Vehicle parking method, device and vehicle
By acquiring parking space and attitude information, and using path planning algorithms to generate and optimize driving paths, the problems of high computational load and low efficiency in existing technologies are solved, and safe parking of vehicles is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING JINGWEI HIRAIN TECH CO INC
- Filing Date
- 2023-07-03
- Publication Date
- 2026-06-02
AI Technical Summary
Existing vehicle parking methods involve large computational loads and low efficiency in driving path planning, which makes collisions easy to occur during vehicle parking.
By acquiring the parking space information and vehicle posture information of the target parking space, a driving path is generated using a preset path planning algorithm, and collision point detection is performed. The driving path is updated based on the collision point location information to optimize the path and avoid collisions.
It reduces the amount of calculation required for driving routes, improves planning efficiency, and ensures that vehicles can safely and without collisions park in the target parking space.
Smart Images
Figure CN116872912B_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of vehicle control technology, and in particular relates to a vehicle parking method, device and vehicle. Background Technology
[0002] In related technologies, vehicle driving routes can be planned based on the parking space information of the target parking space to control the vehicle to park in the target parking space along the driving route. Driving route planning can be implemented based on graph search technology. However, in the process of driving route planning based on graph search technology, the number of searches is not fixed and the time consumed by each search is long, resulting in a large amount of computation to generate driving routes and low driving route planning efficiency. Summary of the Invention
[0003] This application provides a vehicle parking method, apparatus, and vehicle, which can solve the problems of large computational load and low driving path planning efficiency in existing vehicle parking methods.
[0004] In a first aspect, embodiments of this application provide a vehicle parking method, the method comprising:
[0005] Obtain parking space information for the target parking space, as well as the vehicle's attitude information and configuration parameters.
[0006] Based on the parking space information, select an available parking area within the target parking space.
[0007] Based on a preset path planning algorithm and attitude information, a driving path for the vehicle to park in the parking area is generated.
[0008] Based on configuration parameters, driving path, and parking area lines, collision point detection is performed on the driving path. The collision point is the intersection of the vehicle traveling along the driving path and the parking line.
[0009] Once a collision point is detected, the driving path is updated based on the collision location information. This involves performing collision point detection on the driving path.
[0010] If no collision point is detected, control the vehicle to park in the parking area along the driving path.
[0011] In some embodiments, the parking space information includes multiple parking space boundary lines of the target parking space. Based on the parking space information, an vacant parking area is selected within the target parking space, including:
[0012] If the parking space information includes obstacle location information within the target parking space, for each obstacle location information, the first sideline is moved along the normal direction of the first sideline to pass through the obstacle location information. Multiple parking space sidelines include the first sideline.
[0013] A parking area is generated within the target parking space based on the first edge line that passes through the obstacle location information, with the obstacle location information located outside the parking area.
[0014] In some embodiments, moving the first sideline along the normal direction of the first sideline before passing the obstacle position information includes:
[0015] Calculate the estimated distance each parking space edge line moves along its own normal direction to the location where it passes the obstacle.
[0016] Determine the minimum movement distance from the expected movement distance, and set the parking space edge line for which the minimum movement distance is calculated as the first edge line.
[0017] In some embodiments, vehicle configuration parameters are obtained, and collision point detection is performed on the driving path based on the configuration parameters, the driving path, and the parking edge lines of the parking area, including:
[0018] Based on the configuration parameters and the driving path, the motion trajectory of multiple preset contour points of the vehicle is calculated. The motion trajectory is the trajectory of the preset contour points when the vehicle moves along the driving path.
[0019] Calculate the pairwise intersections between each motion trajectory and each parking edge line.
[0020] If the intersection point is zero, then the collision point is determined to be zero.
[0021] If the intersection point is not zero, calculate the distance the vehicle travels to the intersection point, and determine the intersection point corresponding to the minimum travel distance as the collision point.
[0022] In some embodiments, updating the driving path based on the collision location information of the collision point includes:
[0023] Based on the collision location information, the path preceding the collision point is selected as the collision-free path in the driving route.
[0024] Based on a preset mapping relationship, a replanning path group corresponding to the collision location information is determined. The preset mapping relationship includes the mapping relationship between the collision location information and the replanning path group.
[0025] Based on the replanned path group, configuration parameters, and the vehicle's simulated attitude information, a replanned path is calculated. The simulated attitude information represents the vehicle's attitude as it travels along a collision-free path to the collision point. The end point of the collision-free path serves as the starting point of the replanned path.
[0026] The driving path is updated to a connected collision-free path and a replanned path.
[0027] In some embodiments, the multiple parking edges include a first parking edge and a second parking edge arranged opposite to each other, and a third parking edge connecting the first parking edge and the second parking edge. Based on a preset mapping relationship, a replanning path group corresponding to the collision location information is determined, including:
[0028] Based on a preset mapping relationship, a first re-planning path group corresponding to the first collision position information is determined. The first re-planning path group includes a first arc segment and a second arc segment with the same path length.
[0029] The first collision location information is that the collision point is located at the second parking line and the rear of the vehicle is closer to the second parking line than the front of the vehicle.
[0030] In some embodiments, the multiple parking edges include a first parking edge and a second parking edge arranged opposite to each other, and a third parking edge connecting the first parking edge and the second parking edge. Based on a preset mapping relationship, a replanning path group corresponding to the collision location information is determined, including:
[0031] Based on the preset mapping relationship, a second planning path group corresponding to the second collision position information is determined. The second planning path group includes a third circular arc segment.
[0032] The second collision location information is that the collision point is located at the first parking line and the front of the vehicle is closer to the first parking line than the rear of the vehicle.
[0033] In some embodiments, the multiple parking edges include a first parking edge and a second parking edge arranged opposite to each other, and a third parking edge connecting the first parking edge and the second parking edge. Based on a preset mapping relationship, a replanning path group corresponding to the collision location information is determined, including:
[0034] Based on a preset mapping relationship, a third planning path group corresponding to the third collision position information is determined. The third planning path group includes a fourth arc segment and a fifth arc segment, with the fourth arc segment having a preset path length.
[0035] The third collision location information indicates that the collision point is located at the third parking edge line.
[0036] Secondly, embodiments of this application provide a vehicle parking device, the device comprising:
[0037] The acquisition module is used to acquire parking space information of the target parking space, as well as the vehicle's attitude information and configuration parameters.
[0038] The adjustment module is used to select vacant parking areas within the target parking space based on parking space information.
[0039] The path generation module is used to generate the driving path for the vehicle to enter the parking area based on a preset path planning algorithm and attitude information.
[0040] The collision detection module is used to detect collision points along the driving path based on configuration parameters, the driving path, and the parking lines of the parking area. The collision point is the intersection of the vehicle traveling along the driving path and the parking line.
[0041] The path generation module is also used to update the driving path based on the collision location information of the detected collision points, performing the following: collision point detection on the driving path.
[0042] The control module is used to control the vehicle to park in the parking area along the driving path if no collision point is detected.
[0043] Thirdly, embodiments of this application provide a vehicle, the vehicle including: a processor and a memory storing computer program instructions.
[0044] The processor implements the vehicle parking method described above when executing computer program instructions.
[0045] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the vehicle parking method described above.
[0046] Fifthly, embodiments of this application provide a computer program product, which includes computer program instructions that, when executed by a processor, implement the vehicle parking method described above.
[0047] In the vehicle parking method, apparatus, and vehicle provided in this application, an empty parking area is first selected in the target parking space so that a collision-free driving path can be calculated based on the empty parking area. This can, to a certain extent, avoid collisions during the process of the vehicle parking in the parking area along the collision-free driving path. By detecting collision points on the driving path and updating the driving path based on the collision position information of the collision points, the driving path is continuously optimized to ensure that no collision occurs during the process of the vehicle parking in the target parking space along the driving path, thereby reducing or avoiding parking failures caused by collisions. Compared with related vehicle parking methods based on graph search technology, the vehicle parking method provided in this application generates a driving path based on a preset path planning algorithm and collision point detection, which has a small computational load and high efficiency in generating the driving path. Attached Figure Description
[0048] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0049] Figure 1 This is one of the schematic flowcharts of a vehicle parking method provided in an embodiment of this application.
[0050] Figure 2 This is a second schematic flowchart of a vehicle parking method provided in an embodiment of this application.
[0051] Figure 3 This is one of the schematic diagrams showing the location of a vehicle and a target parking space provided in an embodiment of this application.
[0052] Figure 4 This is the second schematic diagram of the vehicle and target parking space location provided in one embodiment of this application.
[0053] Figure 5 This is the third schematic flowchart of a vehicle parking method provided in an embodiment of this application.
[0054] Figure 6 This is the fourth schematic flowchart of a vehicle parking method provided in one embodiment of this application.
[0055] Figure 7 This is the fifth flowchart illustrating a vehicle parking method provided in one embodiment of this application.
[0056] Figure 8 This is the sixth schematic flowchart of a vehicle parking method provided in an embodiment of this application.
[0057] Figure 9 This is one of the schematic diagrams of the collision point between a vehicle and a parking edge line provided in an embodiment of this application.
[0058] Figure 10 This is the second schematic diagram of the collision point between the vehicle and the parking edge line provided in one embodiment of this application.
[0059] Figure 11 This is the third schematic diagram of the collision point between the vehicle and the parking edge line provided in one embodiment of this application.
[0060] Figure 12 This is the seventh flowchart illustrating a vehicle parking method provided in one embodiment of this application.
[0061] Figure 13 This is the eighth schematic flowchart of a vehicle parking method provided in an embodiment of this application.
[0062] Figure 14 This is a schematic diagram of a vehicle parking device according to an embodiment of this application.
[0063] Figure 15 This is a schematic diagram of the structure of a vehicle provided in one embodiment of this application. Detailed Implementation
[0064] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples of this application.
[0065] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.
[0066] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The embodiments will now be described in detail with reference to the accompanying drawings.
[0067] To address the problems of the prior art, this application provides a vehicle parking method. The vehicle parking method provided by this application is described below.
[0068] Figure 1 A schematic flowchart of a vehicle parking method according to an embodiment of this application is shown. The method includes the following steps:
[0069] S110, obtains parking space information of the target parking space, as well as vehicle attitude information and configuration parameters;
[0070] S120: Based on parking space information, select an available parking area within the target parking space.
[0071] S130: Generate the driving path for the vehicle to enter the parking area based on the preset path planning algorithm and attitude information;
[0072] S140 performs collision point detection on the driving path based on configuration parameters, driving path, and parking edge lines of the parking area. The collision point is the intersection of the vehicle traveling along the driving path and the parking edge line.
[0073] S150, if a collision point is detected, update the driving path according to the collision location information of the collision point, and execute S140;
[0074] S160, without detecting a collision point, controls the vehicle to park in the parking area along the driving path.
[0075] The vehicle parking method provided in this application can be applied to parallel parking spaces, where the longitudinal axis of a vehicle parked in a parallel parking space is parallel to the traffic direction of the passage. Compared to perpendicular and angled parking spaces, parallel parking spaces have the least impact on the width of the passage.
[0076] The target parking space is the parking space where the vehicle will park. Prior to S110, the user could select any one of several vacant parking spaces near the vehicle as the target parking space by operating the system. The vehicle could also select any one of the several vacant parking spaces as the target parking space based on a preset algorithm. The vehicle can detect and obtain the parking space information of the target parking space through sensors such as cameras and radar. For example, it can acquire an image including the target parking space, identify the parking grid lines in the image, and obtain the parking space information. The parking space information includes multiple parking space edge lines and the position information of the parking space edge lines relative to the vehicle. Optionally, parking grid lines L1, L3, L2, and L4 form a closed quadrilateral parking space. Among them, parking space edge lines are identified by identifying parking grid lines L1, L2, and L3, and parking space over-line is identified by identifying parking grid line L4. During the process of parking the vehicle into the target parking space, the vehicle needs to cross the parking space over-line to enter the target parking space, but the vehicle does not necessarily need to cross the parking space edge line. The parking space boundary line and the parking space overhang line together define the area where the parking space is located.
[0077] The target parking space may also contain obstacles that obstruct vehicle parking. Parking space information may also include obstacles located within the space. Adjusting the parking space boundary lines allows for the selection of an empty area within the target space as a parking area for subsequent processing. An empty parking area indicates that a vehicle can be placed anywhere within that area. The parking space boundary lines can be bent or folded to position obstacles outside the parking area, or the boundary lines can be moved to position obstacles outside the parking area. Of course, the target parking space may also have an irregular outline; by adjusting the boundary lines of the target parking space, an empty parking area with a preset shape can be obtained.
[0078] The vehicle's attitude information can show its posture in a reference coordinate system, and this attitude information may include heading angle, yaw angle, steering angle, etc. The preset path planning algorithm can be any path planning algorithm in related technologies. Optionally, the preset path planning algorithm is a collision-free Reeds-Shepp curve algorithm, meaning that during the driving path formed by the preset path planning algorithm, whether the vehicle collides with the parking line or the parking space line is not considered. The Reeds-Shepp curve algorithm can plan a path between two points, ensuring that at least one path connects the two points by forming a line family of various path segments. Those skilled in the art will understand that in the driving path generated by the Reeds-Shepp curve algorithm, the starting point is the vehicle's initial position, and the ending point is the parking position where the vehicle enters the target parking space.
[0079] Vehicle configuration parameters include wheelbase, width, length, and height. The vehicle moves along a generated driving path, and the path varies depending on the vehicle's position. Therefore, during movement along the driving path, the vehicle may extend beyond the parking area, potentially colliding with obstacles outside the parking zone. To improve vehicle safety, it's necessary to restrict vehicle movement within the parking zone. Since overall collision detection between the parking zone and the vehicle is difficult to achieve, and can be equivalent to collision detection between the vehicle and individual parking lines, collision point detection is performed on the driving path to determine whether the vehicle will collide with the parking lines. If no collision point exists, the vehicle will not collide with the parking lines, and movement along the path is safe and reliable. If a collision point exists, the vehicle will collide with the parking lines, potentially causing it to extend beyond the parking zone. If a collision point exists, the driving path is updated using the location information of that collision point. The updated driving path is then used for collision point detection until no collision point exists, meaning the collision point is eliminated by updating the driving path. The vehicle is then guided to park in the parking area along this driving path, enabling collision-free parking of the vehicle in the target parking space.
[0080] In this application, an empty parking area is first selected from the target parking space so that a collision-free driving path can be calculated based on the empty parking area. This can, to a certain extent, avoid collisions during the process of parking the vehicle along the collision-free driving path. By detecting collision points on the driving path and updating the driving path based on the collision position information of the collision points, the driving path is continuously optimized to ensure that the vehicle does not collide during the process of parking the target parking space along the driving path, thereby reducing or avoiding parking failures caused by collisions. Compared with related vehicle parking methods based on graph search technology, the vehicle parking method provided in this application generates a driving path based on a preset path planning algorithm and collision point detection, which has a small computational load and high efficiency in generating the driving path.
[0081] Please see Figure 2 In one embodiment, the parking space information includes multiple parking space boundary lines; S120 includes:
[0082] S210, when the parking space information includes obstacle position information of obstacles located in the target parking space, for each obstacle position information, the first sideline is moved along the normal direction of the first sideline to pass through the obstacle position information, and multiple parking space sidelines include the first sideline;
[0083] S220: Based on the first edge line passing through the obstacle location information, a parking area is generated within the target parking space, with the obstacle location information located outside the parking area.
[0084] If the parking space information does not include obstacle location information, set the entire target parking space as an vacant parking area.
[0085] When the parking space information includes only one obstacle location information, a parking area can be obtained by moving only one first edge line along its own normal direction through the obstacle location information and dividing the target parking space according to the moved first edge line.
[0086] When parking space information includes multiple obstacle location information, for any obstacle location, select one of the multiple parking space edge lines as the first edge line corresponding to that obstacle. Move this first edge line along its normal direction through the corresponding obstacle location information. Based on the moved first edge line, a pending area is divided within the target parking space. If obstacle location information is located within this pending area, repeat the above steps. For any obstacle location information within this pending area, select one of the multiple parking space edge lines within the pending area as the first edge line corresponding to that obstacle. Move this first edge line along its normal direction through the corresponding obstacle location information. Based on the moved first edge line, a new pending area is divided within the pending area. Repeat the movement of the parking space edge lines until there is no obstacle location information within the divided pending area, then set this pending area as a parking area.
[0087] The first edge line corresponding to the obstacle location information can be selected according to preset rules. Optionally, the parking space edge line closest to the obstacle location information can be selected as the first edge line. The normal line of the first edge line is a line perpendicular to the first edge line in the plane where each parking space edge line is located, and the normal line direction is along the extension direction of the normal line.
[0088] For example, in Figure 3 In the target parking space shown, obstacle P1 is located within the target parking space. Selecting parking space edge line L1 as the first edge line, we move along its own normal direction X until we pass through the obstacle position information where obstacle P1 is located, thus obtaining the parking edge line L11 shown as a dashed line. An empty parking area is generated based on parking edge line L11 and parking space edges L2 and L3.
[0089] For example, in Figure 4 In the target parking space shown, obstacles P1 and P2 are located within the target parking space. According to preset rules, parking space edge line L3 is selected as the first edge line and moved along its own normal direction Y to pass through the obstacle position information of obstacle P1, resulting in the parking edge line L13 shown as a dashed line. Within the closed area obtained by parking edge line L13 and other edges, obstacle P2 still exists. According to preset rules, parking space edge line L1 is selected as the first edge line and moved along its own normal direction X to pass through the obstacle position information of obstacle P2, resulting in the parking edge line L12 shown as a dashed line. An empty parking area is generated based on parking edge lines L13, L12, and parking space edge line L2.
[0090] Please see Figure 5 In one embodiment, step S210 includes:
[0091] S510, calculate the estimated distance that each parking space edge line moves along its own normal direction to the location information of the obstacle;
[0092] S520, determine the minimum movement distance in the expected movement distance, and set the parking space edge line for which the minimum movement distance is calculated as the first edge line.
[0093] In this embodiment, for any one of the obstacle location information located within the target parking space, the parking space edge with the shortest movement distance is selected as the first edge, and the first edge is moved to pass through the obstacle location information, so as to reduce the movement distance of the first edge and increase the area of the obtained parking area.
[0094] Please see Figure 6 In one embodiment, S140 includes:
[0095] S610 calculates the motion trajectory of multiple preset contour points of the vehicle based on configuration parameters and driving path. The motion trajectory is the trajectory of the preset contour points when the vehicle moves along the driving path.
[0096] S620, calculate the intersection points of each motion trajectory with each parking edge line in pairs;
[0097] S630, when the intersection point is zero, the collision point is determined to be zero;
[0098] S640: If the intersection point is not zero, calculate the distance the vehicle travels to the intersection point and determine the intersection point corresponding to the minimum travel distance as the collision point.
[0099] Those skilled in the art can select multiple points as preset contour points in the vehicle outline as needed. The preset contour points can be protruding vertices in the vehicle outline. Optionally, the number of preset contour points is 4, including two contour points set along the vehicle's horizontal axis at the front of the vehicle and two contour points set along the vehicle's horizontal axis at the rear of the vehicle.
[0100] In the preset reference frame, the position coordinates of each preset contour point are related to the point's position within the vehicle contour, the vehicle's length, and the vehicle's width. Parameters related to the position coordinates of the preset contour points can be queried or calculated through configuration parameters, and the motion trajectory of the preset contour points can be calculated based on these parameters.
[0101] Please refer to the following: Figure 7 Since the preset contour points are located at different positions within the vehicle contour, their movement trajectories differ as the vehicle moves along the driving path. The driving path includes straight segments and circular arc segments. For the vehicle moving along a circular arc segment, the movement trajectory of each preset contour point is a circular trajectory with different radii around the same center. For the vehicle moving along a straight segment, it can be equivalent to the vehicle moving along a circular arc with an infinitely large radius. Therefore, calculating the intersection points between each movement trajectory and each parking edge line can be simplified to solving for the intersection points of each circular arc in the movement trajectory with the parking edge line. In one embodiment, each parking edge line passes through... The intersection point can be calculated using the following formula:
[0102] ;
[0103] ;
[0104] .
[0105] Where a, b, and c are line segment parameters about the parking edge line, Ox and Oy are the coordinates of the center of the arc segment in the preset reference system, and R is the radius of the arc segment.
[0106] When Δ is less than 0, the circular line segment containing the arc segment and the straight line segment containing the parking edge line have no intersection. When Δ is greater than 0, the circular line segment containing the arc segment and the straight line segment containing the parking edge line have an intersection. Determine whether the intersection point is on the arc segment and the parking edge line. If the intersection point is on the arc segment and the parking edge line, then the intersection point is the intersection point of the arc segment and the parking edge line.
[0107] Since the preset detection points arrive at each intersection point in a specific order as the vehicle travels along the path, the intersection point corresponding to the minimum travel distance is the first intersection point reached by the vehicle along the path, and this first intersection point can be identified as the collision point. The travel distance can be calculated using the following formula:
[0108]
[0109] Where dL is the travel distance. Let x be the starting point of the vehicle in any arc segment. The heading angle of the vehicle at the starting point of any arc segment, R is the radius of the arc segment, and x is the x-coordinate of the collision point.
[0110] By calculating the motion trajectory of each contour point, collision detection can be performed on the driving trajectory by identifying the intersection points between each motion trajectory and each parking edge line.
[0111] Please see Figure 8 In one embodiment, updating the driving path based on the collision location information of the collision point includes:
[0112] S710, based on the collision location information, selects the path before the collision point in the driving path as the collision-free path;
[0113] S720, based on the preset mapping relationship, determine the replanning path group corresponding to the collision location information. The preset mapping relationship includes the mapping relationship between the collision location information and the replanning path group.
[0114] S730 calculates the replanning path based on the replanning path group, configuration parameters, and the vehicle's simulated attitude information. The simulated attitude information is the attitude information of the vehicle traveling along the collision-free path to the collision point. The end point of the collision-free path is the starting point of the replanning path.
[0115] S740, update the driving path to a connected collision-free path and a replanned path.
[0116] Collision location information includes the location of the collision point on the parking line and the location of the collision point on the vehicle outline. Different collision location information corresponds to different replanning path groups, which include multiple pre-defined path segments. For example, if the collision point is the front of the vehicle colliding with the parking line, then the replanning path group will at least include a path segment controlling the vehicle to reverse; if the collision point is the rear of the vehicle colliding with the parking line, then the replanning path group will at least include a path segment controlling the vehicle to move forward.
[0117] The updated driving path consists of a connected collision-free path and a replanned path. In other words, the updated driving path includes a collision-free path and a replanned path, with the end point of the collision-free path being the start point of the replanned path.
[0118] In this embodiment, by pre-setting replanning path groups corresponding to different collision location information, the path replanning after the collision point can be performed based on the replanning path groups, thus reducing the computational load of path replanning.
[0119] In one embodiment, the plurality of parking lines includes a first parking line and a second parking line disposed opposite to each other, and a third parking line connecting the first parking line and the second parking line. See also... Figure 9 When a vehicle is parked in the target parking space, the parking line closest to the front of the vehicle is the front parking line L1, the parking line closest to the rear of the vehicle is the rear parking line L2, and the parking line closest to the vehicle door is the side parking line L3. Of the first and second parking lines, one is the front parking line and the other is the rear parking line. For ease of explanation, the following explanation will use the first parking line as the front parking line and the second parking line as the rear parking line.
[0120] In one embodiment, S720 includes:
[0121] According to the preset mapping relationship, a first planning path group corresponding to the first collision position information is determined. The first planning path group includes a first arc segment and a second arc segment with the same path length.
[0122] The first collision location information is that the collision point is located at the second parking line and the rear of the vehicle is closer to the second parking line than the front of the vehicle.
[0123] When the collision point O is the intersection of the vehicle's rear end and the rear parking line, the corresponding replanning path group consists of two circular arc segments of equal length. The radius of curvature and radian of these arc segments can be calculated based on the vehicle's minimum turning radius and simulated attitude information.
[0124] S = ( 1- 2) *R;
[0125] Where S is the path length. The heading angle of the simulated attitude information of 2. The final heading angle of vehicle 1 when it enters the target parking space, where R is the minimum turning radius of the vehicle.
[0126] Please see Figure 10 In one embodiment, S720 includes:
[0127] Based on the preset mapping relationship, a second planning path group corresponding to the second collision position information is determined. The second planning path group includes a third arc segment.
[0128] The second collision location information is that the collision point is located at the first parking line and the front of the vehicle is closer to the first parking line than the rear of the vehicle.
[0129] When the collision point is the intersection of the vehicle's front end and the front parking line, the corresponding replanning path group includes a third circular arc segment. The radius of curvature and radian of this arc segment can be calculated based on the vehicle's minimum turning radius and simulated attitude information, allowing the vehicle to travel along the third circular arc segment to the termination heading angle.
[0130] Please see Figure 11 In one embodiment, S720 includes:
[0131] Based on the preset mapping relationship, the third planning path group corresponding to the third collision position information is determined. The third planning path group includes the fourth arc segment and the fifth arc segment. The fourth arc segment has a preset path length.
[0132] The third collision location information indicates that the collision point is located at the third parking edge line.
[0133] When the collision point is the intersection of the vehicle body and the side parking line, the corresponding replanning path group includes a fourth arc segment and a fifth arc segment. The preset path length of the fourth arc segment can be determined based on the vehicle's rear overhang parameters. That is, the replanning path includes the fourth arc segment with the preset path length and the fifth arc segment calculated based on the vehicle's minimum turning radius and simulated attitude information, so that the vehicle travels along the fifth arc segment to the termination heading angle.
[0134] Please see Figure 12 Different replanning path groups are obtained for different collision locations between the vehicle and the parking line, and path replanning is performed based on the obtained replanning path groups. Different collision locations between the vehicle and the parking line can be divided into rear-side collision, front-side collision, and side collision.
[0135] Please see Figure 13 The vehicle parking method provided in this application may include:
[0136] S1. Real-time sensing of the vehicle's surrounding environment using sensors, analysis yields the parking space boundary, i.e., the parking space information of the target parking space. This parking space information is then processed to obtain the limit boundaries, i.e., the vacant parking areas.
[0137] S2, based on the preset path planning algorithm and attitude information, performs collision-free planning to generate the driving path for the vehicle to enter the parking area;
[0138] S3, performs collision point detection on the driving path;
[0139] S4, based on the collision location information of the collision point, replans the driving path according to the scenario;
[0140] S5, if a collision point is detected, execute S4;
[0141] S5, if no collision point is detected, controls the vehicle to park in the parking area along the driving path.
[0142] Based on the vehicle parking method provided in the above embodiments, this application also provides specific implementations of the vehicle parking device. Please refer to the following embodiments.
[0143] First see Figure 14 The vehicle parking device 900 provided in this application embodiment includes the following modules:
[0144] The acquisition module 901 is used to acquire parking space information of the target parking space, as well as vehicle attitude information and configuration parameters;
[0145] The adjustment module 902 is used to select an empty parking area within the target parking space based on the parking space information.
[0146] The path generation module 903 is used to generate the driving path for the vehicle to enter the parking area based on the preset path planning algorithm and attitude information.
[0147] The collision detection module 904 is used to detect collision points on the driving path based on configuration parameters, driving path, and parking edge lines of the parking area. The collision point is the intersection of the vehicle traveling along the driving path and the parking edge line.
[0148] The path generation module 903 is also used to update the driving path based on the collision position information of the collision point when a collision point is detected, and to perform: collision point detection on the driving path;
[0149] The control module 905 is used to control the vehicle to park in the parking area along the driving path if no collision point is detected.
[0150] As one implementation of this application, the parking space information includes multiple parking space boundary lines of the target parking space, and the aforementioned adjustment module 902 is also used for:
[0151] When the parking space information includes obstacle location information of obstacles located in the target parking space, for each obstacle location information, the first sideline is moved along the normal direction of the first sideline to pass through the obstacle location information, and multiple parking space sidelines include the first sideline.
[0152] A parking area is generated within the target parking space based on the first edge line that passes through the obstacle location information, with the obstacle location information located outside the parking area.
[0153] As one implementation of this application, the aforementioned adjustment module 902 is also used for:
[0154] Calculate the estimated distance each parking space edge line moves along its own normal direction to the location information of the obstacle;
[0155] Determine the minimum movement distance from the expected movement distance, and set the parking space edge line for which the minimum movement distance is calculated as the first edge line.
[0156] As one implementation of this application, the collision detection module 904 is also used for:
[0157] Based on the configuration parameters and driving path, the motion trajectory of multiple preset contour points of the vehicle is calculated. The motion trajectory is the trajectory of the preset contour points when the vehicle moves along the driving path.
[0158] Calculate the intersection points of each motion trajectory with each parking edge line pairwise;
[0159] If the intersection point is zero, then the collision point is determined to be zero.
[0160] If the intersection point is not zero, calculate the distance the vehicle travels to the intersection point, and determine the intersection point corresponding to the minimum travel distance as the collision point.
[0161] As one implementation of this application, the path generation module 903 is further used for:
[0162] Based on the collision location information, the path located before the collision point in the driving path is selected as the collision-free path;
[0163] Based on the preset mapping relationship, determine the replanning path group corresponding to the collision location information. The preset mapping relationship includes the mapping relationship between the collision location information and the replanning path group.
[0164] Based on the replanning path group, configuration parameters, and vehicle simulated attitude information, the replanning path is calculated. The simulated attitude information is the attitude information of the vehicle traveling along the collision-free path to the collision point. The end point of the collision-free path is the start point of the replanning path.
[0165] The driving path is updated to a connected collision-free path and a replanned path.
[0166] As one implementation of this application, the multiple parking edge lines include a first parking edge line and a second parking edge line arranged opposite to each other, and a third parking edge line connecting the first parking edge line and the second parking edge line; the path generation module 903 is further used for:
[0167] According to the preset mapping relationship, a first planning path group corresponding to the first collision position information is determined. The first planning path group includes a first arc segment and a second arc segment with the same path length.
[0168] The first collision location information is defined as the collision point being located at the first parking edge line and the front of the vehicle being closer to the first parking edge line than the rear of the vehicle.
[0169] As one implementation of this application, the multiple parking edge lines include a first parking edge line and a second parking edge line arranged opposite to each other, and a third parking edge line connecting the first parking edge line and the second parking edge line; the path generation module 903 is further used for:
[0170] Based on the preset mapping relationship, a second planning path group corresponding to the second collision position information is determined. The second planning path group includes a third arc segment.
[0171] The second collision location information refers to the collision point being located at the second parking line and the front of the vehicle being closer to the second parking line than the rear of the vehicle.
[0172] As one implementation of this application, the multiple parking edge lines include a first parking edge line and a second parking edge line arranged opposite to each other, and a third parking edge line connecting the first parking edge line and the second parking edge line; the path generation module 903 is further used for:
[0173] Based on the preset mapping relationship, the third planning path group corresponding to the third collision position information is determined. The third planning path group includes the fourth arc segment and the fifth arc segment. The fourth arc segment has a preset path length.
[0174] The third collision location information indicates that the collision point is located at the third parking edge line.
[0175] Figure 15 A schematic diagram of the hardware structure of the vehicle provided in an embodiment of this application is shown.
[0176] The vehicle may include a processor 1201 and a memory 1202 storing computer program instructions.
[0177] Specifically, the processor 1201 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.
[0178] Memory 1202 may include mass storage for data or instructions. For example, and not limitingly, memory 1202 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 1202 may include removable or non-removable (or fixed) media. Where appropriate, memory 1202 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 1202 is non-volatile solid-state memory.
[0179] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.
[0180] The processor 1201 implements any of the vehicle parking methods described in the above embodiments by reading and executing computer program instructions stored in the memory 1202.
[0181] In one example, the vehicle may also include a communication interface 1203 and a bus 1210. For example, Figure 13 As shown, the processor 1201, memory 1202, and communication interface 1203 are connected through bus 1210 and complete communication with each other.
[0182] The communication interface 1203 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.
[0183] Bus 1210 includes hardware, software, or both, that couples vehicle components together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 1210 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.
[0184] The vehicle can be based on the above embodiments to realize the combination of the above-described vehicle parking method, device and vehicle.
[0185] Furthermore, in conjunction with the vehicle parking methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions, which, when executed by a processor, implement any of the vehicle parking methods in the above embodiments and achieve the same technical effect. To avoid repetition, further details are omitted here. The aforementioned computer-readable storage medium may include non-transitory computer-readable storage media, such as read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, etc., and is not limited thereto.
[0186] In addition, this application also provides a computer program product, including computer program instructions, which, when executed by a processor, can implement the steps and corresponding content of the aforementioned method embodiments.
[0187] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.
[0188] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.
[0189] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.
[0190] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.
[0191] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.
Claims
1. A method for parking a vehicle, characterized in that, The method includes: Obtain the parking space information of the target parking space, as well as the vehicle's attitude information and configuration parameters. Based on the parking space information, an empty parking area is selected within the target parking space. Based on a preset path planning algorithm and the attitude information, a driving path is generated for the vehicle to park in the parking area. Based on the configuration parameters, the driving path, and the parking area's edge lines, collision point detection is performed on the driving path. The collision point is the intersection of the vehicle traveling along the driving path and the parking edge line. If the collision point is detected, the driving path is updated based on the collision location information of the collision point, and the following process is repeated: collision point detection is performed on the driving path. If the collision point is not detected, control the vehicle to park in the parking area along the driving path; The step of updating the driving path based on the collision location information of the collision point includes: Based on the collision location information, the path located before the collision point in the driving path is selected as the collision-free path. Based on a preset mapping relationship, a replanning path group corresponding to the collision location information is determined. The preset mapping relationship includes the mapping relationship between the collision location information and the replanning path group. Based on the replanning path group, the configuration parameters, and the vehicle's simulated attitude information, a replanning path is calculated. The simulated attitude information refers to the attitude information of the vehicle traveling along the collision-free path to the collision point. The end point of the collision-free path is the start point of the replanning path. The driving path is updated to be the connected collision-free path and the replanning path.
2. The vehicle parking method according to claim 1, characterized in that, The parking space information includes multiple parking space boundary lines of the target parking space. The step of selecting an vacant parking area within the target parking space based on the parking space information includes: If the parking space information includes obstacle location information of obstacles located within the target parking space, for each obstacle location information, the first sideline is moved along the normal direction of the first sideline to pass through the obstacle location information, and the plurality of parking space sidelines include the first sideline. The parking area is generated within the target parking space by dividing the area based on the first edge line that passes through the obstacle location information, wherein the obstacle location information is located outside the parking area.
3. The vehicle parking method according to claim 2, characterized in that, The process of moving the first sideline along the normal direction of the first sideline before it passes the obstacle position information includes: Calculate the estimated movement distance of each parking space edge along its own normal direction until it passes the obstacle position information. Determine the minimum movement distance among the expected movement distances, and set the parking space edge line for which the minimum movement distance is calculated as the first edge line.
4. The vehicle parking method according to claim 1, characterized in that, The step of obtaining the vehicle's configuration parameters and, based on the configuration parameters, the driving path, and the parking area's parking edge lines, performing collision point detection on the driving path includes: Based on the configuration parameters and the driving path, the motion trajectory of multiple preset contour points of the vehicle is calculated. The motion trajectory is the trajectory of the preset contour points when the vehicle moves along the driving path. Calculate the pairwise intersections between each of the stated motion trajectories and each of the stated parking edge lines. If the intersection point is zero, then the collision point is determined to be zero. If the intersection point is not zero, calculate the driving distance of the vehicle to the intersection point, and determine the intersection point corresponding to the minimum driving distance as the collision point.
5. The vehicle parking method according to claim 1, characterized in that, The multiple parking edges include a first parking edge and a second parking edge that are arranged opposite to each other, and a third parking edge that connects the first parking edge and the second parking edge. The step of determining the replanning path group corresponding to the collision location information according to a preset mapping relationship includes: Based on the preset mapping relationship, a first replanning path group corresponding to the first collision position information is determined. The first replanning path group includes a first arc segment and a second arc segment with the same path length. The first collision location information is that the collision point is located on the second parking edge line and the rear of the vehicle is closer to the second parking edge line than the front of the vehicle.
6. The vehicle parking method according to claim 1, characterized in that, The multiple parking edges include a first parking edge and a second parking edge that are arranged opposite to each other, and a third parking edge that connects the first parking edge and the second parking edge. The step of determining the replanning path group corresponding to the collision location information according to a preset mapping relationship includes: Based on the preset mapping relationship, a second re-planning path group corresponding to the second collision position information is determined. The second re-planning path group includes a third arc segment. The second collision location information is that the collision point is located on the first parking edge line and the front of the vehicle is closer to the first parking edge line than the rear of the vehicle.
7. The vehicle parking method according to claim 1, characterized in that, The multiple parking edges include a first parking edge and a second parking edge that are arranged opposite to each other, and a third parking edge that connects the first parking edge and the second parking edge. The step of determining the replanning path group corresponding to the collision location information according to a preset mapping relationship includes: Based on the preset mapping relationship, a third planning path group corresponding to the third collision position information is determined. The third planning path group includes a fourth arc segment and a fifth arc segment, and the fourth arc segment has a preset path length. The third collision location information refers to the collision point being located on the third parking edge line.
8. A vehicle parking device, characterized in that, The device includes: The acquisition module is used to acquire parking space information of the target parking space, as well as the vehicle's attitude information and configuration parameters. The adjustment module is used to select an vacant parking area within the target parking space based on the parking space information. The path generation module is used to generate the driving path for the vehicle to park in the parking area based on a preset path planning algorithm and the attitude information. The collision detection module is used to detect collision points on the driving path based on the configuration parameters, the driving path, and the parking edge lines of the parking area. The collision point is the intersection of the vehicle traveling along the driving path and the parking edge line. The path generation module is also used to update the driving path based on the collision position information of the collision point when the collision point is detected, and then perform the collision point detection on the driving path again. The control module is used to control the vehicle to park in the parking area along the driving path if the collision point is not detected. The path generation module is further used for: Based on the collision location information, the path located before the collision point in the driving path is selected as the collision-free path. Based on a preset mapping relationship, a replanning path group corresponding to the collision location information is determined. The preset mapping relationship includes the mapping relationship between the collision location information and the replanning path group. Based on the replanning path group, the configuration parameters, and the vehicle's simulated attitude information, a replanning path is calculated. The simulated attitude information refers to the attitude information of the vehicle traveling along the collision-free path to the collision point. The end point of the collision-free path is the start point of the replanning path. The driving path is updated to be the connected collision-free path and the replanning path.
9. A vehicle, characterized in that, The vehicle includes: a processor and a memory storing computer program instructions. When the processor executes the computer program instructions, it implements the vehicle parking method as described in any one of claims 1-7.