A vehicle positioning method, device and vehicle for automatic parking

Abstract

The application relates to the field of automobile-related technologies, and provides a vehicle positioning method and device for automatic parking and a vehicle. The vehicle positioning method for automatic parking determines corresponding target parking space line information and a planned parking track based on an initial pose of the vehicle and a target parking space determined by a user, determines a target corner point position based on the target parking space line information, controls the vehicle to move according to the parking track, determines corresponding driving parking space line information based on a real-time pose of the vehicle during movement of the vehicle, determines corresponding driving corner point positions based on the driving parking space line information, determines a driving pose of the vehicle based on the target parking space line information, the driving parking space line information, the driving corner point positions and the target corner point positions, and corrects positioning information of the vehicle during parking according to the driving pose. The application improves the positioning accuracy of the vehicle, and can also not increase additional equipment, so that the cost of vehicle positioning correction is more low.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and more specifically, to a vehicle positioning method, device, and vehicle for automatic parking. Background Technology

[0002] With the continuous development of time and technology, autonomous driving is becoming increasingly popular. For autonomous vehicles, automatic parking is an important function of vehicle intelligence. Generally, automatic parking positioning is achieved through two methods. One method mainly uses a geometric model based on wheel pulse signals and vehicle parameters to calculate the vehicle's position and attitude angles. However, this algorithm model is relatively idealized and deviates from the actual vehicle conditions. Furthermore, as the vehicle travels a distance, the accumulated odometer error of the wheel pulse signals increases, leading to poor positioning accuracy. The other method is to add inertial sensors and use Kalman filtering to correct the results of the first method. However, the second method increases costs, and the inherent drift of inertial sensors also leads to lower positioning accuracy. Summary of the Invention

[0003] The purpose of this invention is to provide a vehicle positioning method, apparatus, vehicle, and readable storage medium for automatic parking.

[0004] In a first aspect, the present invention provides a vehicle positioning method for automatic parking, the method comprising:

[0005] Obtain the vehicle's initial pose and the target parking space specified by the user;

[0006] Based on the initial pose and the target parking space, the corresponding target parking space line information and the planned parking trajectory are determined, and the target corner point position is determined based on the target parking space line information;

[0007] The vehicle is controlled to drive along the parking trajectory. During the vehicle's movement, the corresponding driving parking line information is determined based on the vehicle's real-time pose, and the corresponding driving corner point position is determined based on the driving parking line information.

[0008] The vehicle's driving posture is determined based on the target parking space line information, the driving parking space line information, the driving corner point position, and the target corner point position. The vehicle's positioning information during the parking process is then corrected based on the driving posture until parking is completed.

[0009] In an optional implementation, before obtaining the user-defined target parking space and the initial pose of the vehicle, the following steps are included:

[0010] Upon receiving a parking instruction from a user, the system detects available parking spaces around the vehicle based on the parking instruction and sends at least one available parking space to the user so that the user can determine a target parking space from the at least one available parking space.

[0011] In an optional implementation, the vehicle is equipped with multiple sensors, and the target parking space line information includes a target parking space reference line, which includes a target longitudinal parking space reference line and a target transverse parking space reference line. Determining the corresponding target parking space line information based on the initial pose and the target parking space includes:

[0012] Based on the initial pose, determine the lateral and longitudinal sensors near the target parking space for detection, and detect the corresponding longitudinal parking space line of the target parking space through the lateral sensor and the corresponding lateral parking space line of the target parking space through the longitudinal sensor.

[0013] The target longitudinal parking space reference line and the target transverse parking space reference line are determined based on the longitudinal parking space line, the transverse parking space line, and the initial pose.

[0014] In an optional implementation, determining the target longitudinal parking space reference line and the target transverse parking space reference line based on the longitudinal parking space line, the transverse parking space line, and the initial pose includes:

[0015] A first coordinate system is established with the initial pose as the origin;

[0016] The expressions of the longitudinal parking space line and the transverse parking space line in the first coordinate system are determined respectively to obtain the target longitudinal parking space reference line and the target transverse parking space reference line.

[0017] In an optional implementation, determining the corresponding target corner position based on the target parking space line information includes:

[0018] The intersection point of the target longitudinal parking space reference line and the target transverse parking space reference line is calculated to obtain the target corner point position corresponding to the target parking space.

[0019] In an optional implementation, the target parking space line information includes target parking space lines, which include longitudinal parking space lines and transverse parking space lines. Determining the corresponding driving parking space line information based on the real-time pose of the vehicle includes:

[0020] A second coordinate system is established with the real-time pose of the vehicle as the origin;

[0021] Based on the real-time pose and the target parking space line information, determine the longitudinal and lateral sensors close to the target parking space line for detection, and detect the corresponding longitudinal and lateral parking space lines through the longitudinal and lateral sensors to obtain the driving longitudinal parking space reference line and driving lateral parking space reference line corresponding to the longitudinal and lateral parking space lines in the second coordinate system.

[0022] In an optional implementation, determining the longitudinal and lateral sensors near the target parking line for detection based on the real-time pose and the target parking line information includes:

[0023] Determine whether the angle between the longitudinal direction of the vehicle and the longitudinal parking line is less than a preset angle based on the real-time pose.

[0024] When the included angle is less than the preset angle, a lateral sensor close to the longitudinal parking space line is selected to detect the longitudinal parking space line, and a longitudinal sensor close to the lateral parking space line is selected to detect the lateral parking space line.

[0025] When the included angle is greater than or equal to the preset angle, a lateral sensor close to the lateral parking space is selected to detect the lateral parking line, and a longitudinal sensor close to the longitudinal parking space is selected to detect the longitudinal parking line.

[0026] In a second aspect, the present invention provides a vehicle positioning device for automatic parking, the device comprising:

[0027] The acquisition module is used to acquire the vehicle's initial pose and the target parking space specified by the user.

[0028] The target module is used to determine the corresponding target parking space line information and the planned parking trajectory based on the initial pose and the target parking space, and to determine the target corner point position based on the target parking space line information;

[0029] The real-time module is used to control the vehicle to drive according to the parking trajectory. During the vehicle movement, the module determines the corresponding driving parking line information based on the real-time pose of the vehicle, and determines the corresponding driving corner point position based on the driving parking line information.

[0030] The positioning module is used to determine the driving posture of the vehicle based on the target parking space line information, the driving parking space line information, the driving corner point position and the target corner point position, and to correct the positioning information of the vehicle during the parking process according to the driving posture until parking is completed.

[0031] Thirdly, the present invention provides a vehicle including a memory and a processor, the memory storing a computer program that executes the automatic parking vehicle positioning method when the computer program is run on the processor.

[0032] Fourthly, the present invention provides a readable storage medium storing a computer program that, when run on a processor, executes the vehicle positioning method for automatic parking.

[0033] The beneficial effects of the embodiments of the present invention are:

[0034] This application provides a vehicle positioning method for automatic parking. The method acquires the vehicle's initial pose and a target parking space determined by the user. Based on the initial pose and the target parking space, it determines the corresponding target parking space line information and plans a parking trajectory. Based on the target parking space line information, it determines the target corner position and controls the vehicle to travel along the parking trajectory. During vehicle movement, based on the vehicle's real-time pose, it determines the corresponding driving parking space line information and the corresponding driving corner position. Based on the target parking space line information, the driving parking space line information, the driving corner position, and the target corner position, it determines the vehicle's driving pose and corrects the vehicle's positioning information during the parking process until parking is complete. This application improves vehicle positioning accuracy and can be implemented without adding additional equipment, thus reducing the cost of vehicle positioning correction.

[0035] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0036] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope of protection of the present invention. In the various drawings, similar components are numbered similarly.

[0037] Figure 1 This paper illustrates a first flowchart of a vehicle positioning method for automatic parking according to an embodiment of this application.

[0038] Figure 2 A second schematic diagram of an automatic parking vehicle positioning method according to an embodiment of this application is shown;

[0039] Figure 3 This paper illustrates a flowchart of a vehicle positioning method for automatic parking according to an embodiment of this application, which determines the parking space reference line and the target corner point position.

[0040] Figure 4 This illustration shows a target parking space and a vehicle in an automatic parking vehicle positioning method according to an embodiment of this application;

[0041] Figure 5This illustration shows a schematic diagram of the target parking space and the vehicle in a coordinate system in an automatic parking vehicle positioning method proposed in an embodiment of this application;

[0042] Figure 6 The diagram illustrates the process of determining the driving parking space line function and the driving corner point position in an automatic parking vehicle positioning method according to an embodiment of this application.

[0043] Figure 7 This paper illustrates a flowchart of a vehicle positioning method for automatic parking according to an embodiment of this application, which determines the sensors during vehicle movement.

[0044] Figure 8 A schematic diagram of the structure of an automatic parking vehicle positioning device provided in an embodiment of this application is shown.

[0045] Explanation of key component symbols:

[0046] 10-Vehicle positioning device for automatic parking; 11-Acquisition module; 12-Target module; 13-Real-time module; 14-Positioning module. Detailed Implementation

[0047] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0048] The components of the embodiments of the invention described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0049] In the following, the terms “comprising,” “having,” and their cognates, which may be used in various embodiments of the invention, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as excluding, firstly, the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations thereof.

[0050] Furthermore, the terms "first," "second," and "third" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0051] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of the invention pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be interpreted as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of the invention.

[0052] Example 1

[0053] Please refer to Figure 1 This application provides a vehicle positioning method for automatic parking. Exemplarily, the vehicle positioning method for automatic parking includes steps S100 to S400.

[0054] Step S100: Obtain the initial pose of the vehicle and the target parking space determined by the user.

[0055] In this application, when the vehicle is about to start automatic parking, the vehicle is stationary. The current position and posture of the vehicle are obtained as the initial position and posture, and the target parking space determined by the user is obtained, and the parking space data corresponding to the target parking space is obtained.

[0056] In one implementation, such as Figure 2 As shown, step S500 is included before step S100.

[0057] Step S500: Upon receiving a parking instruction from the user, detect available parking spaces around the vehicle according to the parking instruction, and send at least one available parking space to the user so that the user can determine the target parking space from at least one available parking space.

[0058] In this application, when a user needs to activate the automatic parking function, the user can control the vehicle to start automatic parking via an automatic parking button, voice control, or other means. The vehicle will receive the parking command sent by the user. Upon receiving the parking command, the system will detect available parking spaces around the vehicle based on the received command and obtain the corresponding parking space data for each available space. This parking space data includes the position information of multiple parking space lines of the available parking space, the status information of the available parking space, and the relative position of the available parking space and the vehicle.

[0059] The system sends at least one detected available parking space to the corresponding user terminal based on the parking instruction. The user then selects one of the available parking spaces from the received list based on their needs or preferences as the target parking space for their vehicle. The user terminal can be a device capable of human-computer interaction, such as a car display screen, a rear-head display screen, a mobile phone, or a tablet.

[0060] Step S200: Based on the initial pose and the target parking space, determine the corresponding target parking space line information and plan the parking trajectory, and determine the target corner point position based on the target parking space line information.

[0061] Understandably, each parking space includes multiple parking lines, usually four. Based on the initial position of the vehicle when it is stationary and the target parking space selected by the user, the relative position between the target parking space and the vehicle can be determined, or the relative position between the target parking space and the vehicle can be determined based on the parking space data corresponding to the target parking space. In other words, the relative position between the multiple parking lines corresponding to the target parking space and the vehicle can be determined.

[0062] In this application, the target parking space and the vehicle have various relative positions. For example, the target parking space can be located at the left rear, left front, right rear, or right front of the vehicle. At least one sensor with the optimal viewing angle is determined based on the relative position of the target parking space and the vehicle. The parking space lines on the target parking space are detected using this at least one sensor to determine the corresponding target parking space information. The target parking space information includes the target parking space line and the target parking space reference line. The target parking space line includes longitudinal and lateral parking space lines, and the target parking space reference line includes a target longitudinal parking space reference line and a target lateral parking space reference line. The target corner point position of the target parking space is determined based on the determined target parking space information. The vehicle is equipped with multiple sensors, such as vision sensors and camera sensors. These sensors are divided into longitudinal and lateral sensors. The longitudinal sensors are at least one sensor positioned longitudinally on the vehicle, including front and rear sensors. The lateral sensors are at least one sensor positioned laterally on the vehicle, including left and right sensors. The target parking space line information includes the target parking space reference line and the target parking space line.

[0063] As an example, when the target parking space is in front of the vehicle on the left, the target parking space will be detected by the sensor on the vehicle that is closest to the target parking space, that is, by the sensors on the front and left sides of the vehicle.

[0064] In this application, after determining the initial pose of the vehicle and the target parking space, the parking trajectory of the vehicle to the target parking space can be planned by the corresponding algorithm. The planned parking trajectory includes multiple waypoints. Planning the parking trajectory is not the focus of this application and will not be elaborated on here.

[0065] In one implementation, such as Figure 3 As shown, based on the initial pose and the target parking space, the corresponding target parking space line information is determined, including sub-steps S210 to S220.

[0066] Sub-step S210: Based on the initial pose, determine the lateral and longitudinal sensors near the target parking space for detection, and detect the corresponding longitudinal parking line of the target parking space through the lateral sensor and the corresponding lateral parking line of the target parking space through the longitudinal sensor.

[0067] It is understood that the lateral sensor includes at least one sensor, such as a left-side sensor and a right-side sensor, and the longitudinal sensor includes at least one sensor, such as a front-side sensor and a rear-side sensor. The target parking space line consists of at least one lateral parking space line and at least one longitudinal parking space line. The target vehicle reference line includes the target longitudinal parking space reference line corresponding to the lateral parking space line, and the target lateral parking space reference line corresponding to the longitudinal parking space line, when the vehicle is detected in its current position by the corresponding sensor near the target parking space.

[0068] In this application, the corresponding lateral and longitudinal sensors on the vehicle are determined based on the corresponding positions of the target parking space and the vehicle's current pose. In other words, the lateral sensor and the longitudinal sensor on the vehicle closest to the target parking space are used as sensors to detect parking lines in the target parking space. Specifically, the parking line closest to the lateral sensor in the target parking space can be detected by the lateral sensor, which is the first longitudinal parking line in the target parking space. Alternatively, the lateral sensor can be used to detect a parking line parallel to the first longitudinal parking line in the target parking space, resulting in the second longitudinal parking line in the target parking space. Similarly, the parking line closest to the longitudinal sensor in the target parking space is detected by the longitudinal sensor, which is the first lateral parking line in the target parking space. The longitudinal sensor can also be used to detect a parking line parallel to the first lateral parking line, resulting in the second lateral parking line in the target parking space. For example, the vehicle uses the lateral sensor closest to the target parking space to detect one or more of the first and second longitudinal parking lines on the target parking space, and uses the longitudinal sensor closest to the target parking space to detect one or more of the first and second lateral parking lines on the target parking space. Here, "longitudinal parking line" and "lateral parking line" are merely names for the parking lines on the target parking space and do not restrict the direction of the parking lines.

[0069] Exemplary examples show that when the target parking space is on the right side of the vehicle, the vehicle's lateral sensor is selected as the right-side sensor. The right-side sensor detects the parking line closest to the vehicle; this is the longitudinal parking line. The right-side sensor can also detect parking lines parallel to the closest parking line; both detected parking lines are longitudinal. When the target parking space is on the left side of the vehicle, the left-side sensor is selected to detect the vehicle's longitudinal parking line. When the target parking space is in front of the vehicle, the vehicle's longitudinal sensor is selected as the front-side sensor. The front-side sensor detects the parking line closest to this front-side sensor; this is the lateral parking line. When the target parking space is behind the vehicle, the rear-side sensor is selected to detect the lateral parking line in the target parking space closest to the vehicle.

[0070] For example, such as Figure 4 As shown, when the target parking space is B and the vehicle is C, and the target parking space is close to the upper left of the vehicle, when the left-side sensor and the front-side sensor on the vehicle detect a corresponding parking line, the parking line closest to the corresponding sensor on the target parking space can be detected. For example, the left-side sensor detects the parking line a that is close to the longitudinal direction of the vehicle, and the parking line a represents the longitudinal parking line. The front-side sensor detects the parking line b that is close to the lateral direction of the vehicle, and the parking line b represents the lateral parking line. Therefore, the target parking line includes the longitudinal parking line a and the lateral parking line b.

[0071] Sub-step S220: Determine the target longitudinal parking space reference line and the target transverse parking space reference line based on the longitudinal parking space line, the transverse parking space line and the initial pose.

[0072] After detecting the target parking space line, i.e., determining the corresponding longitudinal and transverse parking lines, a first coordinate system is established with the vehicle's initial pose as the origin, the vehicle's longitudinal direction as the X-axis, and the vehicle's transverse direction as the Y-axis. For example, as... Figure 5 As shown, with O m Establish the first coordinate system with point as the origin, and take the longitudinal direction of the vehicle as X. m The axis, the lateral direction of the vehicle is Y. m Axis. Determine the expression corresponding to the target parking space line in the first coordinate system as the corresponding target parking space reference line. In other words, determine the target longitudinal parking space reference line and the target transverse parking space reference line corresponding to the longitudinal parking space line and the transverse parking space line in the first coordinate system.

[0073] As an example, the target longitudinal parking space reference line corresponding to the longitudinal parking space line in the first coordinate system is represented as: y = k 1m x+b 1m The target transverse parking space reference line corresponding to the transverse parking space line is represented as: y = k 2m x+b 2mThe target corner point A is determined by integrating the target longitudinal parking space reference line and the target transverse parking space reference line. This target corner point A is the intersection of the longitudinal and transverse parking space lines on the target parking space; that is, it is the intersection of any two parking space lines on the target parking space. In other words, the corresponding target corner point position A(x) is obtained by solving for the corner point using the target longitudinal and transverse parking space reference lines. m ,y m ,θ m ), θ m The target lateral parking space reference line is represented by y = k. 2m x+b 2m The corresponding direction.

[0074] Understandably, when two longitudinal parking lines and two transverse parking lines are detected on a vehicle—that is, when the first and second longitudinal parking lines, and the first and second transverse parking lines—the corresponding first target transverse parking space reference line, second target transverse parking space reference line, first target longitudinal parking space reference line, and second target longitudinal parking space reference line are detected, thus determining the target parking space reference line corresponding to each parking line on the target parking space. When a longitudinal parking line intersects with a transverse parking line, a target corner point will exist. Therefore, based on the aforementioned first target transverse parking space reference line, second target transverse parking space reference line, first target longitudinal parking space reference line, and second target longitudinal parking space reference line, the target corner point position corresponding to each target corner point on the target parking space will be determined. For example, the corresponding first target corner point position will be determined based on the first target transverse parking space reference line and the first target longitudinal parking space reference line. Specifically, when the corresponding sensors detect the two target parking space lines closest to the vehicle, a vertex of the target parking space closest to the vehicle will be determined based on the detected two target parking space lines, thus obtaining the corresponding target corner point position.

[0075] Step S300: Control the vehicle to drive along the parking trajectory. During the vehicle's movement, determine the corresponding driving parking line information based on the vehicle's real-time pose, and determine the corresponding driving corner point position based on the driving parking line information.

[0076] After planning the parking path, the vehicle will be controlled to drive along the planned parking trajectory. The parking path includes multiple waypoints. Whenever the vehicle reaches a waypoint on the parking path, its real-time pose (x, y, θ) at that point will be calculated. Based on the vehicle's real-time pose and the selected target parking space, the corresponding driving parking space line information for that real-time pose will be determined. The driving parking space line information will then determine the corresponding driving corner point position. This driving parking space line information includes driving parking space reference lines, which include lateral and longitudinal driving parking space reference lines.

[0077] In one implementation, such as Figure 6 As shown, the corresponding driving parking space information is determined based on the real-time pose of the vehicle, including sub-steps S310 to S320.

[0078] Sub-step S310: Establish a second coordinate system with the vehicle's real-time pose as the origin.

[0079] In this application, the real-time pose of the vehicle at a given path point will be calculated based on wheel pulse signals or inertial sensors. After determining the real-time pose, the point where the vehicle's real-time pose is located will be used as the origin O. C Establish a corresponding second coordinate system, and define the longitudinal direction of the vehicle as the X-axis of the coordinate system. c The lateral direction of the vehicle is the Y-axis of the coordinate system. C Axial direction.

[0080] Sub-step S320: Based on the real-time pose and target parking line information, determine the longitudinal and lateral sensors close to the target parking line for detection, and detect the corresponding longitudinal and lateral parking lines through the longitudinal and lateral sensors to obtain the driving longitudinal parking reference line and driving lateral parking reference line corresponding to the longitudinal and lateral parking lines in the second coordinate system.

[0081] In this application, the target parking space line includes longitudinal parking space lines and transverse parking space lines. The driving parking space line information includes driving parking space reference lines, which include driving longitudinal parking space reference lines and driving transverse parking space reference lines. Based on the vehicle's real-time pose and the target parking space line information, longitudinal and transverse sensors near the target parking space line are determined for detection. The determined longitudinal and transverse sensors are then used to detect the corresponding longitudinal and transverse parking space lines. Specifically, based on the detected target parking space line information, at least one of a first longitudinal parking space line and a second longitudinal parking space line, as well as at least one of a first transverse parking space line and a second transverse parking space line, are detected. This determines the function corresponding to the target parking space line in the established second coordinate system, i.e., the corresponding driving parking space reference line. In the second coordinate system, the expression for the driving transverse parking space reference line corresponding to the transverse parking space line is: y = k 1c x+b 1c The expression for the reference line of the longitudinal parking space corresponding to the longitudinal parking space line is: y = k 2c x+b 2c .

[0082] Understandably, the target corner point on the target parking space line in the second coordinate system will be calculated using the determined longitudinal and lateral parking space reference lines to obtain the driving corner point position A(x) in the second coordinate system. c ,y c ,θ c), where θ c The reference line for the lateral parking space is y = k. 2c x+b 2c The corresponding direction. When multiple target corner points exist, the driving corner point position corresponding to each target corner point in the second coordinate system will be determined.

[0083] In one implementation, such as Figure 7 As shown, the longitudinal and lateral sensors near the target parking line are determined based on the real-time pose and target parking line information, including sub-steps S321 to S322.

[0084] Sub-step S321: Determine whether the angle between the longitudinal direction of the vehicle and the longitudinal parking line is less than the preset angle based on the real-time pose.

[0085] It is understood that the vehicle includes a lateral sensor positioned in the lateral direction and a longitudinal sensor positioned in the longitudinal direction. During vehicle movement, the longitudinal direction of the vehicle is determined based on its real-time pose, and it is determined whether the angle between the vehicle's longitudinal direction and the longitudinal parking line of the target parking space is less than a preset angle, thereby determining the relative positional relationship between the vehicle and the target parking space when the vehicle reaches that pose. When the angle between the vehicle's longitudinal direction and the longitudinal parking line is less than the preset angle, sub-step S322 is executed; when the angle between the vehicle's longitudinal direction and the longitudinal parking line is greater than or equal to the preset angle, sub-step S323 is executed.

[0086] Sub-step S322: Select a transverse sensor near the longitudinal parking space line to detect the longitudinal parking space line, and a longitudinal sensor near the transverse parking space line to detect the transverse parking space line.

[0087] When the included angle is less than a preset angle, the lateral sensor closest to the target parking space line will be selected to detect the longitudinal parking space line. The longitudinal sensor on the vehicle closest to the lateral parking space line will then be used to detect the corresponding lateral parking space line. The preset angle can be set according to actual conditions, for example, 45°.

[0088] As an example, when the longitudinal parking line closest to the vehicle in the target parking space is on the left side of the vehicle and the lateral parking line is behind the vehicle, the lateral sensor will be selected as the left-side sensor and the longitudinal sensor as the rear-side sensor; when the longitudinal and lateral parking lines of the target parking space are on the right and rear sides of the vehicle, respectively, the lateral sensor will be selected as the right-side sensor and the longitudinal sensor as the rear-side sensor.

[0089] Sub-step S323: Select the lateral sensor near the lateral parking space to detect the lateral parking line, and the longitudinal sensor near the longitudinal parking space to detect the longitudinal parking line.

[0090] It is understandable that the position of the target parking space remains constant, while the vehicle is constantly moving. Therefore, the lateral and longitudinal parking lines within the target parking space remain unchanged. When the included angle is greater than or equal to a preset angle, the lateral sensor of the vehicle closest to the target parking space line will detect the corresponding lateral parking line, and the longitudinal sensor will detect the corresponding longitudinal parking line. Exemplarily, the longitudinal parking line will be detected using the vehicle's front or rear sensors, and the lateral parking line will be detected using the vehicle's left or right sensors.

[0091] Step S400: Determine the vehicle's driving posture based on the target parking space line information, driving parking space line information, driving corner point position and target corner point position, and correct the vehicle's positioning information during the parking process according to the driving posture until parking is completed.

[0092] In this application, after calculating the target parking space line information and target corner point position in the first coordinate system, and the driving parking space line information and driving corner point position in the second coordinate system, the target parking space reference line in the first coordinate system and the driving parking space reference line in the second coordinate system are determined respectively. In other words, the corresponding target lateral parking space reference line, target longitudinal parking space reference line, driving lateral parking space reference line, and driving longitudinal parking space reference line are determined, thereby determining the slope of each parking space reference line in the target parking space reference line and the driving parking space reference line. Based on the target corner point position and driving corner point position of each target corner point in the target parking space in the first and second coordinate systems respectively, the driving pose of the vehicle is calculated by a preset formula, and the vehicle positioning is corrected according to the obtained driving pose (x′,y′,θ′), that is, the real-time pose (x,y,θ) of the vehicle is corrected. The preset formula is as follows:

[0093]

[0094] That is, the driving pose (x′, y′, θ′) represents the vehicle's pose after positioning correction in the first coordinate system.

[0095] In this application, the vehicle positioning is corrected solely through sensor fusion, which not only improves the vehicle's positioning accuracy but also requires less computing power and no additional equipment, thus making the cost of vehicle visual correction positioning much lower.

[0096] The vehicle positioning method for automatic parking based on the above embodiments, Figure 8 A schematic diagram of the structure of an automatic parking vehicle positioning device 10 according to an embodiment of this application is shown. The automatic parking vehicle positioning device 10 includes:

[0097] The acquisition module 11 is used to acquire the initial pose of the vehicle and the target parking space determined by the user;

[0098] The target module 12 is used to determine the corresponding target parking space line information and the planned parking trajectory based on the initial pose and the target parking space, and to determine the target corner point position based on the target parking space line information;

[0099] Real-time module 13 is used to control the vehicle to drive according to the parking trajectory. During the vehicle movement, it determines the corresponding driving parking line information based on the real-time pose of the vehicle and determines the corresponding driving corner point position based on the driving parking line information.

[0100] The positioning module 14 is used to determine the driving posture of the vehicle based on the target parking space line information, the driving parking space line information, the driving corner point position and the target corner point position, and to correct the positioning information of the vehicle during the parking process according to the driving posture until parking is completed.

[0101] The vehicle positioning device 10 for automatic parking in this embodiment is used to execute the vehicle positioning method for automatic parking in the above embodiment. The implementation schemes and beneficial effects involved in the above embodiments are also applicable in this embodiment, and will not be repeated here.

[0102] This application also provides a terminal device, including a memory and a processor. The memory stores a computer program, and the computer program executes the above-described automatic parking vehicle positioning method when it runs on the processor.

[0103] This application also provides a computer-readable storage medium storing a computer program that, when executed on a processor, implements the above-described automatic parking vehicle positioning method.

[0104] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0105] In addition, the functional modules or units in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0106] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0107] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A vehicle positioning method for automatic parking, characterized in that, The method includes: Obtain the vehicle's initial pose and the target parking space specified by the user; Based on the initial pose and the target parking space, the corresponding target parking space line information and the planned parking trajectory are determined, and the target corner point position is determined based on the target parking space line information; The vehicle is controlled to drive along the parking trajectory. During the vehicle's movement, the corresponding driving parking line information is determined based on the vehicle's real-time pose, and the corresponding driving corner point position is determined based on the driving parking line information. The vehicle's driving posture is determined based on the target parking space line information, the driving parking space line information, the driving corner point position, and the target corner point position. The vehicle's positioning information during the parking process is then corrected based on the driving posture until parking is completed. The steps of determining the corresponding target parking space line information and planned parking trajectory based on the initial pose and the target parking space, and determining the target corner point position based on the target parking space line information, include: The first longitudinal parking line in the target parking line is obtained by detecting the parking line closest to the lateral sensor on the vehicle. The second longitudinal parking line in the target parking line is obtained by detecting the parking line parallel to the first longitudinal parking line in the target parking space using the lateral sensor. The first transverse parking line of the target parking space is obtained by detecting the parking line closest to the longitudinal sensor in the target parking space using the longitudinal sensor. The second transverse parking line of the target parking space is obtained by detecting the parking line parallel to the first transverse parking line using the longitudinal sensor. A first coordinate system is established with the vehicle's initial pose as the origin, and the vehicle's longitudinal direction is used as the coordinate system. The axle, the lateral direction of the vehicle is... axis; In the first coordinate system, the target longitudinal parking space reference line corresponding to the first longitudinal parking space line is represented as: The target horizontal parking space reference line corresponding to the first horizontal parking space line is represented as follows: The corner points are determined by using the target longitudinal parking space reference line and the target transverse parking space reference line. , Indicates the direction corresponding to the target horizontal parking space reference line; The steps of determining the corresponding driving parking line information based on the real-time pose of the vehicle, and determining the corresponding driving corner point position based on the driving parking line information, include: The point where the vehicle's real-time pose is located is taken as the origin. Establish a corresponding second coordinate system, and set the longitudinal direction of the vehicle as the coordinate system's axis. The axial direction and the lateral direction of the vehicle are the coordinate system's... Axial direction; Based on the vehicle's real-time pose and the target parking space line information, the longitudinal and lateral sensors near the target parking space line are determined for detection. The corresponding longitudinal and lateral parking space lines are then detected using these sensors. In the second coordinate system, the expression for the driving lateral parking space reference line corresponding to the lateral parking space line is: The expression for the reference line of the driving longitudinal parking space corresponding to the longitudinal parking space line is: The driving corner point position in the second coordinate system is obtained by calculating using the longitudinal and lateral parking space reference lines. ,in, Indicates the direction corresponding to the horizontal parking space reference line; The step of determining the vehicle's driving posture based on the target parking space line information, the driving parking space line information, the driving corner point position, and the target corner point position includes: The vehicle's driving posture is calculated using a preset formula, and based on the obtained driving posture... Correcting the vehicle's positioning, i.e., correcting the vehicle's real-time pose. Make corrections; The preset formula is as follows: That is, driving position This represents the vehicle's position after positioning correction in the first coordinate system.

2. The vehicle positioning method for automatic parking according to claim 1, characterized in that, Before obtaining the initial pose of the vehicle and the target parking space determined by the user, the following steps are also included: Upon receiving a parking instruction from a user, the system detects available parking spaces around the vehicle based on the parking instruction and sends at least one available parking space to the user so that the user can determine a target parking space from the at least one available parking space.

3. The vehicle positioning method for automatic parking according to claim 1, characterized in that, The step of determining the longitudinal and lateral sensors near the target parking line for detection based on the real-time pose and the target parking line information includes: Determine whether the angle between the longitudinal direction of the vehicle and the longitudinal parking line is less than a preset angle based on the real-time pose. When the included angle is less than the preset angle, a lateral sensor close to the longitudinal parking space line is selected to detect the longitudinal parking space line, and a longitudinal sensor close to the lateral parking space line is selected to detect the lateral parking space line. When the included angle is greater than or equal to the preset angle, a lateral sensor close to the lateral parking space is selected to detect the lateral parking line, and a longitudinal sensor close to the longitudinal parking space is selected to detect the longitudinal parking line.

4. A vehicle positioning device for automatic parking, characterized in that, The device includes: The acquisition module is used to acquire the vehicle's initial pose and the target parking space specified by the user. The target module is used to determine the corresponding target parking space line information and plan the parking trajectory based on the initial pose and the target parking space, and to determine the target corner point position based on the target parking space line information; The real-time module is used to control the vehicle to drive according to the parking trajectory. During the vehicle movement, the module determines the corresponding driving parking line information based on the real-time pose of the vehicle, and determines the corresponding driving corner point position based on the driving parking line information. The positioning module is used to determine the driving posture of the vehicle based on the target parking space line information, the driving parking space line information, the driving corner point position and the target corner point position, and to correct the positioning information of the vehicle during the parking process according to the driving posture until parking is completed. The steps of determining the corresponding target parking space line information and planned parking trajectory based on the initial pose and the target parking space, and determining the target corner point position based on the target parking space line information, include: The first longitudinal parking line in the target parking line is obtained by detecting the parking line closest to the lateral sensor on the vehicle. The second longitudinal parking line in the target parking line is obtained by detecting the parking line parallel to the first longitudinal parking line in the target parking space using the lateral sensor. The first transverse parking line of the target parking space is obtained by detecting the parking line closest to the longitudinal sensor in the target parking space using the longitudinal sensor. The second transverse parking line of the target parking space is obtained by detecting the parking line parallel to the first transverse parking line using the longitudinal sensor. A first coordinate system is established with the vehicle's initial pose as the origin, and the longitudinal direction of the vehicle as the coordinate system. The axle, the lateral direction of the vehicle is axis; In the first coordinate system, the target longitudinal parking space reference line corresponding to the first longitudinal parking space line is represented as: The target horizontal parking space reference line corresponding to the first horizontal parking space line is represented as follows: The corner points are determined by using the target longitudinal parking space reference line and the target transverse parking space reference line. , Indicates the direction corresponding to the target horizontal parking space reference line; The steps of determining the corresponding driving parking line information based on the real-time pose of the vehicle, and determining the corresponding driving corner point position based on the driving parking line information, include: The point where the vehicle's real-time pose is located is taken as the origin. Establish a corresponding second coordinate system, and set the longitudinal direction of the vehicle as the coordinate system's axis. The axial direction and the lateral direction of the vehicle are the coordinate system's... Axial direction; Based on the vehicle's real-time pose and the target parking space line information, the longitudinal and lateral sensors near the target parking space line are determined for detection. The corresponding longitudinal and lateral parking space lines are then detected using these sensors. In the second coordinate system, the expression for the driving lateral parking space reference line corresponding to the lateral parking space line is: The expression for the reference line of the driving longitudinal parking space corresponding to the longitudinal parking space line is: The driving corner point position in the second coordinate system is obtained by calculating using the longitudinal and lateral parking space reference lines. ,in, Indicates the direction corresponding to the horizontal parking space reference line; The step of determining the vehicle's driving posture based on the target parking space line information, the driving parking space line information, the driving corner point position, and the target corner point position includes: The vehicle's driving posture is calculated using a preset formula, and based on the obtained driving posture... Correcting the vehicle's positioning, i.e., correcting the vehicle's real-time pose. Make corrections; The preset formula is as follows: 。 5. A vehicle, characterized in that, It includes a memory and a processor, the memory storing a computer program that, when executed on the processor, performs the vehicle positioning method for automatic parking as described in any one of claims 1 to 3.

6. A readable storage medium, characterized in that, It stores a computer program that, when run on a processor, executes the vehicle positioning method for automatic parking as described in any one of claims 1 to 3.

Images