Methods, devices, and vehicles for determining vehicle parking posture angles

Abstract

This invention relates to a method, apparatus, and vehicle for determining a vehicle's parking posture angle. The method includes: acquiring contour point data of an obstacle within a preset distance of a parking space; determining obstacle edge segments based on the contour point data, wherein the obstacle edge segments represent the edges of the obstacle in a plane parallel to the parking space, and the length of the obstacle edge segments is greater than a preset target length, with the target length obstacle edge segments covering multiple contour points; and determining the vehicle's parking posture angle based on the obstacle edge segments. This method, by representing the edges of obstacles with line segments of target length, reduces the influence of factors such as environmental noise and sensor errors, thereby improving the accuracy of calculating the vehicle's parking posture angle.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and more specifically to a method, apparatus, and vehicle for determining the parking posture angle of a vehicle. Background Technology

[0002] With the rapid development of intelligent vehicles, automatic parking systems have become an indispensable part of them. Accurately obtaining the relative positional relationship between the vehicle and the parking space, as well as the vehicle's own attitude angle, is crucial for achieving safe and efficient parking during automatic parking.

[0003] Traditional parking space detection and attitude calculation methods typically rely on data from a single sensor, such as an ultrasonic sensor. However, due to factors such as environmental noise and sensor errors, the detected obstacle positions may be inaccurate, leading to significant errors in the calculated parking attitude angles.

[0004] Therefore, how to accurately calculate the vehicle's parking attitude angle is an urgent problem to be solved. Summary of the Invention

[0005] One objective of this invention is to provide a method for determining the parking posture angle of a vehicle, so as to improve the accuracy of calculating the parking posture angle of a vehicle; a second objective is to provide a device for determining the parking posture angle of a vehicle; and a third objective is to provide a vehicle.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0007] In a first aspect, the present invention provides a method for determining the parking posture angle of a vehicle, the method comprising:

[0008] Obtain the outline point data of obstacles within a preset distance of the parking space;

[0009] Obstacle edge segments are determined based on the contour point data. The obstacle edge segments are used to represent the edges of obstacles in a plane parallel to the parking space. The length of the obstacle edge segments is greater than a preset target length, and the obstacle edge segments cover multiple contour points.

[0010] The parking posture angle of the vehicle is determined based on the edge segments of the obstacle.

[0011] Based on the above technical means, the obstacle edge is represented by an obstacle edge line segment of target length. Compared with directly using continuous data points, this can reduce the influence of factors such as environmental noise and sensor errors, thereby achieving accurate calculation of the vehicle parking posture angle.

[0012] Furthermore, determining the obstacle edge segment based on the obstacle's contour points includes:

[0013] Based on the outline points of the obstacle, determine all outline points in each plane parallel to the parking space;

[0014] For all contour points in each plane, determine the initial obstacle line segment based on the target length;

[0015] Based on the initial obstacle edge segments in each plane, determine the obstacle edge segments in all planes.

[0016] Based on the above technical means, by determining the obstacle line segment through the contour points of each plane, the direction of the obstacle can be determined, avoiding interference caused by contour points at different heights, and ensuring that the direction of the obstacle line segment can represent the direction of the obstacle.

[0017] Further, determining the obstacle edge segments in all planes based on the initial obstacle edge segments in each plane includes:

[0018] Obtain the line segment direction of the initial obstacle edge line segment in each plane;

[0019] Based on the line direction of all initial obstacle edge segments in the plane, the initial obstacle edge segments within a preset direction angle threshold are determined as the obstacle edge segments.

[0020] Based on the above technical means, by setting a preset direction angle threshold, the lateral direction line segments of the vehicle can be excluded, further ensuring that the direction of the obstacle edge line segments can represent the direction of the obstacle.

[0021] Further, determining the obstacle edge segments in all planes based on the initial obstacle edge segments in each plane includes:

[0022] Obtain the line segment direction of the initial obstacle edge line segment in each plane;

[0023] Sort the number of segments under each initial obstacle edge line segment direction according to the line segment direction of all planes;

[0024] The direction of the line segment with the most line segments in the sorting is determined as the target direction;

[0025] The line segment in the target direction is taken as the edge line segment of the obstacle.

[0026] Based on the aforementioned technical means, the longest position on the edge of an obstacle has the most line segments. Therefore, the direction of the obstacle's edge can be determined by sorting the directions of the line segments.

[0027] Furthermore, determining the initial obstacle segment based on the target length includes:

[0028] The initial contour point of the line segment is determined by using the contour point closest to the parked vehicle as the initial contour point, and the target length is used as the step size to determine the ending contour point of the line segment.

[0029] An initial obstacle line segment is determined based on the initial contour point and the ending contour point of the line segment;

[0030] Using the end contour point of the line segment as the initial contour point of the new line segment, a new initial obstacle line segment is determined until a new end contour point of the line segment cannot be determined.

[0031] Using the aforementioned techniques, by connecting the ends of line segments, it can be ensured that the initial obstacle line segment encompasses all contour points within it. The initial obstacle line segment has a target length, which is greater than the distance between two points during normal data acquisition; the target length is longer. Small deviations in the contour points, resulting in directional changes on the initial obstacle line segment of the target length, cause less directional change compared to the directional change between two normal data points, thus reducing data error.

[0032] Furthermore, determining the parking posture angle of the vehicle based on the edge segment of the obstacle and the parking space includes:

[0033] The parking attitude angle is determined based on the obstacle edge segments using a pre-built extended Kalman filter model.

[0034] Based on the aforementioned technical means, the extended Kalman filter algorithm fuses data from ultrasonic sensors and vehicle attitude sensors, effectively reducing the impact of noise and interference on the calculation results and improving the accuracy and stability of the calculation.

[0035] Furthermore, determining the parking posture angle of the vehicle based on the edge segment of the obstacle and the parking space includes:

[0036] The parking posture angle is determined based on the average value of the directional angles of the obstacle edge segments.

[0037] Based on the aforementioned technical means, by calculating the average value of the directional angles of the obstacle edge segments, the direction of the obstacle edge can be accurately represented, and this can be used as the parking attitude angle of the target.

[0038] Furthermore, if there are obstacles on both sides of the parking space, determining the parking posture angle of the vehicle based on the edge segments of the obstacles includes:

[0039] Obtain the left-side average value of the direction angle of the obstacle edge line segment on the left side of the parking space;

[0040] Obtain the average right-side value of the direction angle of the obstacle edge line segment to the right of the parking space;

[0041] The parking posture angle is determined based on the average value on the left and the average value on the right.

[0042] By using the aforementioned technical means, and taking into account obstacles on both sides of the parking space, the parking posture angle of the target can be more accurately determined when parking.

[0043] Furthermore, the method also includes:

[0044] The parking posture angle is input into the automatic parking system for parking.

[0045] Secondly, this application provides a device for determining a vehicle target attitude angle, the device comprising:

[0046] The acquisition module is used to acquire the outline point data of obstacles within a preset distance of the parking space;

[0047] The line segment determination module is used to determine the obstacle edge line segment based on the contour point data. The obstacle edge line segment is used to represent the edge of the obstacle in a plane parallel to the parking space. The length of the obstacle edge line segment is greater than a preset target length.

[0048] An angle determination module is used to determine the parking posture angle of the vehicle based on the edge line segments of the obstacle.

[0049] Thirdly, this application provides an electronic device, including: a memory and a processor;

[0050] The memory stores computer-executed instructions;

[0051] The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any of the first aspects.

[0052] Fourthly, this application provides a vehicle including a controller for performing the method as described in any of the first aspects.

[0053] Fifthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any of the first aspects.

[0054] The beneficial effects of this invention are:

[0055] (1) The present invention represents the obstacle edge with an obstacle edge line segment of target length. Compared with directly using continuous data points, it can reduce the influence of environmental noise, sensor error and other factors, thereby increasing the accuracy of calculating the vehicle parking attitude angle.

[0056] (2) This invention uses an extended Kalman filter algorithm to fuse data from ultrasonic sensors and vehicle attitude sensors, effectively reducing the impact of noise and interference on the calculation results and improving the accuracy and stability of the calculation. The extended Kalman filter algorithm is recursive, enabling it to update the estimation results in real time and adaptively adjust the model parameters based on new observation data, thereby enhancing the robustness and adaptability of the system. Attached Figure Description

[0057] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0058] Figure 1 A schematic diagram illustrating the application scenario of vehicle parking provided in this application;

[0059] Figure 2 A schematic diagram illustrating the ultrasonic sensor used in this application for obstacle identification;

[0060] Figure 3 Flowchart of the method for determining the vehicle parking attitude angle provided in this application Figure 1 ;

[0061] Figure 4 A schematic diagram of the coordinate system provided in this application;

[0062] Figure 5 A schematic diagram illustrating the determination of initial obstacle line segments in a plane, as provided in this application;

[0063] Figure 6 Schematic diagram of the method for determining the vehicle parking attitude angle provided in this application Figure 2 ;

[0064] Figure 7 A schematic diagram of the structure of the vehicle target attitude angle determination device provided in this application;

[0065] Figure 8 A schematic diagram of the structure of the electronic device provided in this application.

[0066] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0067] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, 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 invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0068] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0069] Figure 1 This is a schematic diagram illustrating the application scenario of vehicle parking provided in this application. Figure 1 The image shows several parking scenarios. In image a, parking spaces are provided on the site, and nearby vehicles are parked normally; in image b, parking spaces are provided on the site, and nearby vehicles are parked at an angle; in image c, no parking spaces are provided on the site, and nearby vehicles are parked normally; in image d, no parking spaces are provided on the site, and nearby vehicles are parked at an angle.

[0070] The automatic parking process may encounter any of the above scenarios. In any of these scenarios, it is crucial to accurately obtain the relative positional relationship between the vehicle and the parking space, as well as the vehicle's own attitude angle.

[0071] Traditional parking space detection and attitude calculation methods typically rely on data from a single sensor, such as an ultrasonic sensor. Ultrasonic sensors determine obstacles (e.g., surrounding vehicles) around the parking space by transmitting ultrasonic signals. By having several ultrasonic sensors transmit signals multiple times, the sensor can record the distance measured each time, forming a time series. This gradually accumulates information, allowing the identification of the positions and relative relationships of multiple objects. However, due to factors such as environmental noise and sensor errors, the identified obstacle positions may be inaccurate.

[0072] Figure 2 This is a schematic diagram illustrating the ultrasonic sensor used in this application for obstacle identification. Figure 2 In the process, the system identifies the location points of vehicles next to parking spaces and determines the vehicle outline by connecting the locations with the lines formed by these locations according to a time sequence. However, environmental noise or sensor errors can cause significant discrepancies between the actual location points and the actual situation, leading to errors in determining the vehicle's parking attitude angle based on this data.

[0073] In view of the above problems, this application draws and filters obstacle line segments during parking to make the obstacle line segments more consistent with the actual situation of the obstacles, and then performs subsequent parking attitude angle estimation to avoid the perception error problem of the prior art.

[0074] The following describes the technical solution of this application and how it solves the aforementioned technical problems using specific embodiments, with the vehicle controller as the executing entity. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0075] Figure 3 Flowchart of the method for determining the vehicle parking attitude angle provided in this application Figure 1 ,like Figure 3 As shown, the method includes:

[0076] S101. Obtain the outline point data of obstacles within a preset distance of the parking space.

[0077] In this step, parking spaces are first determined based on data collected by sensors. In one approach, a vehicle camera captures images of the area around the vehicle, identifies marked parking lines on the ground where no vehicles are parked, and thus determines the parking space. In another approach, where there are no marked parking lines on the ground, sensor data is acquired using cameras, ultrasonic sensors, or radar. Based on this data, the length, width, and height of the space are determined, and it is assessed whether the space meets the required dimensions for a parking space. If it does, the parking space is determined.

[0078] After a parking space is determined, the contour point data of obstacles within a preset distance from the parking space are acquired by ultrasonic sensors. The preset distance can be ten meters, five meters, or determined by the limitations of the ultrasonic sensor's acquisition capabilities.

[0079] S102. Determine the obstacle edge segment based on the contour point data. The obstacle edge segment is used to represent the edge of the obstacle in a plane parallel to the parking space. The length of the obstacle edge segment is greater than the preset target length. The obstacle edge segment covers multiple contour points.

[0080] In one implementation, a coordinate system is first established. This system can be based on the vehicle itself as the origin or on the parking space. Figure 4 A schematic diagram of the coordinate system provided in this application, such as Figure 4As shown, the origin is the upper right corner of the parking space, the y-axis is the direction of the parking space line, and the x-axis is the direction perpendicular to the y-axis. Based on the contour height of each point, contour points at the same height are defined as contour points in a plane parallel to the parking space. This yields multiple contour points in different planes. Within each plane, obstacle segments are determined based on the contour points.

[0081] To determine obstacle segments, first identify all segments that meet the distance requirements, and then identify the obstacle segments from among them. This can be done in the following way:

[0082] Figure 5 A schematic diagram of determining the initial obstacle line segment in the plane provided in this application, such as Figure 5 As shown, for all contour points in each plane, the initial contour point of a line segment is selected. This can be done by choosing the contour point closest to the parked vehicle, and the ending contour point is determined using the target length as the step size. The target length can be any distance between 0.4m and 0.8m; for example, 0.4m, 0.5m, 0.6m, and 0.8m can be selected. For the ending contour point, a selection can be made at the end of the step size with an error range, and a point can be randomly selected from the selected points, or a point can be selected according to a preset rule, such as the first contour point after the target length. Connecting the initial and ending contour points of the line segment determines an initial obstacle line segment. This allows the initial obstacle line segment to cover multiple contour points within its length range. The ending contour point is then used as the new initial contour point to determine new initial obstacle line segments until no new ending contour point can be determined.

[0083] After obtaining all initial obstacle segments in a plane, which may include segments along the vehicle's longitudinal direction (i.e., the vehicle's body direction) and segments along the vehicle's lateral direction (i.e., the vehicle's front direction), the lateral segments need to be removed to obtain obstacle segments representing the vehicle's longitudinal direction. The direction of these segments indicates the vehicle's posture when entering the parking space and is a key parameter for path planning during parking. Similarly, all obstacle segments in the plane can be obtained. There are several ways to remove lateral segments, such as limiting the direction by a segment direction threshold or determining it by comparing the number of segment directions. These methods will not be elaborated here but will be introduced in subsequent embodiments.

[0084] For vehicles, which are typically 5 meters long, a target length of 0.5 meters can identify approximately ten obstacle edge segments, reducing the number of segments that need to be drawn using only sensors to determine obstacle data points. Because the number of segments is reduced, the directional error of the segments is minimized, making the direction of the obstacle edge segments more accurate.

[0085] Because the contour points acquired by ultrasonic sensors are at different heights, a direct line connecting different heights indicates a vertical direction. One approach is to define initial obstacle line segments on different planes, representing the edge direction of the obstacle at a certain height. Another approach is to draw lines that do not distinguish between planes, encompassing different heights, thus indicating vertical direction. In this case, a projection onto a plane parallel to the parking space yields the horizontal direction.

[0086] It should be noted that the plane where the parking space is located is used here because the vehicle or parking space may be located on a slope, and the plane where the parking space is located also represents the direction of the terrain, thus avoiding the error caused by using the horizontal plane.

[0087] S103. Determine the parking posture angle of the vehicle based on the edge line segments of the obstacle.

[0088] In one approach, after obtaining the obstacle edge segments, the coordinates of the segment endpoints in the coordinate system are determined, i.e., the optimized obstacle data. An extended Kalman filter model is established based on the vehicle dynamics model and sensor characteristics, and initial parameters are set. The data is input into the extended Kalman filter for iterative calculation. In each iteration, the target attitude angle of the vehicle is estimated based on the state prediction equation and the observation update equation, and the uncertainty of the estimation result is updated based on the covariance update equation. After multiple iterations, the converged target parking attitude angle is obtained. This angle is then compared and evaluated using the nearest and farthest obstacle cluster segments to finally determine the heading angle reference angle, which is then output to the automatic parking system.

[0089] In one implementation, the average value of the directional angles of the obstacle line segments is determined in the coordinate system as the target heading angle of the vehicle at this moment (i.e., the target parking attitude angle).

[0090] This embodiment provides a method for determining a vehicle's parking posture angle. The method includes: acquiring contour point data of obstacles within a preset distance of the parking space; determining obstacle edge segments based on the contour point data, whereby the obstacle edge segments represent the edges of obstacles in a plane parallel to the parking space, and the length of the obstacle edge segments is greater than a preset target length; and determining the vehicle's parking posture angle based on the obstacle edge segments. This method, by representing the edges of obstacles with line segments of a target length, reduces the influence of factors such as environmental noise and sensor errors, thereby achieving accurate calculation of the vehicle's parking posture angle.

[0091] The following section provides a detailed explanation of how to determine obstacle segments.

[0092] Method 1: Filter by quantity.

[0093] Within a defined coordinate system, the line segment directions of the initial obstacle edge segments in each plane are obtained. Based on these line segment directions across all planes, the number of segments in each direction is sorted, effectively summarizing all initial obstacle edge line segment directions. A direction is considered to be within the error angle range; for example, two directions separated by 1° are considered one direction. After sorting, the line segment direction with the most segments in the sorted sequence is determined as the target direction. Finally, the line segments in the target direction are used as the obstacle edge segments.

[0094] In this way, the direction of the edge line can be determined based on the line segment with the most obstacles.

[0095] Method 2: Filter by direction.

[0096] In this method, under a defined coordinate system, the direction of the parking space edge line is determined based on the direction of the parking space. An angle range threshold, such as 45°, 50°, or 60°, is added to the parking space edge line direction to obtain a preset direction angle threshold. The preset direction angle must be less than 80° to exclude lateral initial obstacle edge lines. For example, taking the upper right corner of the parking space as the origin, the parking space edge line direction is 90°, and the added angle range threshold is 45°. Therefore, the obstacle edge line segments need to be within the preset direction angle threshold (45° to 135°). The line segment direction of the initial obstacle edge line segments in each plane is obtained; based on the line segment directions of the initial obstacle edge line segments in all planes, the initial obstacle edge line segments within the preset direction angle threshold are determined as obstacle edge line segments.

[0097] By filtering each plane in this way, only the edge segments of obstacles on the side of the vehicle can be retained. This method has a wider range of applications and can be used in scenarios such as parallel parking or obstacles placed laterally.

[0098] When there are obstacles on both sides of the parking space, the parking angle needs to be determined by considering the edge segments of the obstacles on both sides.

[0099] Obtain the left-side average of the directional angle of the obstacle edge line segment to the left of the parking space.

[0100] Obtain the average value of the direction angle of the obstacle edge line segment to the right of the parking space.

[0101] The parking posture angle is determined based on the average values ​​of the left and right sides.

[0102] In one implementation, the average values ​​of the left and right sides are averaged to obtain the parking posture angle.

[0103] In another implementation, the left and right sides can be weighted and averaged to obtain the parking posture angle. The weighting coefficient can be determined based on the distance of the vehicle's left or right side from the parking space, or based on the magnitude of the left and right directions.

[0104] When there are obstacles on both sides, the two obstacles may face the same direction or different directions, and their opening angles are different. Taking into account the openings on both sides and then determining the target parking attitude angle can give the vehicle more room for adjustment.

[0105] The following complete example illustrates a parking space with an obstacle on only one side.

[0106] Figure 6 Schematic diagram of the method for determining the vehicle parking attitude angle provided in this application Figure 2 ,like Figure 6 As shown, it includes the following steps:

[0107] S201. Determine parking spaces based on sensor data.

[0108] In this step, data about the surrounding environment is collected using ultrasonic, laser, or other sensors to identify available parking spaces. The parking spaces are then scanned to obtain parameters such as their length, width, and distance.

[0109] S202. Determine the edge line segment of the obstacle within the preset distance of the parking space.

[0110] After identifying a parking space, the system filters out obstacles based on information from ultrasonic sensors.

[0111] In one approach, the center positions and orientations of each end of an obstacle segment of the target length are projected onto a plane in space. If all obstacles lie on the same plane, they can be considered to be distributed along the same line and aligned with an axis parallel to this line. In this case, the orientation of the side obstacle edge segments can be determined using the normal vector of this plane. If all obstacles are not on the same plane but distributed across multiple different planes, it is necessary to first filter the planes containing these obstacles, then select the obstacle edge segments with the largest number, and store the coordinates of each end of the corresponding obstacle edge segments for later use. Preferably, the orientation of the obstacle edge segments is determined using Euler's formula. Optionally, the two selected obstacle edge segments may intersect or be adjacent.

[0112] In one approach, the specific method for determining the initial obstacle edge segment, and the process for determining the obstacle edge segment from the initial obstacle edge segment, are similar to those described in the aforementioned method embodiments, and will not be repeated here.

[0113] S203. Determine the initial heading angle based on vehicle perception information.

[0114] The vehicle's current attitude angles, including yaw, pitch, and roll angles, are obtained through vehicle attitude sensors, providing a reference for subsequent parking maneuvers.

[0115] S204. Update the heading angle based on the initial heading angle and the updated obstacle edge information.

[0116] After obtaining the obstacle edge information, the obstacle's position information is determined and stored. The position information can be obtained by measuring distance using sensors to obtain information such as its distance in the parking coordinate system, thereby determining the relative position of the obstacle in the parking coordinate system.

[0117] The obstacle edge segments detected by the sensor that are longer than the target length are selected as the candidate obstacle segments. The endpoint coordinate data are input into a pre-established extended Kalman filter model. The target length is any value between 0.4m and 0.8m, preferably 0.65m.

[0118] As the depth of the parking space increases, obstacle edge information is updated. The updated data is input into an extended Kalman filter (EDF), and the EDF algorithm iteratively calculates the state-space model. During prediction, the current state value and its covariance matrix are predicted based on the previous state estimate and system dynamics equations. During updating, the predicted heading angle is compared with the measured target heading angle (i.e., the average of the direction angles of the edge segments) from the ultrasonic sensor. The Kalman gain is used to fuse the measured value into the predicted value to obtain the current state estimate, and the covariance matrix is ​​updated to reflect the uncertainty of the estimate. Finally, the EDF outputs the converged obstacle attitude angle. The target attitude angle calculation module calculates different attitude angles for single-sided and double-sided obstacles. For single-sided obstacle parking spaces, the angle is referenced from the angle of the single-sided obstacle; for double-sided obstacle parking spaces, the average of the calculated angles of both obstacles is used as the target attitude heading angle.

[0119] S205. Determine whether the heading angle meets the allowable error conditions.

[0120] To ensure that the vehicle's heading angle is within the allowable error range, error allowance conditions are set to ensure that the vehicle can safely and accurately enter the parking space.

[0121] If the heading angle error is not met, return to S204 to continue updating the heading angle.

[0122] If the heading angle error allowable condition is met, then proceed to step S206.

[0123] S206. Parking control based on heading angle.

[0124] Based on the determined final heading angle, the system controls the vehicle's steering and speed to perform parking operations, including adjusting direction, controlling acceleration and deceleration, to ensure the vehicle completes parking safely and smoothly. Before controlling parking, obstacle boundaries can be further determined based on the outline points of obstacles to ensure that the vehicle's planned path does not touch the obstacle boundaries.

[0125] The entire process provides a clear logical structure for the automated parking system. By fusing data from ultrasonic sensors and vehicle attitude sensors using an extended Kalman filter algorithm, the impact of noise and interference on the calculation results is effectively reduced, improving the accuracy and stability of attitude angle calculations. The extended Kalman filter algorithm is recursive, enabling real-time updates to the estimation results and adaptive adjustments to model parameters based on new observation data, thereby enhancing the system's robustness and adaptability.

[0126] This invention is not only applicable to ultrasonic parking systems, but can also be extended to other autonomous driving scenarios that require attitude angle calculation, such as automatic following and automatic obstacle avoidance.

[0127] Figure 7 A schematic diagram of the structure of the vehicle target attitude angle determination device provided in this application is shown below. Figure 7 As shown, the vehicle target attitude angle determination device 70 provided in this embodiment includes:

[0128] The acquisition module 701 is used to acquire the outline point data of obstacles within a preset distance of the parking space;

[0129] The line segment determination module 702 is used to determine the obstacle edge line segment based on the contour point data. The obstacle edge line segment is used to represent the edge of the obstacle in a plane parallel to the parking space. The length of the obstacle edge line segment is greater than the preset target length. The obstacle edge line segment covers multiple contour points.

[0130] Angle determination module 703 is used to determine the parking posture angle of the vehicle based on the edge line segment of the obstacle.

[0131] Optionally, the line segment determination module 702 is specifically used for:

[0132] Based on the outline points of the obstacle, determine all outline points in each plane parallel to the parking space;

[0133] For all contour points in each plane, determine the initial obstacle line segment based on the target length;

[0134] Based on the initial obstacle edge segments in each plane, determine the obstacle edge segments in all planes.

[0135] Optionally, the line segment determination module 702 is further configured to:

[0136] Obtain the line segment direction of the initial obstacle edge line segment in each plane;

[0137] Based on the line direction of all initial obstacle edge segments in the plane, the initial obstacle edge segments within a preset direction angle threshold are determined as the obstacle edge segments.

[0138] Optionally, the line segment determination module 702 is further configured to:

[0139] Obtain the line segment direction of the initial obstacle edge line segment in each plane;

[0140] Sort the number of segments under each initial obstacle edge line segment direction according to the line segment direction of all planes;

[0141] The direction of the line segment with the most line segments in the sorting is determined as the target direction;

[0142] The line segment in the target direction is taken as the edge line segment of the obstacle.

[0143] Optionally, the line segment determination module 702 is further configured to:

[0144] For all contour points in each plane, the contour point closest to the parked vehicle is taken as the initial contour point of the line segment, and the target length is used as the step size to determine the ending contour point of the line segment.

[0145] An initial obstacle line segment is determined based on the initial contour point and the ending contour point of the line segment;

[0146] Using the end contour point of the line segment as the initial contour point of the new line segment, a new initial obstacle line segment is determined until a new end contour point of the line segment cannot be determined.

[0147] Optionally, the angle determination module 703 is specifically used for:

[0148] The parking attitude angle is determined based on the obstacle edge segments using a pre-built extended Kalman filter model.

[0149] Optionally, the angle determination module 703 is further configured to:

[0150] The parking posture angle is determined based on the average value of the directional angles of the obstacle edge segments.

[0151] Optionally, if there are obstacles on both sides of the parking space, the angle determination module 703 is further used for:

[0152] Obtain the left-side average value of the direction angle of the obstacle edge line segment on the left side of the parking space;

[0153] Obtain the average right-side value of the direction angle of the obstacle edge line segment to the right of the parking space;

[0154] The parking posture angle is determined based on the average value on the left and the average value on the right.

[0155] Optionally, the device includes a parking module 704, the parking module 707 being used for:

[0156] The parking posture angle is input into the automatic parking system for parking.

[0157] The vehicle target attitude angle determination device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0158] Figure 8 A schematic diagram of the structure of the electronic device provided in this application. Figure 8 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0159] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0160] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0161] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0162] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0163] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0164] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0165] This application also provides a vehicle including a controller for performing the above-described method.

[0166] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0167] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0168] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0169] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0170] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0171] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0172] If a function is implemented as a software functional unit and sold or used as an independent product, it 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 part 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 personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of 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.

[0173] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0174] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for determining the parking posture angle of a vehicle, characterized in that, The method includes: Obtain the outline point data of obstacles within a preset distance of the parking space; Obstacle edge segments are determined based on the contour point data. The obstacle edge segments are used to represent the edges of obstacles in a plane parallel to the parking space. The length of the obstacle edge segments is greater than a preset target length, and the obstacle edge segments cover multiple contour points. The parking posture angle of the vehicle is determined based on the edge line segments of the obstacle; The step of determining the parking posture angle of the vehicle based on the edge segment of the obstacle and the parking space includes: The parking attitude angle is determined based on the obstacle edge segments using a pre-built extended Kalman filter model.

2. The method according to claim 1, characterized in that, Determining the obstacle edge segment based on the obstacle's contour points includes: Based on the outline points of the obstacle, determine all outline points in each plane parallel to the parking space; For all contour points in each plane, determine the initial obstacle line segment based on the target length; Based on the initial obstacle edge segments in each plane, determine the obstacle edge segments in all planes.

3. The method according to claim 2, characterized in that, The step of determining the obstacle edge segments in all planes based on the initial obstacle edge segments in each plane includes: Obtain the line segment direction of the initial obstacle edge line segment in each plane; Based on the line direction of all initial obstacle edge segments in the plane, the initial obstacle edge segments within a preset direction angle threshold are determined as the obstacle edge segments.

4. The method according to claim 2, characterized in that, The step of determining the obstacle edge segments in all planes based on the initial obstacle edge segments in each plane includes: Obtain the line segment direction of the initial obstacle edge line segment in each plane; Sort the number of segments under each initial obstacle edge line segment direction according to the line segment direction of all planes; The direction of the line segment with the most line segments in the sorting is determined as the target direction; The line segment in the target direction is taken as the edge line segment of the obstacle.

5. The method according to claim 2, characterized in that, The step of determining the initial obstacle segment based on the target length includes: The initial contour point of the line segment is determined by using the contour point closest to the parked vehicle as the initial contour point, and the target length is used as the step size to determine the ending contour point of the line segment. An initial obstacle line segment is determined based on the initial contour point and the ending contour point of the line segment; Using the end contour point of the line segment as the initial contour point of the new line segment, a new initial obstacle line segment is determined until a new end contour point of the line segment cannot be determined.

6. The method according to any one of claims 1 to 4, characterized in that, The step of determining the parking posture angle of the vehicle based on the edge segment of the obstacle and the parking space includes: The parking posture angle is determined based on the average value of the directional angles of the obstacle edge segments.

7. The method according to any one of claims 1 to 4, characterized in that, If there are obstacles on both sides of the parking space, determining the parking posture angle of the vehicle based on the edge segments of the obstacles includes: Obtain the left-side average value of the direction angle of the obstacle edge line segment on the left side of the parking space; Obtain the average right-side value of the direction angle of the obstacle edge line segment to the right of the parking space; The parking posture angle is determined based on the average value on the left and the average value on the right.

8. A device for determining the target attitude angle of a vehicle, characterized in that, The device includes: The acquisition module is used to acquire the outline point data of obstacles within a preset distance of the parking space; The line segment determination module is used to determine the obstacle edge line segment based on the contour point data. The obstacle edge line segment is used to represent the edge of the obstacle in a plane parallel to the parking space. The length of the obstacle edge line segment is greater than a preset target length, and the obstacle edge line segment of the target length covers multiple contour points. An angle determination module is used to determine the parking posture angle of the vehicle based on the edge line segments of the obstacle. The angle determination module is specifically used for: The parking attitude angle is determined based on the obstacle edge segments using a pre-built extended Kalman filter model.

9. A vehicle, characterized in that, The vehicle includes a controller for performing the method as described in any one of claims 1-7.

Images