking-out direction, visual and environmental information is fully utilized, and the parking-out decision is optimized through ultrasonic and visual perception to ensure that the parking-out decision in a complex environment is more comprehensive and improve the system safety.

[0138] In one implementation manner of this embodiment, it further includes: identifying the non-passable area of the parking-out direction based on a lidar or a visual sensor, and controlling the vehicle to park in combination with the non-passable area of the parking-out direction. Among them, the visual sensor preferably uses a monocular camera or a stereo camera. On this basis, through multi-sensor fusion technology, combining the advantages of different sensors, the accuracy and robustness of parking space detection can be further improved.

[0139] That is, in this embodiment, when performing automatic parking, it is also possible to further combine vision and lidar to identify obstacles and freespace (referring to the area available for driving around the vehicle), identify the non-passable area of the parking-out direction, optimize the parking-out decision, and provide a safe direction recommendation. Moreover, in this embodiment, a lidar is used instead of an ultrasonic sensor to obtain freespace data, which can further improve the obstacle detection accuracy. In this embodiment, the non-parkable direction is identified through ultrasonic and visual detection of freespace, further avoiding potential risks during the parking-out process.

[0140] In this embodiment, when the vehicle stops, the calculation of the parking-out direction and type is automatically triggered. At the same time, in this embodiment, after the calculation, the recommended parking-out direction and type or multiple sets of vehicle positioning data are saved to ensure that the data is still available after power-off or restart. In this way, when the vehicle starts and confirms that it needs to use the parking-out direction and type obtained by the method of this embodiment for automatic parking, the saved vehicle positioning data can be directly called for calculation to obtain the recommended parking-out direction and type (if the vehicle position has a slight displacement), or the previously calculated parking-out direction and type can be directly called (if the vehicle position has not changed) to perform automatic parking. Therefore, this embodiment can optimize the system response speed and user experience, ensure that the vehicle quickly restores the positioning data and recommended parking-out direction after power-off and restart, avoid data loss, effectively ensure the continuity and reliability of the parking system, reduce the operation complexity, and improve the system intelligence level.

[0141] A specific application example of the parking-out direction control method in the automatic parking of this embodiment is as follows: When the vehicle is powered on, the system establishes an OC coordinate system through the wheel pulse sensor, and interpolates and records the vehicle position and attitude information (x, y, θ) every 20 cm. The vehicle positioning data within 30 m (150 groups) is stored in a rolling manner, and the calculation of the parking-out direction and type is triggered in the vehicle stop state, and the recommended direction is automatically determined in combination with the real-time positioning data. When the vehicle stops, based on the current vehicle positioning data, coordinate transformation is performed to the vehicle local coordinate system, the data within 5 m is filtered, an array of vehicle positioning data is generated and sorted, and the parking-out direction and type are accurately determined through multiple constraint conditions of the heading angle. The vehicle positioning data or the determined parking-out direction and type are saved when the vehicle loses power, ensuring that the system can be quickly restored after restart. This embodiment not only improves the intelligence level of the parking system through accurate vehicle positioning, scientific determination of the parking-out direction and type, and multi-source perception data fusion, but also significantly improves the user experience, safety, and applicability, and has great promotion value and practical significance.

[0142] The protection scope of the parking-out direction control method in the automatic parking described in the embodiments of this application is not limited to the execution order of the steps listed in this embodiment. Any solution achieved by adding or subtracting steps of the prior art and replacing steps according to the principle of this application is included in the protection scope of this application.

[0143] The embodiments of this application also provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the parking-out direction control method provided in any embodiment of this application.

[0144] In the embodiments of the present application, any combination of one or more storage media may be adopted. The storage medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0145] The embodiments of the present application further provide an electronic device. Figure 9 Shown is a schematic structural diagram of the electronic device 100 provided by the embodiments of the present application. In some embodiments, the electronic device may be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), or other terminal devices. In addition, the method for controlling the parking-out direction in the automatic parking provided by the present application may also be applied to databases, servers, and service response systems based on terminal artificial intelligence. The embodiments of the present application do not impose any restrictions on the specific application scenarios of the method for controlling the parking-out direction in the automatic parking.

[0146] As Figure 9 shown, the electronic device 100 provided by the embodiments of the present application includes a memory 101 and a processor 102.

[0147] The memory 101 is used to store a computer program; preferably, the memory 101 includes: various media such as ROM, RAM, magnetic disks, USB flash drives, memory cards, or optical discs that can store program codes.

[0148] Specifically, the memory 101 may include a computer system readable medium in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The electronic device 100 may further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 101 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present application.

[0149] The processor 102 is connected to the memory 101 and is configured to execute the computer program stored in the memory 101, so that the electronic device 100 executes the method for controlling the parking-out direction in automatic parking provided in any embodiment of the present application.

[0150] Optionally, the processor 102 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0151] Optionally, the electronic device 100 in this embodiment may further include a display 103. The display 103 is communicatively connected to the memory 101 and the processor 102 and is configured to display a relevant GUI interaction interface for the method for controlling the parking-out direction in automatic parking.

[0152] In summary, the present application combines information on vehicle position, vehicle attitude, and heading angle to analyze and determine the parking type (parallel / perpendicular) and the parking-out direction (left / right / straight). It accurately distinguishes between parallel and perpendicular parking spaces based on multiple conditional constraints of the heading angle, improving the robustness of the algorithm, effectively reducing the error rate of parking and parking-out operations, enhancing the reliability and accuracy of automatic parking. Moreover, by automatically recommending the parking-out direction and type, it can significantly reduce the operation complexity of the driver and improve the usability. The present application realizes the precise positioning of the vehicle position and attitude by establishing an OC coordinate system and combining the wheel pulse interpolation method. The data is stored in a rolling update manner and has the function of power-off preservation to ensure the continuity and reliability of the data. The present application adopts a coordinate transformation and screening method to convert the absolute coordinate system data into data in the vehicle local coordinate system, improving the flexibility and accuracy of data processing. In the present application, visual perception, ultrasonic detection, and environmental information are introduced in the calculation of the parking-out direction and type to ensure more comprehensive parking-out decisions in complex environments. And the non-parking directions are identified through the freespace of ultrasonic and visual detection to further avoid potential risks during the parking-out process. The present application is applicable to various parking scenarios such as parallel parking spaces, perpendicular parking spaces, and complex row parking spaces, and can provide efficient parking solutions in different environments. Moreover, it has strong compatibility with existing parking assistance systems, facilitating rapid deployment and promotion. Therefore, the present application effectively overcomes various drawbacks in the prior art and has high industrial utilization value.

[0153] The above embodiments are only illustrative of the principles and effects of the present application and are not intended to limit the present application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed in the present application should still be covered by the claims of the present application.

Claims

1. A method for controlling the direction of an automatic parking vehicle, characterized in that: including: Upon vehicle power-on, real-time record vehicle positioning data; Upon vehicle stop, obtain vehicle forward direction data from the vehicle positioning data, and determine the front and rear parking-out directions of the vehicle based on the vehicle forward direction data; Obtain the vehicle heading angle from the vehicle positioning data, and determine whether the current parking space type of the vehicle is a vertical parking space or a horizontal parking space based on the constraint conditions of the vehicle heading angle: When the current parking space of the vehicle is a vertical parking space, determine the left and right parking-out directions of the vehicle based on the front and rear parking-out directions of the vehicle and the vehicle heading angle; When the current parking space of the vehicle is a horizontal parking space, obtain the distance by which the vehicle deviates left or right from the vehicle positioning data, and determine the left and right parking-out directions of the vehicle based on the distance by which the vehicle deviates left or right; Control vehicle parking based on the determined front and rear parking-out directions of the vehicle, the current parking space type of the vehicle, and the left and right parking-out directions of the vehicle.

2. The method for controlling the direction of exiting the automatic parking according to claim 1, characterized in that: The step of upon vehicle power-on, real-time record vehicle positioning data includes: Upon vehicle power-on, establish the coordinate system of the vehicle itself, and record the initial position and attitude data of the vehicle based on the coordinate system of the vehicle itself; During vehicle driving, real-time record vehicle positioning data based on wheel pulse signal interpolation and heading angle.

3. The method for controlling the direction of exiting the automatic parking according to claim 2, characterized in that: It also includes: Upon vehicle stop, convert the real-time recorded vehicle positioning data from the coordinate system of the vehicle itself to the vehicle local dynamic coordinate system; wherein, the vehicle local dynamic coordinate system has the center of the vehicle body as the origin, the vehicle forward direction as the x-axis, and the vehicle left direction as the y-axis; Filter the vehicle positioning data within a preset distance range; wherein, the abscissa of the data points in the filtered vehicle positioning data satisfies the abscissa constraint condition composed of the preset distance and the vehicle length, the ordinate satisfies the ordinate constraint condition composed of the preset distance and the vehicle width, and the heading angle satisfies the heading angle constraint condition.

4. The method for controlling the direction of exiting the automatic parking according to claim 3, characterized in that: The step of obtain vehicle forward direction data from the vehicle positioning data, and determine the front and rear parking-out directions of the vehicle based on the vehicle forward direction data includes: Sort the filtered vehicle positioning data in chronological order to form a vehicle positioning data array; Respectively obtain the x-coordinates of each vehicle forward direction data from the vehicle positioning data array, and calculate the sum of all x-coordinates; Judge whether the sum of the x-coordinates is greater than 0: If so, determine that the parking-out direction of the vehicle is forward; If not, determine that the parking-out direction of the vehicle is backward.

5. The method for controlling the direction of exiting the automatic parking according to claim 4, characterized in that: The constraint conditions include: The first constraint condition: whether the index idx1 corresponding to the maximum value of the heading angle θ in the vehicle positioning data array satisfies idx1 < k * l; wherein, l is the length of the vehicle positioning data array, and k is a fixed value; Second constraint: The maximum heading angle θ in the vehicle positioning data array max Does it satisfy θ max is smaller than the first angle preset value θ1; The third constraint condition: the heading angle θ that is the earliest in the vehicle positioning data array last Does it satisfy θ last is smaller than the second angle preset value θ2; The step of determine whether the current parking space type of the vehicle is a vertical parking space or a horizontal parking space based on the first constraint condition of the vehicle heading angle includes: Detect whether the vehicle heading angle simultaneously satisfies the first constraint condition, the second constraint condition, and the third constraint condition: If so, determine that the current parking space type of the vehicle is a horizontal parking space; If not, determine that the current parking space type of the vehicle is a vertical parking space.

6. The method for controlling the direction of exiting the automatic parking vehicle according to claim 4 or 5, characterized in that: The determining of the left and right parking directions of the vehicle based on the front and rear parking directions of the vehicle and the vehicle heading angle comprises: Get the maximum absolute value of the heading angle in the vehicle positioning data array θ max1 ; When the vehicle is parked forward: If θ max1 If it is greater than θ3, the parking direction of the vehicle is determined to be right; If θ max1 If it is less than -θ3, the parking direction of the vehicle is determined to be left; If -θ3≤θ max1 ≤θ3, the vehicle’s exit direction is determined to be straight ahead; When the vehicle is parked in the reverse direction: If θ max1 If it is greater than θ3, the parking direction of the vehicle is determined to be left; If θ max1 If it is less than -θ3, the parking direction of the vehicle is determined to be right; If -θ3≤θ max1 ≤θ3, it is determined that the parking direction of the vehicle is straight ahead, wherein θ3 is a preset value of the third angle.

7. The method for controlling the direction of exiting the automatic parking according to claim 4 or 5, characterized in that: The determining of the left or right parking direction of the vehicle based on the distance that the vehicle is offset to the left or right includes: Get the maximum value y of the absolute value of the ordinate in the vehicle positioning data array max ; Determine the maximum value y of the absolute value of the ordinate max Is it greater than 0? If so, determine the maximum absolute value y of the ordinate max is the distance the vehicle is offset to the left, and the parking direction of the vehicle is to the left; If not, determine the maximum value y of the absolute value of the ordinate max is the distance the vehicle is offset to the right, and the parking direction of the vehicle is to the right.

8. The method for controlling the direction of exiting the automatic parking according to claim 1, characterized in that: Also includes: Check whether the vehicle is automatically parked: If so, obtaining a vehicle parking exit control parameter based on the automatic parking entry, and controlling the parking of the vehicle based on the vehicle parking exit control parameter; If not, check whether the current parking space of the vehicle is a row parking space: If yes, then obtaining the parking space type detected by the vehicle vision sensor, and controlling the vehicle parking based on the parking space type detected by the vehicle vision sensor, the determined front and rear parking exit directions of the vehicle, and the left and right parking exit directions of the vehicle; If not, the vehicle parking is controlled based on the determined front and rear parking exit directions of the vehicle, the type of parking space currently located by the vehicle, and the left and right parking exit directions of the vehicle.

9. The method for controlling the direction of exiting the automatic parking according to claim 1, characterized in that: Also includes: The recorded vehicle positioning data is stored and / or the determined front and rear parking exit directions of the vehicle, the type of parking space currently occupied by the vehicle, and the left and right parking exit directions of the vehicle are stored.

10. The method for controlling the direction of exiting the automatic parking according to claim 1 or 8, characterized in that: Also includes: The vehicle parking is controlled based on the laser radar or visual sensor and the identification of the impassable area in the parking direction, and in combination with the impassable area in the parking direction.

11. An electronic device, characterized in that: The electronic device comprises: Processor and memory; The memory stores program instructions; The processor is used to run the program instructions to execute the parking direction control method in automatic parking according to any one of claims 1 to 10.

Images