Automatic parking method, device, equipment and medium
By calculating the correlation between the vehicle trajectory point and the vehicle orientation, determining the body polygon and determining the brake stop, the problem of existing parking solutions being unable to predict the collision between the body area and dynamic obstacles when the steering wheel angle changes, and improving the safety of parking and driving experience.
Patent Information
- Application Number
- CN202411587033.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-07
- Publication Date
- 2025-01-07
AI Technical Summary
The existing parking solution cannot predict the area where the body rigid body will pass when the steering wheel angle changes in real time, resulting in poor driving experience and in real time whether there is a collision between the dynamic obstacle and the body, resulting in problems such as misbraking and missing brakes.
By calculating the trajectory points on the vehicle trajectory and the current vehicle orientation, determine the vehicle body polygon, and determine whether the brake needs to be stopped based on the change in the steering wheel angle to avoid misbraking and missing brakes.
Improves parking safety and driving experience, avoids misbraking and missing brakes, and ensures the accuracy of dynamic obstacle avoidance.
Smart Images
Figure CN119261879A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of autonomous driving technology, and in particular to an automatic parking method, device, equipment and medium. Background Art
[0002] The current parking solution cannot predict the area that the vehicle body will pass through when the steering wheel angle changes in real time, which brings a bad driving experience to the driver. In addition, the current parking solution can only achieve dynamic obstacle avoidance based on the fixed steering wheel angle, and cannot predict whether the dynamic obstacle will collide with the vehicle body when the steering wheel angle changes in real time, which makes the current dynamic obstacle avoidance strategy have the problems of false braking and missed braking. Therefore, the above problems urgently need to be solved by technical personnel in this field. Summary of the invention
[0003] In view of this, the purpose of the present invention is to provide an automatic parking method, device, equipment and medium, which can calculate the area to be passed by the vehicle body and determine whether to brake the vehicle in combination with the change of the steering wheel angle, thereby avoiding false braking and missed braking and improving parking safety. The specific scheme is as follows:
[0004] In a first aspect, the present application discloses an automatic parking method, comprising:
[0005] Calculating a vehicle body polygon according to the track points on the traversed vehicle track and the current vehicle orientation, and associating the track points, the current vehicle orientation and the vehicle body polygon to obtain an association relationship;
[0006] Determine a first target trajectory point that is closest to the current position of the vehicle in Euclidean distance from the vehicle trajectory, and obtain a first vehicle body polygon corresponding to the first target trajectory point based on the association relationship; wherein the vehicle body polygon is a polygon that represents the contour of the vehicle body;
[0007] Determine a target left boundary and a target right boundary according to the vertex coordinate index of the first vehicle body polygon, and determine an area to be passed by the vehicle body according to the target left boundary and the target right boundary;
[0008] Automatic parking is performed according to the area to be passed by the vehicle body, and the polygon where the obstacle is located is determined according to the driving speed of the target obstacle. Then, it is determined whether to brake the vehicle according to the first vehicle body polygon and the polygon where the obstacle is located until parking is completed.
[0009] Optionally, the calculating of the vehicle body polygon according to the track points on the traversed vehicle track and the current vehicle orientation, and associating the track points, the current vehicle orientation and the vehicle body polygon to obtain an association relationship include:
[0010] Calculating a second body polygon and a third body polygon according to the last track point on the vehicle track, the current vehicle orientation, the body length and the body width, and determining a union polygon of the second body polygon and the third body polygon to obtain a target body polygon;
[0011] The last track point is deleted, and the track points on the vehicle track are traversed from back to front to obtain the current last track point, and then the process jumps to the step of calculating the third vehicle body polygon and determining the union polygon of the second vehicle body polygon and the third vehicle body polygon, until the traversal is completed to obtain a plurality of target vehicle body polygons;
[0012] Each of the target vehicle body polygons is respectively associated with the corresponding last trajectory point and the corresponding current vehicle orientation to obtain the association relationship.
[0013] Optionally, the calculating the second body polygon and the third body polygon according to the last track point on the vehicle track, the current vehicle orientation, the body length and the body width includes:
[0014] The last trajectory point is determined as the center point, and four vertex coordinates are obtained according to the current vehicle orientation, the vehicle body length and the vehicle body width;
[0015] The four vertex coordinates are translated by a target length according to the current vehicle orientation to obtain new four vertex coordinates, and the second body polygon and the third body polygon are calculated based on the new four vertex coordinates; wherein the target length is obtained based on the body length and the body rear overhang length.
[0016] Optionally, determining a target left boundary and a target right boundary according to the vertex coordinate index of the first vehicle body polygon includes:
[0017] Determine a first trajectory point and a second trajectory point from the vehicle trajectory according to the vehicle gear position, determine a left front vertex index and a right front vertex index of the vehicle according to the first trajectory point, and determine a left rear vertex index and a right rear vertex index of the vehicle according to the second trajectory point;
[0018] The target left boundary is determined according to the left front vertex index and the left back vertex index, and the target right boundary is determined according to the right front vertex index and the right back vertex index.
[0019] Optionally, determining the first trajectory point and the second trajectory point from the vehicle trajectory according to the vehicle gear position includes:
[0020] If the gear position of the vehicle is a forward gear position, the last track point of the vehicle track is determined as the first track point, and the first track point of the vehicle track is determined as the second track point;
[0021] If the gear position of the vehicle is a reverse gear position, the first trajectory point of the vehicle trajectory is determined as the first trajectory point, and the last trajectory point of the vehicle trajectory is determined as the second trajectory point.
[0022] Optionally, determining the polygon where the obstacle is located according to the travel speed of the target obstacle includes:
[0023] Taking the current obstacle orientation of the target obstacle as the first coordinate axis direction and the orientation perpendicular to the first coordinate axis as the second coordinate axis direction, calculating a first driving speed component of the target obstacle in the first coordinate axis direction and a second driving speed component in the second coordinate axis direction;
[0024] Determine the target total time based on the target travel time and the target safety time; wherein the target travel time is the time required for the vehicle to travel from the starting point to the first target trajectory point;
[0025] A first boundary is determined according to the first driving speed component and the target total time, a second boundary is determined according to the second driving speed component and the target total time, and then a polygon where the obstacle is located is determined according to the first boundary and the second boundary.
[0026] Optionally, judging whether to brake the vehicle according to the first vehicle body polygon and the polygon where the obstacle is located includes:
[0027] Determine a second target trajectory point corresponding to the target total time, and obtain a fourth vehicle body polygon corresponding to the second target trajectory point based on the association relationship;
[0028] A difference polygon between the first vehicle body polygon and the fourth vehicle body polygon is determined to obtain a fifth vehicle body polygon, and whether to brake the vehicle is determined based on the shortest Euclidean distance between the fifth vehicle body polygon and the polygon where the obstacle is located.
[0029] In a second aspect, the present application discloses an automatic parking device, comprising:
[0030] A vehicle body polygon association module, used for calculating a vehicle body polygon according to a track point on a traversed vehicle track and a current vehicle orientation, and associating the track point, the current vehicle orientation and the vehicle body polygon to obtain an association relationship;
[0031] A body polygon determination module, used to determine a first target track point with the closest Euclidean distance to the current position of the vehicle from the vehicle track, and obtain a first body polygon corresponding to the first target track point based on the association relationship; wherein the body polygon is a polygon representing the contour of the body;
[0032] A module for determining an area to be passed, used for determining a target left boundary and a target right boundary according to the vertex coordinate index of the first vehicle body polygon, and determining an area to be passed by the vehicle body according to the target left boundary and the target right boundary;
[0033] The parking and obstacle avoidance module is used to automatically park the vehicle according to the area to be passed by the vehicle body, determine the polygon where the obstacle is located according to the driving speed of the target obstacle, and then determine whether to brake the vehicle according to the first vehicle body polygon and the polygon where the obstacle is located until parking is completed.
[0034] In a third aspect, the present application discloses an electronic device, including:
[0035] Memory, used to store computer programs;
[0036] A processor is used to execute the computer program to implement the automatic parking method disclosed above.
[0037] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the automatic parking method disclosed above is implemented.
[0038] It can be seen that the present application discloses an automatic parking method, including: calculating a vehicle body polygon based on trajectory points on a traversed vehicle trajectory and a current vehicle orientation, and associating the trajectory points, the current vehicle orientation and the vehicle body polygon to obtain an association relationship; determining a first target trajectory point from the vehicle trajectory that is closest to the Euclidean distance of the vehicle's current position, and obtaining a first vehicle body polygon corresponding to the first target trajectory point based on the association relationship; wherein the vehicle body polygon is a polygon that characterizes the vehicle body contour; determining a target left boundary and a target right boundary based on the vertex coordinate index of the first vehicle body polygon, and determining an area to be passed by the vehicle body based on the target left boundary and the target right boundary; performing automatic parking based on the area to be passed by the vehicle body, and determining the polygon where the obstacle is located based on the driving speed of the target obstacle, and then judging whether to brake the vehicle based on the first vehicle body polygon and the polygon where the obstacle is located until parking is completed. From the above, it can be seen that since the predicted vehicle trajectory includes the position coordinates and driving direction of the vehicle at certain moments in the future, as the parking process proceeds, the current orientation of the vehicle at different moments is constantly changing, that is, the steering wheel angle in the present application is constantly changing. In this case, the present application can calculate the polygon representing the vehicle body contour based on the trajectory points on the traversed vehicle trajectory and the vehicle orientation, and calculate the area to be passed by the vehicle body based on the first vehicle body polygon corresponding to the first target trajectory point with the closest Euclidean distance to the current position of the vehicle, so that the driver can see it intuitively, thereby improving the driver's driving experience. Furthermore, during the parking process, the present application combines the change in the steering wheel angle, that is, the difference in the vehicle orientation, and determines whether to brake the vehicle based on the polygon where the obstacle is located and the first vehicle body polygon of the vehicle. In this way, it can avoid false braking and missed braking, and improve parking safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0040] Figure 1 A flow chart of an automatic parking method disclosed in this application;
[0041] Figure 2 A schematic diagram of an area to be passed by a vehicle disclosed in the present application;
[0042] Figure 3 A schematic diagram of a target trajectory disclosed in the present application;
[0043] Figure 4 A schematic diagram of a rectangular frame D disclosed in the present application;
[0044] Figure 5 A schematic diagram of a rectangular frame merging disclosed in the present application;
[0045] Figure 6 A schematic diagram of a vertex coordinate index disclosed in this application;
[0046] Figure 7 A schematic diagram of the coordinates of a dynamic obstacle disclosed in the present application;
[0047] Figure 8 A schematic diagram of a rectangular frame where a dynamic obstacle is located disclosed in the present application;
[0048] Fig. 9 A schematic diagram of a dynamic obstacle avoidance method disclosed in the present application;
[0049] Fig.10 This is a schematic diagram of the structure of an automatic parking device disclosed in this application;
[0050] Fig.11 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION
[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0052] The current parking solution cannot predict the area that the vehicle body will pass through when the steering wheel angle changes in real time, which brings a bad driving experience to the driver. In addition, the current parking solution can only achieve dynamic obstacle avoidance based on the fixed steering wheel angle, and cannot predict whether the dynamic obstacle will collide with the vehicle body when the steering wheel angle changes in real time, which makes the current dynamic obstacle avoidance strategy have the problems of false braking and missed braking. Therefore, the above problems urgently need to be solved by technical personnel in this field.
[0053] To this end, an embodiment of the present application proposes an automatic parking solution that can calculate the area to be passed by the vehicle body and determine whether to brake the vehicle based on the change in the steering wheel angle to avoid false braking and missed braking.
[0054] The present application embodiment discloses an automatic parking method, see Figure 1 As shown, the method includes:
[0055] Step S11: Calculate the vehicle body polygon according to the track points on the traversed vehicle track and the current vehicle orientation, associate the track points, the current vehicle orientation and the vehicle body polygon to obtain an association relationship.
[0056] Figure 2 A schematic diagram of a vehicle-to-pass area is disclosed. The area between the target left boundary and the target right boundary is the vehicle-to-pass area. After the vehicle-to-pass area is calculated, it is displayed through an interface so that the driver can view it intuitively. The calculation process of the vehicle-to-pass area is described below:
[0057] First, determine the vehicle trajectory. The vehicle trajectory is represented by trajectory points with equal intervals, usually 0.1 meters. The trajectory point elements include: the center coordinates of the vehicle's rear axle (x, y) and the current vehicle orientation (yaw), see Figure 3 As shown. Furthermore, the body polygon is calculated based on the track points on the traversed vehicle track and the current vehicle orientation. Specifically, the second body polygon and the third body polygon are calculated based on the last track point on the vehicle track, the current vehicle orientation, the body length and the body width, and the union polygon of the second body polygon and the third body polygon is determined to obtain the target body polygon, the last track point is deleted, the track points on the vehicle track are traversed from back to front, the current last track point is obtained, and the step of calculating the third body polygon and determining the union polygon of the second body polygon and the third body polygon is jumped to the end of the traversal to obtain a number of target body polygons.
[0058] It should be pointed out that when calculating the second body polygon and the third body polygon, the last trajectory point is determined as the center point, and the four vertex coordinates are obtained according to the current vehicle orientation, body length and body width, and the four vertex coordinates are translated by the target length according to the vehicle orientation to obtain new four vertex coordinates, and the second body polygon and the third body polygon are calculated based on the new four vertex coordinates; wherein the target length is the difference between the body length and the rear overhang length of the body.
[0059] See also Figure 4As shown, trajectory point C is the last trajectory point. With trajectory point C as the center point of the rear axle of the vehicle, rectangular frame D (i.e., the second body polygon) is calculated in the above manner. With trajectory point E as the center point of the rear axle of the vehicle, rectangular frame F (i.e., the third body polygon) is calculated. Furthermore, a tool library (such as the boost library) is used to calculate the polygonal union of rectangular frame D and rectangular frame F, and the polygonal union is reassigned to rectangular frame D. It can be understood that the polygonal union represents the union of the body contours of all trajectory points from the end point of the trajectory to a certain trajectory point in the middle. In addition, in the first calculation, trajectory point C and trajectory point E are the same trajectory point, but in the subsequent calculation process, trajectory point E will traverse all trajectory points on the entire vehicle trajectory from back to front. Figure 5 It is the polygon union Z when traversing to the fourth trajectory point.
[0060] Furthermore, each current second vehicle body polygon is associated with the corresponding last trajectory point and vehicle orientation to obtain an association relationship, which is then stored in the container G.
[0061] Step S12: determining a first target trajectory point on the vehicle trajectory that is closest to the current position of the vehicle in Euclidean distance, and obtaining a first vehicle body polygon corresponding to the first target trajectory point based on the association relationship; wherein the vehicle body polygon is a polygon that represents the contour of the vehicle body.
[0062] In this embodiment, the Euclidean distance between each trajectory point in the vehicle trajectory and the current position of the vehicle is determined, and the first target trajectory point closest to the Euclidean distance to the current position of the vehicle is determined, and then the first vehicle body polygon corresponding to the first target trajectory point is obtained based on the association relationship in the container G.
[0063] Step S13: determining a target left boundary and a target right boundary according to the vertex coordinate index of the first vehicle body polygon, and determining an area to be passed by the vehicle body according to the target left boundary and the target right boundary.
[0064] Determine the first and second track points from the vehicle track according to the vehicle gear position, determine the left front vertex index leftFrontInde and the right front vertex index rightFrontIndex of the vehicle according to the first track point, and determine the left rear vertex index leftBackIndexx and the right rear vertex index rightBackIndex of the vehicle according to the second track point. Specifically, take the first track point as the center point of the rear axle of the vehicle, calculate the body contour, and use the left front coordinate of the body contour to query the coordinates of the first body polygon to obtain the left front vertex index, and use the right front coordinate of the body contour to query the coordinates of the first body polygon to obtain the right front vertex index, take the second track point as the center point of the rear axle of the vehicle, calculate the body contour, use the left rear coordinate of the body contour to query the coordinates of the first body polygon to obtain the left rear vertex index, and use the right rear coordinate of the body contour to query the coordinates of the first body polygon to obtain the right rear vertex index. Further, determine the target left boundary according to the left front vertex index and the left rear vertex index, determine the target right boundary according to the right front vertex index and the right rear vertex index, and determine the area between the target left boundary and the target right boundary as the area to be passed by the vehicle body.
[0065] It should be pointed out that if the vehicle gear is in the forward gear (D gear), the last trajectory point of the vehicle trajectory is determined as the first trajectory point (upper point), and the first trajectory point of the vehicle trajectory is determined as the second trajectory point (lower point); if the vehicle gear is in the reverse gear (R gear), the first trajectory point of the vehicle trajectory is determined as the first trajectory point, and the last trajectory point of the vehicle trajectory is determined as the second trajectory point.
[0066] See also Figure 6 As shown in the figure, if the vehicle gear is in D gear, then leftBackIndex is used as the starting index, leftFrontIndex is used as the end index, and the point between the two is used as the left boundary of the target, rightBackIndex is used as the starting index, rightFrontIndex is used as the end index, and the point between the two is used as the right boundary of the target. If the vehicle gear is in R gear, then leftFrontIndex is used as the starting index, leftBackIndex is used as the end index, and the point between the two is used as the left boundary of the target, rightFrontIndex is used as the starting index, rightBackIndex is used as the end index, and the point between the two is used as the right boundary of the target.
[0067] Step S14: Automatically park the vehicle according to the area to be passed by the vehicle body, determine the polygon where the obstacle is located according to the driving speed of the target obstacle, and then determine whether to brake the vehicle according to the first vehicle body polygon and the polygon where the obstacle is located until parking is completed.
[0068] In this embodiment, the area that the vehicle body is to pass through is displayed so that the driver can perform automatic parking according to the area that the vehicle body is to pass through, thereby improving the driver's driving experience.
[0069] Furthermore, during automatic parking, the vehicle's steering wheel angle changes in real time. Traditional technology cannot predict collisions with dynamic obstacles in this situation, which can easily lead to misbraking and missed braking.
[0070] To this end, this embodiment determines whether to brake the vehicle based on the first vehicle body polygon and the obstacle polygon. Figure 7 As shown, the obstacle direction of the target obstacle (i.e., the dynamic obstacle) is taken as the first coordinate axis direction (x-axis) and the direction perpendicular to the first coordinate axis is taken as the second coordinate axis direction (y-axis), and the first driving speed component v of the target obstacle in the first coordinate axis direction is calculated. x and the second travel speed component v in the direction of the second coordinate axis y , and determine the target total time based on the target driving time and the target safety time; wherein the target driving time is the time required for the vehicle to travel from the starting point to the first target trajectory point. Further, determine the first boundary based on the first driving speed component and the target total time, and determine the second boundary based on the second driving speed component and the target total time, and then determine the polygon J where the obstacle is located based on the first boundary and the second boundary, see Figure 8 It should be noted that the target safety time is the time for calibrating the diagnostic trouble code (DTC), which is the process of setting and adjusting the fault detection and diagnosis function in the vehicle electronic control system.
[0071] Further, a second target trajectory point corresponding to the target total time is determined, and a fourth vehicle body polygon W corresponding to the second target trajectory point is obtained based on the association relationship, and then a difference polygon between the first vehicle body polygon and the fourth vehicle body polygon is determined to obtain a fifth vehicle body polygon V, and whether to brake the vehicle is determined based on the shortest Euclidean distance between the fifth vehicle body polygon and the polygon where the obstacle is located, see Fig. 9 As shown, if the distance between the current dynamic obstacle rectangle J and the polygon V is less than a certain safety distance (the safety distance is related to the obstacle type, such as 1 meter for a car and 0.5 meter for a pedestrian), the vehicle will brake to a stop. In this embodiment, a tool library (such as the boost library) can be used to calculate the shortest Euclidean distance between the rectangle J and the polygon V. Based on the above method, the braking timing of this embodiment for dynamic obstacles is more accurate, thereby reducing the rate of false braking and missed braking.
[0072] It can be seen that the present application discloses an automatic parking method, including: calculating a vehicle body polygon based on trajectory points on a traversed vehicle trajectory and a current vehicle orientation, and associating the trajectory points, the current vehicle orientation and the vehicle body polygon to obtain an association relationship; determining a first target trajectory point from the vehicle trajectory that is closest to the Euclidean distance of the vehicle's current position, and obtaining a first vehicle body polygon corresponding to the first target trajectory point based on the association relationship; wherein the vehicle body polygon is a polygon that characterizes the vehicle body contour; determining a target left boundary and a target right boundary based on the vertex coordinate index of the first vehicle body polygon, and determining an area to be passed by the vehicle body based on the target left boundary and the target right boundary; performing automatic parking based on the area to be passed by the vehicle body, and determining the polygon where the obstacle is located based on the driving speed of the target obstacle, and then judging whether to brake the vehicle based on the first vehicle body polygon and the polygon where the obstacle is located until parking is completed. From the above, it can be seen that since the predicted vehicle trajectory includes the position coordinates and driving direction of the vehicle at certain moments in the future, as the parking process proceeds, the current orientation of the vehicle at different moments is constantly changing, that is, the steering wheel angle in this application is constantly changing. The change in the steering wheel angle will affect the orientation of the vehicle. In this case, the present application can calculate the polygon representing the vehicle body contour based on the trajectory points on the traversed vehicle trajectory and the vehicle orientation, and calculate the area to be passed by the vehicle body based on the first vehicle body polygon corresponding to the first target trajectory point with the closest Euclidean distance to the current position of the vehicle, so that the driver can see it intuitively, which improves the driver's driving experience. Furthermore, during the parking process, the present application combines the change in the steering wheel angle, that is, the difference in the vehicle orientation, and determines whether to brake the vehicle based on the polygon where the obstacle is located and the first vehicle body polygon of the vehicle. In this way, it can avoid false braking and missed braking, and improve parking safety.
[0073] Correspondingly, the present application also discloses an automatic parking device, see Fig.10 As shown, the device comprises:
[0074] A vehicle body polygon association module 11 is used to calculate a vehicle body polygon according to a track point on the traversed vehicle track and a current vehicle orientation, and associate the track point, the current vehicle orientation and the vehicle body polygon to obtain an association relationship;
[0075] The vehicle body polygon determination module 12 is used to determine a first target trajectory point that is closest to the current position of the vehicle in a European distance from the vehicle trajectory, and obtain a first vehicle body polygon corresponding to the first target trajectory point based on the association relationship; wherein the vehicle body polygon is a polygon that represents the contour of the vehicle body;
[0076] A to-be-passed area determination module 13, configured to determine a target left boundary and a target right boundary according to the vertex coordinate index of the first vehicle body polygon, and determine a to-be-passed area of the vehicle body according to the target left boundary and the target right boundary;
[0077] The parking and obstacle avoidance module 14 is used to automatically park the vehicle according to the area to be passed by the vehicle body, determine the polygon where the obstacle is located according to the driving speed of the target obstacle, and then determine whether to brake the vehicle according to the first vehicle body polygon and the polygon where the obstacle is located until parking is completed.
[0078] Among them, for more specific working processes of the above-mentioned modules, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.
[0079] It can be seen that the present application discloses an automatic parking method, including: calculating a vehicle body polygon based on trajectory points on a traversed vehicle trajectory and a current vehicle orientation, and associating the trajectory points, the current vehicle orientation and the vehicle body polygon to obtain an association relationship; determining a first target trajectory point from the vehicle trajectory that is closest to the Euclidean distance of the vehicle's current position, and obtaining a first vehicle body polygon corresponding to the first target trajectory point based on the association relationship; wherein the vehicle body polygon is a polygon that characterizes the vehicle body contour; determining a target left boundary and a target right boundary based on the vertex coordinate index of the first vehicle body polygon, and determining an area to be passed by the vehicle body based on the target left boundary and the target right boundary; performing automatic parking based on the area to be passed by the vehicle body, and determining the polygon where the obstacle is located based on the driving speed of the target obstacle, and then judging whether to brake the vehicle based on the first vehicle body polygon and the polygon where the obstacle is located until parking is completed. From the above, it can be seen that since the predicted vehicle trajectory includes the position coordinates and driving direction of the vehicle at certain moments in the future, as the parking process proceeds, the current orientation of the vehicle at different moments is constantly changing, that is, the steering wheel angle in this application is constantly changing. The change in the steering wheel angle will affect the orientation of the vehicle. In this case, the present application can calculate the polygon representing the vehicle body contour based on the trajectory points on the traversed vehicle trajectory and the vehicle orientation, and calculate the area to be passed by the vehicle body based on the first vehicle body polygon corresponding to the first target trajectory point with the closest Euclidean distance to the current position of the vehicle, so that the driver can see it intuitively, which improves the driver's driving experience. Furthermore, during the parking process, the present application combines the change in the steering wheel angle, that is, the difference in the vehicle orientation, and determines whether to brake the vehicle based on the polygon where the obstacle is located and the first vehicle body polygon of the vehicle. In this way, it can avoid false braking and missed braking, and improve parking safety.
[0080] Furthermore, an embodiment of the present application also provides an electronic device. Fig.11This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.
[0081] Fig.11 The present invention provides a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the automatic parking method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.
[0082] In this embodiment, the power supply 26 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 24 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.
[0083] In addition, the memory 22, as a carrier for storing resources, may be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include a computer program 221, and the storage method may be temporary storage or permanent storage. In addition to the computer program that can be used to complete the automatic parking method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 221 may further include a computer program that can be used to complete other specific tasks.
[0084] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the automatic parking method disclosed above is implemented.
[0085] For the specific steps of the method, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, which will not be described in detail here.
[0086] The various embodiments in this application are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0087] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0088] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0089] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0090] The above is a detailed introduction to an automatic parking method, device, equipment, and storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for a person skilled in the art, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. An automatic parking method, characterized in that: include: Calculating a vehicle body polygon according to the track points on the traversed vehicle track and the current vehicle orientation, and associating the track points, the current vehicle orientation and the vehicle body polygon to obtain an association relationship; Determine a first target trajectory point that is closest to the current position of the vehicle in Euclidean distance from the vehicle trajectory, and obtain a first vehicle body polygon corresponding to the first target trajectory point based on the association relationship; wherein the vehicle body polygon is a polygon that represents the contour of the vehicle body; Determine a target left boundary and a target right boundary according to the vertex coordinate index of the first vehicle body polygon, and determine a region to be passed by the vehicle body according to the target left boundary and the target right boundary; Automatic parking is performed according to the area to be passed by the vehicle body, and the polygon where the obstacle is located is determined according to the driving speed of the target obstacle. Then, it is determined whether to brake the vehicle according to the first vehicle body polygon and the polygon where the obstacle is located until parking is completed.
2. The automatic parking method according to claim 1, characterized in that: The calculating of the vehicle body polygon according to the track points on the traversed vehicle track and the current vehicle orientation, and associating the track points, the current vehicle orientation and the vehicle body polygon to obtain an association relationship include: Calculating a second body polygon and a third body polygon according to the last track point on the vehicle track, the current vehicle orientation, the body length and the body width, and determining a union polygon of the second body polygon and the third body polygon to obtain a target body polygon; The last track point is deleted, and the track points on the vehicle track are traversed from back to front to obtain the current last track point, and then the process jumps to the step of calculating the third vehicle body polygon and determining the union polygon of the second vehicle body polygon and the third vehicle body polygon, until the traversal is completed to obtain a plurality of target vehicle body polygons; Each of the target vehicle body polygons is respectively associated with the corresponding last trajectory point and the corresponding current vehicle orientation to obtain the association relationship.
3. The automatic parking method according to claim 2, characterized in that: The calculating the second body polygon and the third body polygon according to the last track point on the vehicle track, the current vehicle orientation, the body length and the body width includes: The last trajectory point is determined as the center point, and four vertex coordinates are obtained according to the current vehicle orientation, the vehicle body length and the vehicle body width; The four vertex coordinates are translated by a target length according to the current vehicle orientation to obtain new four vertex coordinates, and the second body polygon and the third body polygon are calculated based on the new four vertex coordinates; wherein the target length is obtained based on the body length and the body rear overhang length.
4. The automatic parking method according to claim 1, characterized in that: The step of determining the target left boundary and the target right boundary according to the vertex coordinate index of the first vehicle body polygon includes: Determine a first trajectory point and a second trajectory point from the vehicle trajectory according to the vehicle gear position, determine a left front vertex index and a right front vertex index of the vehicle according to the first trajectory point, and determine a left rear vertex index and a right rear vertex index of the vehicle according to the second trajectory point; The target left boundary is determined according to the left front vertex index and the left back vertex index, and the target right boundary is determined according to the right front vertex index and the right back vertex index.
5. The automatic parking method according to claim 4, characterized in that: The step of determining a first trajectory point and a second trajectory point from the vehicle trajectory according to the vehicle gear position includes: If the gear position of the vehicle is a forward gear position, the last track point of the vehicle track is determined as the first track point, and the first track point of the vehicle track is determined as the second track point; If the gear position of the vehicle is a reverse gear position, the first trajectory point of the vehicle trajectory is determined as the first trajectory point, and the last trajectory point of the vehicle trajectory is determined as the second trajectory point.
6. The automatic parking method according to any one of claims 1 to 5, characterized in that: The step of determining the polygon where the obstacle is located according to the travel speed of the target obstacle comprises: Taking the current obstacle orientation of the target obstacle as the first coordinate axis direction and the orientation perpendicular to the first coordinate axis as the second coordinate axis direction, calculating a first driving speed component of the target obstacle in the first coordinate axis direction and a second driving speed component in the second coordinate axis direction; Determine the target total time based on the target travel time and the target safety time; wherein the target travel time is the time required for the vehicle to travel from the starting point to the first target trajectory point; A first boundary is determined according to the first driving speed component and the target total time, a second boundary is determined according to the second driving speed component and the target total time, and then a polygon where the obstacle is located is determined according to the first boundary and the second boundary.
7. The automatic parking method according to claim 6, characterized in that: The determining whether to brake the vehicle according to the first vehicle body polygon and the polygon where the obstacle is located includes: Determine a second target trajectory point corresponding to the target total time, and obtain a fourth vehicle body polygon corresponding to the second target trajectory point based on the association relationship; A difference polygon between the first vehicle body polygon and the fourth vehicle body polygon is determined to obtain a fifth vehicle body polygon, and whether to brake the vehicle is determined based on the shortest Euclidean distance between the fifth vehicle body polygon and the polygon where the obstacle is located.
8. An automatic parking device, characterized in that: include: A vehicle body polygon association module, used for calculating a vehicle body polygon according to a track point on a traversed vehicle track and a current vehicle orientation, and associating the track point, the current vehicle orientation and the vehicle body polygon to obtain an association relationship; A body polygon determination module, used to determine a first target track point with the closest Euclidean distance to the current position of the vehicle from the vehicle track, and obtain a first body polygon corresponding to the first target track point based on the association relationship; wherein the body polygon is a polygon representing the contour of the body; A module for determining an area to be passed, used for determining a target left boundary and a target right boundary according to the vertex coordinate index of the first vehicle body polygon, and determining an area to be passed by the vehicle body according to the target left boundary and the target right boundary; The parking and obstacle avoidance module is used to automatically park the vehicle according to the area to be passed by the vehicle body, determine the polygon where the obstacle is located according to the driving speed of the target obstacle, and then determine whether to brake the vehicle according to the first vehicle body polygon and the polygon where the obstacle is located until parking is completed.
9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the automatic parking method as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: Used to store a computer program; wherein, when the computer program is executed by a processor, the automatic parking method as described in any one of claims 1 to 7 is implemented.