Parking trajectory planning method, storage medium, controller, and vehicle

Abstract

A parking trajectory planning method, comprising: determining an initial parking point, a target parking point, and a rotation starting point of a vehicle with respect to a target parking space, wherein the vehicle has the capability to rotate about a single wheel, and the rotation starting point is the point at which the vehicle starts to rotate about a target wheel in a parking exit trajectory from the target parking point to the initial parking point; and on the basis of the initial parking point, the target parking point, and the rotation starting point, determining a target parking trajectory of the vehicle from the initial parking point to the target parking point. A computer-readable storage medium, a controller, and a vehicle are further provided. By using the parking trajectory planning method, the vehicle can complete parking in a narrow parking space in a single maneuver, thereby reducing the number of gear changes, shortening vehicle parking time, and improving parking efficiency.

Description

Parking trajectory planning method, storage medium, controller and vehicle

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure claims priority to Chinese patent application number 202410056482.6, filed with the China Patent Office on January 12, 2024, entitled “Parking trajectory planning method, storage medium, controller and vehicle,” the entire contents of which are incorporated by reference into this disclosure. Technical Field

[0003] The present disclosure relates to the field of autonomous driving technology, and in particular to a parking trajectory planning method, storage medium, controller, and vehicle. Background Art

[0004] With the development of vehicle technology, vehicles can achieve automatic parking by planning parking trajectories. That is, the vehicle can move to a designated parking space along the planned trajectory. However, in the case of parking in a narrow parking space, the vehicle often needs to maneuver several times to park in the parking space. Summary of the Invention

[0005] To overcome the technical problems existing in the related art, the present disclosure provides a parking trajectory planning method, a storage medium, a controller and a vehicle.

[0006] To achieve the above objectives, in a first aspect, the present disclosure provides a parking trajectory planning method, the method comprising:

[0007] Determining an initial parking point, a target parking point, and a rotation starting point of the vehicle relative to the target parking space, wherein if the vehicle has a single-wheel rotation function, the rotation starting point is the starting point of the vehicle's rotation around the target wheel in the parking trajectory from the target parking point to the initial parking point;

[0008] A target parking trajectory of the vehicle from the initial parking point to the target parking point is determined according to the initial parking point, the target parking point, and the rotation starting point.

[0009] In a second aspect, the present disclosure provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implements the parking trajectory planning method described in the first aspect.

[0010] In a third aspect, the present disclosure provides a controller, comprising:

[0011] a storage device storing a computer program;

[0012] A control device is used to execute the computer program to implement the parking trajectory planning method described in the first aspect.

[0013] In a fourth aspect, the present disclosure provides a vehicle, comprising the controller described in the third aspect.

[0014] Optionally, the vehicle includes four motors, each motor driving a corresponding wheel.

[0015] The above technical solution can achieve the following beneficial effects:

[0016] The target parking trajectory from the initial parking point to the target parking point is determined based on the vehicle's initial parking point, target parking point, and rotation starting point. The vehicle has a single-wheel rotation function, and the rotation starting point is the starting point of the rotation around the target wheel in the vehicle's exit trajectory from the target parking point to the initial parking point. This single-wheel rotation function allows the vehicle to plan a target parking trajectory, allowing the vehicle to park in a narrow parking space in one go, reducing the number of maneuvers and ultimately shortening parking time and improving parking efficiency.

[0017] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following detailed description, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0019] FIG1 is a schematic diagram showing a parking process according to an exemplary embodiment of the present disclosure.

[0020] FIG. 2 is another schematic diagram showing a parking process according to an exemplary embodiment of the present disclosure.

[0021] FIG3 is a flowchart showing a parking trajectory planning method according to an exemplary embodiment of the present disclosure.

[0022] FIG4 is a schematic diagram showing a parking trajectory planning according to an exemplary embodiment of the present disclosure.

[0023] FIG5 is another schematic diagram showing a parking trajectory planning according to an exemplary embodiment of the present disclosure.

[0024] 6a and 6b are schematic diagrams showing a method of determining a target rotation end point according to an exemplary embodiment of the present disclosure.

[0025] FIG. 7 is a schematic diagram showing a method of determining a minimum rotation angle according to an exemplary embodiment of the present disclosure.

[0026] FIG. 8 is a schematic diagram showing a method of determining a maximum rotation angle according to an exemplary embodiment of the present disclosure.

[0027] 9a to 9d are schematic diagrams showing different parking trajectories according to exemplary embodiments of the present disclosure.

[0028] FIG. 10 is a block diagram of a controller according to an exemplary embodiment of the present disclosure.

[0029] FIG. 11 is a block diagram of a vehicle according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] The following describes the specific embodiments of the present disclosure in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure and are not intended to limit the present disclosure.

[0031] As mentioned in the background technology, the existing trajectory planning method is performed for vehicles that do not have a single-wheel rotation function (hereinafter referred to as conventional vehicles). The rotation center point of conventional vehicles during the rotation process is a point outside the vehicle, resulting in a large rotation angle of the vehicle during the rotation process. As a result, in parking scenarios in narrow parking spaces, such as narrow side parking scenarios, the vehicle usually needs to maneuver multiple times before it can be parked in the parking space, resulting in low parking efficiency.

[0032] It should be understood that four-wheel independent drive technology means that the vehicle is equipped with four motors, each of which drives a wheel independently, so that the steering and speed of the four wheels of the vehicle can be different. When the vehicle is equipped with four-wheel independent drive technology, it can lock a certain wheel and keep it different when the vehicle is stopped, and control the vehicle to rotate 360° clockwise or counterclockwise around the axis of the locked wheel as the center of the circle. In other words, the vehicle has the function of rotating around a single wheel, so that the rotation angle of the vehicle during the rotation process can be controlled within a smaller range. For example, in a parking scenario in a narrow parking space, the single-wheel rotation method can effectively reduce the parking space, so that the vehicle can be parked in a narrow parking space in one go.

[0033] Referring to Figure 1, taking the parking space located in front of the right side of the vehicle as an example, the driving trajectory of the vehicle when parking head-on into the parking space is: first turn right forward to enter the parking space, then rotate counterclockwise around the left front wheel of the vehicle until the vehicle body is level with the parking space, and finally move forward or backward to adjust the vehicle to the middle of the parking space.

[0034] Referring to Figure 2, taking the parking space located behind the right side of the vehicle as an example, the driving trajectory of the vehicle in the rear-end parking space method is: first back up and turn right to back into the parking space, then rotate clockwise around the left rear wheel of the vehicle until the vehicle body is level with the parking space, and finally move forward or backward to adjust the vehicle to the middle of the parking space.

[0035] In summary, the process of parallel parking using single-wheel rotation can be summarized into three stages: entering the parking space, single-wheel rotation, and adjusting the vehicle's position. Accordingly, this disclosure provides a parking trajectory planning method based on the vehicle's single-wheel rotation function to improve the success rate and efficiency of automated parking.

[0036] FIG3 is a flow chart of a parking trajectory planning method according to an exemplary embodiment of the present disclosure. As shown in FIG3 , the parking trajectory planning method may include the following steps:

[0037] In step S11, the initial parking point, target parking point, and rotation starting point of the vehicle relative to the target parking space are determined. The vehicle has a single-wheel rotation function, and the rotation starting point is the starting point of the vehicle's rotation around the target wheel in the parking trajectory from the target parking point to the initial parking point.

[0038] It is worth noting that the initial parking point (init point) represents the position of the vehicle's rear axle center point at the beginning of parking, and the target parking point (target point) represents the position of the vehicle's rear axle center point after the vehicle is safely parked in the target parking space.

[0039] Among them, a two-dimensional coordinate system can be established with the short side of the target parking space as the Y-axis and the long side of the target parking space as the X-axis. The two-dimensional coordinate system can cover the position of the rear axle center point of the vehicle during the entire parking process, so that the initial parking point, the target parking point and the rotation starting point can be determined according to the coordinate points of the rear axle center point of the vehicle in the two-dimensional coordinate system when the vehicle is in different positions during the parking process.

[0040] It should be understood that the target parking space can be a vertical parking space or a side parking space, and this disclosure does not limit this.

[0041] In step S12 , a target parking trajectory of the vehicle from the initial parking point to the target parking point is determined according to the initial parking point, the target parking point, and the rotation starting point.

[0042] It should be understood that when the initial parking point is outside the target parking space and the target parking point and the rotation starting point are inside the target parking space, the target parking trajectory can be a parking-in trajectory; when the initial parking point and the rotation starting point are inside the target parking space and the target parking point is inside the target parking space, the target parking trajectory can be a parking-out trajectory.

[0043] In the disclosed embodiment, a target parking trajectory is determined for the vehicle from the initial parking point to the target parking point based on the vehicle's initial parking point, target parking point, and rotation starting point. The vehicle has a single-wheel rotation function, and the rotation starting point is the starting point of the rotation around the target wheel in the vehicle's exit trajectory from the target parking point to the initial parking point. This allows the vehicle to plan a target parking trajectory using the vehicle's single-wheel rotation function. This allows the vehicle to park in a narrow parking space in one go, reducing the number of maneuvers required, thereby shortening parking time and improving parking efficiency.

[0044] In order to facilitate those skilled in the art to better understand the parking trajectory planning method provided by the present disclosure, the steps of the method are described in detail below with examples.

[0045] In an optional embodiment, in step S12, determining a target parking trajectory of the vehicle from the initial parking point to the target parking point based on the initial parking point, the target parking point, and the rotation starting point may include:

[0046] Determining a first trajectory based on the target parking point and the rotation starting point, and determining a second trajectory based on the rotation starting point and the initial parking point;

[0047] A target parking trajectory of the vehicle from the initial parking point to the target parking point is obtained according to the first trajectory and the second trajectory.

[0048] It is worth noting that, when the target parking point coincides with the rotation starting point, the target parking trajectory of the vehicle from the initial parking point to the target parking point can be directly obtained based on the initial parking point and the target parking point.

[0049] For example, according to the target parking point target point and the initial parking point init point of the vehicle corresponding to the target parking space, a target parking trajectory of the vehicle from the initial parking point init point to the target parking point target point can be obtained.

[0050] It should be understood that the first trajectory and the second trajectory may be planned simultaneously, or the first trajectory may be planned first and then the second trajectory, or the second trajectory may be planned first and then the first trajectory, which is not limited in the present disclosure.

[0051] It is worth noting that the first trajectory can be the vehicle's adjusted trajectory within the target parking space. In practical applications, to avoid collisions with the vehicle's outline, the adjusted trajectory within the target parking space is a horizontal straight line. Therefore, in the disclosed embodiments, the first trajectory can be a straight line. The second trajectory can be the vehicle's movement trajectory between the target parking space and the starting point for parking, and can be a curved trajectory.

[0052] As shown in Figure 4, the first trajectory is determined based on the vehicle's target parking point (target point) and the rotation starting point. The second trajectory is determined based on the rotation starting point and the initial parking point (init point). Thus, the vehicle's target parking trajectory from the initial parking point (init point) to the target parking point (target point) is obtained based on the first and second trajectories. Therefore, using segmented planning for parking trajectory planning can reduce the difficulty of trajectory planning and further improve trajectory planning efficiency.

[0053] In an optional embodiment, determining the first trajectory according to the target parking point and the rotation starting point, and determining the second trajectory according to the rotation starting point and the initial parking point may include:

[0054] determining a first trajectory from the target parking point to the rotation starting point, and determining a second trajectory from the rotation starting point to the initial parking point;

[0055] Obtaining a target parking trajectory of the vehicle from the initial parking point to the target parking point based on the first trajectory and the second trajectory may include:

[0056] The first trajectory and the second trajectory are spliced ​​to obtain an initial parking trajectory from the target parking point to the initial parking point, and the initial parking trajectory is reversed to obtain a target parking trajectory of the vehicle from the initial parking point to the target parking point.

[0057] It should be understood that when the target parking trajectory is a parking-out trajectory, no inversion processing is required. When the target parking trajectory is a parking-in trajectory, the parking-out trajectory needs to be inverted to obtain the corresponding parking-in trajectory.

[0058] It should be understood that the vehicles in both the first and second trajectories have no risk of collision with the safe parking space boundary, where the safe parking space boundary can be a space boundary where the vehicle may collide during parking, such as the space boundary of the target parking space and the space boundary outside the target garage as shown in FIG. 5 .

[0059] It is worth noting that when planning a vehicle's parking trajectory from the initial parking point to the target parking point in the disclosed embodiment, the rotation starting point must first be determined. However, this is difficult to determine when directly planning the parking trajectory. Therefore, the disclosed embodiment can first plan the vehicle's exit trajectory from the target parking point to the initial parking point, and then invert the exit trajectory to obtain the vehicle's parking trajectory from the initial parking point to the target parking point. Furthermore, determining the rotation starting point when directly planning the parking trajectory requires complex calculations based on a large amount of data. Therefore, the disclosed embodiment can quickly determine the rotation starting point based on relevant data when the vehicle is in the target parking space. The entire process involves only a small amount of data and is simple to calculate, further reducing the computational complexity of trajectory planning.

[0060] For example, as shown in Figure 4, when the target parking space is located behind the right side of the vehicle, the position of the center point of the vehicle's rear axle outside the parking space when the vehicle starts parking is set as init_point (initial parking point), and the position of the center point of the vehicle's rear axle inside the parking space when parking is completed is set as target_point (target parking point). First, a parking exit trajectory from target_point to init_point is planned, and then the parking exit trajectory is reversed to a parking entry trajectory from init_point to target_point.

[0061] Through the above method, the embodiment of the present disclosure can combine the single-wheel rotation function of the vehicle to first plan the parking trajectory from the target parking point to the initial parking point, and then invert the parking trajectory to obtain the parking trajectory from the initial parking point to the target parking point. This provides a new parking trajectory planning method, which can realize the parking of the vehicle in a narrow parking space in one go, reduce the number of maneuvers, and thus reduce the parking time of the vehicle and improve parking efficiency.

[0062] In an optional embodiment, determining the second trajectory from the rotation starting point to the initial parking point may include:

[0063] Determining a minimum rotation angle and a maximum rotation angle of the vehicle around the axis of the target wheel in the parking trajectory, and determining a target rotation end point based on a first rotation end point after the vehicle rotates around the minimum rotation angle and a second rotation end point after the vehicle rotates around the maximum rotation angle;

[0064] Determine a single wheel rotation trajectory from a rotation start point to a target rotation end point, and an off-parking trajectory from the target rotation end point to an initial parking point;

[0065] The single-wheel rotation trajectory and the parking trajectory outside the garage are spliced ​​into a second trajectory from the rotation starting point to the initial parking point.

[0066] For ease of expression, let the single-wheel rotation process be VOT, let the rotation starting point in the parking trajectory from the target parking point target_point to the initial parking point init_point be vot_start, and the target rotation ending point be vot_end; the trajectory from target_point to vot_start is the in-parking adjustment trajectory, and let the planning of the in-parking adjustment trajectory be Plannrt1; the trajectory from vot_start to vot_end is the single-wheel rotation trajectory, and let the planning of the single-wheel rotation trajectory be VOT-Planner; the trajectory from vot_end to init_point is the out-parking entry trajectory, and let the planning of the out-parking entry trajectory be Planner2.

[0067] It should be understood that the planning of the second trajectory consists of VOT-Planner+Planner2. Correspondingly, when the target parking point and the rotation starting point coincide, the planning of the target parking trajectory consists of VOT-Planner+Planner2. Correspondingly, when the target parking point and the rotation starting point do not coincide, the planning of the target parking trajectory consists of Planner1+VOT-Planner+Planner2.

[0068] It's worth noting that the vehicle rotates around the target wheel's axis within the exit trajectory, with no collision risk from the rotation start point to the target rotation end point. Therefore, the target rotation end point can be determined based on the minimum and maximum rotation angles. A single-wheel rotation trajectory is then planned for the vehicle around the target wheel's axis from the rotation start point to the target rotation end point. A parking trajectory outside the parking garage is then planned from the target rotation end point to the initial parking point. The single-wheel rotation trajectory and the parking trajectory outside the parking garage are then combined to form a second trajectory.

[0069] For example, as shown in Figure 5, the target rotation end point vot_end can be determined based on the minimum rotation angle and the maximum rotation angle, and then a single-wheel rotation trajectory from vot_start to vot_end and an out-of-parking trajectory from vot_end to init_point are planned. The single-wheel rotation trajectory and the out-of-parking trajectory are spliced ​​to obtain a trajectory from vot_start to init_point.

[0070] In this disclosed embodiment, the vehicle's single-wheel rotation function can be leveraged to first determine the rotation end point based on the minimum and maximum rotation angles of the vehicle during a single-wheel rotation within the parking trajectory. Segmented trajectory planning is then performed based on the rotation start and end points, along with the initial parking point, to generate a second trajectory. This reduces the difficulty of second trajectory planning and further improves the efficiency of target parking trajectory planning.

[0071] In an optional embodiment, determining the target rotation end point according to the first rotation end point after the vehicle rotates around the minimum rotation angle and the second rotation end point after the vehicle rotates around the maximum rotation angle may include:

[0072] Sampling is performed between a first rotation end point after the vehicle rotates around a minimum rotation angle and a second rotation end point after the vehicle rotates around a maximum rotation angle to obtain a plurality of sampling points;

[0073] For each sampling point, a first candidate trajectory from the sampling point to the rotation starting point is determined using different trajectory planning algorithms. A target candidate trajectory is determined based on the trajectory cost of each first candidate trajectory, and the sampling point corresponding to the target candidate trajectory is used as the target rotation end point.

[0074] Accordingly, the parking trajectory outside the garage is the target candidate trajectory.

[0075] It should be understood that, as shown in Figures 6a and 6b, the first end point of the vehicle's rotation around the minimum rotation angle can be used as the sampling starting point, and the second end point of the vehicle's rotation around the maximum rotation angle can be used as the sampling ending point. Sampling can then be performed from the sampling starting point to the sampling ending point according to the sampling step length, thereby obtaining multiple sampling points. The sampling step length can be preset based on the accuracy requirements of the trajectory planning or based on the distance of the vehicle's profile relative to the safe parking space limit during a single wheel rotation. In this disclosure, the sampling step length is 5°.

[0076] It is worth noting that trajectory planning algorithms can include existing trajectory planning algorithms such as the geometric trajectory planning algorithm and the RS curve trajectory algorithm. The geometric trajectory algorithm can be used to plan trajectories for parallel parking or diagonal parking. The RS curve algorithm can be used to plan curved trajectories during parking trajectory planning.

[0077] In the disclosed embodiment, a target candidate trajectory can be determined based on the trajectory costs of multiple first candidate trajectories from each sampling point to the rotation starting point, thereby obtaining a target rotation end point. Specifically, the target rotation end point is determined based on the target candidate trajectory with the lowest trajectory cost. This ensures that the target parking trajectory obtained by trajectory planning based on the target rotation end point has the lowest cost while the vehicle is traveling, further reducing the cost of automated parking and improving its efficiency.

[0078] In an optional embodiment, the trajectory cost of the first candidate trajectory is determined by at least one of the trajectory length of the first candidate trajectory, the single wheel rotation angle of the vehicle in the first candidate trajectory, the collision risk value of the vehicle in the first candidate trajectory, and the number of gear shifts of the vehicle in the first candidate trajectory.

[0079] It should be understood that the more types of parameters involved in determining the trajectory cost, the higher the accuracy of the obtained trajectory cost, and the more reliable the target candidate trajectory determined based on the trajectory cost.

[0080] For example, when the trajectory cost is determined based on the trajectory length, single wheel rotation angle, collision risk value, and number of gear shifts, the cost values ​​corresponding to the trajectory length, single wheel rotation angle, collision risk value, and number of gear shifts can be substituted into the calculation formula: Costtraj=p1·cost 轨迹长度 +p2·cost 单轮旋转角度 +p3·cost 碰撞风险值 +p4·cost 换挡次数 ,

[0081] Among them, Costtraj represents the trajectory cost, p1 represents the preset weight of the trajectory length, cost 轨迹长度represents the cost value corresponding to the trajectory length, p2 represents the preset weight corresponding to the single wheel rotation angle, cost 单轮旋转角度 Represents the cost value corresponding to the single wheel rotation angle, p3 represents the preset weight corresponding to the collision risk value, cost 碰撞风险值 Represents the cost value corresponding to the collision risk value, p4 represents the preset weight corresponding to the number of gear shifts, cost 换挡次数 Indicates the cost value corresponding to the number of gear shifts.

[0082] It is worth noting that p1, p2, p3, and p4 can be optimized and adjusted through simulation or actual vehicle testing.

[0083] The trajectory cost calculation process in the disclosed embodiment comprehensively considers the impact of trajectory length, single-wheel rotation angle, trajectory collision risk, and the number of trajectory shifts on parking efficiency and safety. While ensuring parking safety and efficiency, the trajectory cost of each trajectory is determined. The target candidate trajectory is then determined based on this trajectory cost, which can reduce the cost of automated parking and improve its efficiency.

[0084] In an optional embodiment, determining a target candidate trajectory according to the trajectory cost of each first candidate trajectory may include:

[0085] When all vehicles in the first candidate trajectories have no collision risk with surrounding obstacles, a target candidate trajectory is determined according to the trajectory cost of each first candidate trajectory;

[0086] The parking trajectory method may further include:

[0087] When there is a collision risk between the vehicle and surrounding obstacles in the first candidate trajectory, a second candidate trajectory from each sampling point to the initial parking point is determined in sequence by a trajectory search method until the vehicle has no collision risk with surrounding obstacles in the obtained second candidate trajectory;

[0088] The final second candidate trajectory is determined as the target candidate trajectory.

[0089] It is worth noting that the trajectory search method can include algorithms such as hybrid A* and RTT (Recurrently Target-attennding Tracking, recurrent network for target tracking). Compared with the trajectory planning algorithm, the trajectory search algorithm involves more parameters in its calculation process and the calculation process is more complicated. Among them, the hybrid A* algorithm and the RTT algorithm can both perform trajectory planning for each sampling point in turn. Each time a second candidate trajectory is obtained, it is determined whether there is a collision risk between the vehicle and the surrounding obstacles in the second candidate trajectory. If there is a collision risk between the vehicle and the surrounding obstacles in the second candidate trajectory, trajectory planning is performed for the next sampling point; if there is no collision risk between the vehicle and the surrounding obstacles in the second candidate trajectory, the second candidate trajectory of this planning is determined as the target candidate trajectory, and there is no need to perform trajectory planning for the next sampling point.

[0090] It should be understood that when there is no collision risk between the vehicle and surrounding obstacles in the first candidate trajectory obtained by the trajectory planning method, the trajectory planning is successful and there is no need to use the trajectory search algorithm for trajectory planning; when there is a collision risk between the vehicle and surrounding obstacles in the first candidate trajectory obtained by the trajectory planning method, the trajectory planning fails and the trajectory search algorithm can be used for trajectory planning to obtain the target candidate trajectory.

[0091] For example, as shown in FIG6a and FIG6b, the planning process of the target candidate trajectory may include:

[0092] I. Sampling between a first rotation end point after the vehicle rotates around a minimum rotation angle and a second rotation end point after the vehicle rotates around a maximum rotation angle to obtain n sampling points pi.

[0093] II. For each sampling point, the geometric trajectory planning algorithm is used to plan the trajectory from the sampling point pi to the initial parking point init_point, and the RS curve trajectory algorithm is used to plan the trajectory from the sampling point pi to the initial parking point init_point to obtain 2n first candidate trajectories.

[0094] III. Determine whether the vehicle in the 2n first candidate trajectories has a collision risk with surrounding obstacles. If so, execute V; otherwise, execute IV.

[0095] IV. According to the trajectory cost of each candidate trajectory, determine the target candidate trajectory with the lowest trajectory cost from the 2n first candidate trajectories, and use the sampling point corresponding to the target candidate trajectory as the target rotation end point.

[0096] V. Use the RTT algorithm to sequentially determine the second candidate trajectory from each sampling point pi to the initial parking point init_point until the vehicle has no collision risk with surrounding obstacles in the obtained second candidate trajectory. The final second candidate trajectory is determined as the target candidate trajectory, and the sampling point corresponding to the target candidate trajectory is used as the target rotation end point.

[0097] In an optional embodiment, the minimum rotation angle is greater than a first preset angle, and there is no risk of collision with obstacles around the target parking space when the vehicle drives out of the target parking space in a straight line along the first rotation end point corresponding to the minimum rotation angle;

[0098] The maximum rotation angle is less than the second preset angle, and there is no risk of collision with obstacles outside the target parking space while the vehicle rotates along the maximum rotation angle.

[0099] It is worth noting that the first preset angle and the second preset angle can be empirical values ​​determined based on a large amount of actual parking data. In the embodiment of the present disclosure, the first preset angle can be 20°, and the second preset angle can be 60°. For example, the minimum rotation angle can be greater than 20°, and can ensure that there is no risk of collision with obstacles around the target parking space when the vehicle drives out of the target parking space in a straight line along the first rotation end point corresponding to the minimum rotation angle. The maximum rotation angle can be less than 60°, and can ensure that there is no risk of collision with obstacles outside the target parking space when the vehicle rotates around the axis of the target wheel to the maximum rotation angle.

[0100] In an optional embodiment, determining the minimum rotation angle of the vehicle around the axis of the target wheel in the parking trajectory may include:

[0101] Determine an initial first rotation angle, and loop through the following steps: determine an initial rotation end point after the vehicle rotates about the axis of the target wheel about the rotation start point by the first rotation angle, determine a straight line trajectory between the initial rotation end point and the target rear axle center point of the vehicle, and when there is a collision risk for the vehicle in the straight line trajectory, increase the first rotation angle according to a first preset step size to obtain a new first rotation angle until there is no collision risk for the vehicle in the obtained straight line trajectory, wherein the target rear axle center point is located at a portion of the vehicle outside the target parking space, and is a preset distance away from the initial rotation end point in a target direction, and the target direction is a direction parallel to the short side of the target parking space;

[0102] The first rotation angle finally obtained is determined as the minimum rotation angle of the vehicle rotating around the axis of the target wheel in the parking trajectory.

[0103] For example, in the embodiment of the present disclosure, the first preset step size may be 2%.

[0104] It should be understood that if the vehicle's parking trajectory is tail-in, the target rear axle center point point may be on a ray starting from the initial rotation end point vot_point1 along the vehicle's front direction, and the longitudinal axis distance between the target rear axle center point point and the initial rotation end point vot_point1 in the two-dimensional coordinate system described above may be 1.5 meters. If the target parking space is a parallel parking space, the longitudinal axis direction in the two-dimensional coordinate system is the width direction of the vehicle when it is in the parallel parking space. For example, the target rear axle center point point may be on a ray starting from the initial rotation end point vot_point1 along the vehicle's front direction, and the longitudinal axis distance between the target rear axle center point point and the initial rotation end point vot_point1 in the vehicle's width direction when the vehicle is in the parallel parking space is 1.5 meters.

[0105] It should be understood that the direction of rotation of the vehicle around the axis of the target wheel from the rotation starting point may be determined by the position of the vehicle and the target parking space. For example, when the target parking space is to the right front or left rear of the vehicle, the rotation direction may be counterclockwise; when the target parking space is to the right rear or left front of the vehicle, the rotation direction may be clockwise.

[0106] For example, the target parking space is at the right rear of the vehicle, see Figure 7, let the first preset step size be angel_step1, let the target rear axle center point be point, let the first rotation angle be angel_min, let the initial rotation end point be vot_point1, initialize angel_min = 20°, and the first preset step size angel_step1 = 2%.

[0107] a. Calculate vot_point1 after the vehicle rotates counterclockwise around the axis of the target wheel for angel_min from the starting point.

[0108] b. Determine whether there is a collision risk for the vehicle in the straight line between vot_point1 and point. If so, set angel_min += angel_step1 and return to step a. If not, use the current angel_min as the minimum rotation angle.

[0109] In an optional embodiment, determining the maximum rotation angle of the vehicle around the axis of the target wheel in the parking trajectory may include:

[0110] Determining an initial second rotation angle and looping through the following steps: determining whether a collision risk exists after the vehicle rotates about the axis of the target wheel by the second rotation angle from the rotation starting point; and when the vehicle does not exist a collision risk, increasing the second rotation angle by a second preset step size to obtain a new second rotation angle until the vehicle exists a collision risk;

[0111] The rotation angle obtained by subtracting the second preset step length from the final second rotation angle is determined as the maximum rotation angle of the vehicle rotating around the axis of the target wheel in the parking trajectory.

[0112] It is worth noting that the first preset step length and the second preset step length may be the same or different.

[0113] For example, the target parking space is at the right rear of the vehicle, see Figure 8, let the second preset step size be angel_step2, let the second rotation angle be angel_max, let the vehicle rotate around the axis of the target wheel by the second rotation angle from the rotation starting point to the rotation ending point vot_point2, initialize angel_min = 60°, and the second preset step size angel_step2 = 2%.

[0114] c. Calculate vot_point2 after the vehicle rotates counterclockwise around the axis of the target wheel by angel_max from the rotation starting point.

[0115] d. Determine whether the vehicle's outline exceeds the safe parking space limit when it is at vot_point2. That is, determine whether there is a collision risk after the vehicle rotates counterclockwise by angel_max around the axis of the target wheel from the starting point. If so, set angel_max += angel_step2 and return to step c. If not, set angel_max -= angel_step2 and use the current angel_max as the maximum rotation angle.

[0116] In an optional embodiment, as shown in FIG9a , when the target parking space is located in the right front of the vehicle, the target wheel is the left front wheel of the vehicle, and accordingly, the target parking trajectory is the front parking trajectory; or

[0117] As shown in FIG9b , when the target parking space is located behind the right side of the vehicle, the target wheel is the left rear wheel of the vehicle, and accordingly, the target parking trajectory is the rear parking trajectory; or

[0118] As shown in FIG9c , when the target parking space is located in front of the left side of the vehicle, the target wheel is the right front wheel of the vehicle, and accordingly, the target parking trajectory is the front parking trajectory; or

[0119] As shown in FIG9 d , when the target parking space is located behind the left side of the vehicle, the target wheel is the right rear wheel of the vehicle, and accordingly, the target parking trajectory is the rear parking trajectory.

[0120] For example, as shown in Figure 9a, when the target parking space is located in front of the right side of the vehicle, the corresponding front parking trajectory is as follows: the vehicle first turns right to enter the target parking space, then rotates around the axis of the vehicle's left front wheel until the vehicle body is parallel to the long side of the target parking space, and finally adjusts forward or backward to position the vehicle in the middle of the target parking space. As shown in Figure 9b, when the target parking space is located behind the right side of the vehicle, the corresponding rear parking trajectory is as follows: the vehicle first reverses and turns right to reverse into the space, then rotates around the axis of the vehicle's left rear wheel until the vehicle body is parallel to the long side of the target parking space, and finally adjusts forward or backward to position the vehicle in the middle of the target parking space. As shown in Figure 9c, when the target parking space is located in front of the left side of the vehicle, the corresponding front parking trajectory is as follows: the vehicle first turns left to enter the target parking space, then rotates around the axis of the vehicle's right front wheel until the vehicle body is parallel to the long side of the target parking space, and finally adjusts forward or backward to position the vehicle in the middle of the target parking space. As shown in Figure 9d, when the target parking space is located behind the left side of the vehicle, the corresponding rear parking trajectory is: the vehicle first backs up and turns left to back into the parking space, then rotates around the axis of the right rear wheel until the vehicle body is parallel to the long side of the target parking space, and finally moves forward or backward to adjust the vehicle to the middle position of the target parking space.

[0121] In the disclosed embodiment, the front-end parking trajectory or the rear-end parking trajectory can be planned according to the positional relationship between the target parking space and the vehicle, so that the vehicle can be parked with its front end or its rear end, realizing front-end parking in the side parking space end-road scenario, which cannot be realized by conventional parking.

[0122] The present disclosure also provides a controller, as shown in FIG10 , which includes:

[0123] A storage device 801 , wherein the storage device 801 stores a computer program;

[0124] The control device 802 is used to execute a computer program to implement any of the above parking trajectory planning methods.

[0125] In the disclosed embodiment, a target parking trajectory for the vehicle from the initial parking point to the target parking point is determined based on the vehicle's initial parking point, target parking point, and rotation starting point. The vehicle has a single-wheel rotation function, and the rotation starting point is the starting point of the rotation around the target wheel in the vehicle's exit trajectory from the target parking point to the initial parking point. This allows the vehicle to plan a target parking trajectory using the vehicle's single-wheel rotation function. This allows the vehicle to park in a narrow parking space in one go, avoiding multiple maneuvers, thereby reducing parking time and improving parking efficiency.

[0126] An embodiment of the present disclosure also provides a vehicle, which includes the above-mentioned controller.

[0127] In a possible embodiment, the vehicle includes four motors, each motor driving a corresponding wheel.

[0128] In the disclosed embodiment, a target parking trajectory is determined for the vehicle from the initial parking point to the target parking point based on the vehicle's initial parking point, target parking point, and rotation starting point. The vehicle has a single-wheel rotation function, and the rotation starting point is the starting point of the rotation around the target wheel in the vehicle's exit trajectory from the target parking point to the initial parking point. This allows the vehicle to plan a target parking trajectory using the vehicle's single-wheel rotation function. This allows the vehicle to park in a narrow parking space in one go, reducing the number of maneuvers required, thereby shortening parking time and improving parking efficiency.

[0129] FIG11 is a block diagram of a vehicle 900 according to an exemplary embodiment. For example, vehicle 900 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or another type of vehicle. Vehicle 900 may be an autonomous vehicle or a semi-autonomous vehicle.

[0130] 11 , vehicle 900 may include various subsystems, such as an infotainment system 910, a perception system 920, a decision-making control system 930, a drive system 940, and a computing platform 950. Vehicle 900 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of vehicle 900 may be interconnected via wired or wireless means.

[0131] In some embodiments, the infotainment system 910 may include a communication system, an entertainment system, a navigation system, and the like.

[0132] The perception system 920 may include several sensors for sensing information about the environment surrounding the vehicle 900. For example, the perception system 920 may include a global positioning system (which may be a GPS system, a BeiDou system, or another positioning system), an inertial measurement unit (IMU), a laser radar, a millimeter-wave radar, an ultrasonic radar, and a camera.

[0133] The decision control system 930 may include a computing system, the aforementioned controller, a steering system, a throttle, and a braking system.

[0134] The drive system 940 may include components that provide power to the vehicle 900. In one embodiment, the drive system 940 may include an engine, a power source, a transmission system, and wheels. The engine may be an internal combustion engine, an electric motor, an air compression engine, or a combination thereof. The engine is capable of converting energy provided by the power source into mechanical energy.

[0135] Some or all functions of the vehicle 900 are controlled by a computing platform 950. The computing platform 950 may include at least one processor 951 and a memory 952. The processor 951 may execute instructions 953 stored in the memory 952.

[0136] The processor 951 can be any conventional processor, such as a commercially available CPU. The processor can also include a graphics processor (GPU), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), or a combination thereof.

[0137] The memory 952 can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0138] In addition to the instructions 953 , the memory 952 may also store data, such as the initial parking point, target parking point, and rotation starting point of the vehicle relative to the target parking space. The data stored in the memory 952 may be used by the computing platform 950 .

[0139] In the embodiment of the present disclosure, the processor 951 may also execute the instruction 953 to complete all or part of the steps of the above-mentioned parking trajectory planning method.

[0140] In another exemplary embodiment, a computer-readable storage medium containing program instructions is also provided. When executed by a processor, these program instructions implement the steps of the aforementioned parking trajectory planning method. For example, the computer-readable storage medium may be the aforementioned memory 952 containing the program instructions. These program instructions may be executed by the processor 951 of the vehicle 900 to perform the aforementioned parking trajectory planning method.

[0141] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable device, and has a code portion for performing the above-mentioned automatic driving method when executed by the programmable device.

[0142] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the scope of protection of the present disclosure.

[0143] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0144] In addition, the various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A parking trajectory planning method, characterized in that, The method includes: Determining an initial parking point, a target parking point, and a rotation starting point for the vehicle to a target parking space, where the vehicle has a single-wheel rotation function, and the rotation starting point is the starting point of the vehicle rotating around the target wheel in the parking-out trajectory from the target parking point to the initial parking point; Determining a target parking trajectory of the vehicle from the initial parking point to the target parking point according to the initial parking point, the target parking point, and the rotation starting point.

2. The parking trajectory planning method according to claim 1, wherein The determining the target parking trajectory of the vehicle from the initial parking point to the target parking point according to the initial parking point, the target parking point, and the rotation starting point includes: Determining a first trajectory according to the target parking point and the rotation starting point, and determining a second trajectory according to the rotation starting point and the initial parking point; Obtaining the target parking trajectory of the vehicle from the initial parking point to the target parking point according to the first trajectory and the second trajectory.

3. The parking trajectory planning method according to claim 2, wherein The determining the first trajectory according to the target parking point and the rotation starting point, and determining the second trajectory according to the rotation starting point and the initial parking point includes: Determining a first trajectory from the target parking point to the rotation starting point, and determining a second trajectory from the rotation starting point to the initial parking point; The obtaining the target parking trajectory of the vehicle from the initial parking point to the target parking point according to the first trajectory and the second trajectory includes: Splicing the first trajectory and the second trajectory to obtain an initial parking trajectory from the target parking point to the initial parking point, and reversing the initial parking trajectory to obtain the target parking trajectory of the vehicle from the initial parking point to the target parking point.

4. The parking trajectory planning method according to claim 2 or 3, wherein The determining the second trajectory according to the rotation starting point and the initial parking point includes: Determining a minimum rotation angle and a maximum rotation angle for the vehicle to rotate around the axis of the target wheel in the parking-out trajectory, and determining a target rotation end point according to a first rotation end point after the vehicle rotates around the minimum rotation angle and a second rotation end point after the vehicle rotates around the maximum rotation angle; Determining a single-wheel rotation trajectory from the rotation starting point to the target rotation end point, and an out-of-parking-space parking trajectory from the target rotation end point to the initial parking point; Splicing the single-wheel rotation trajectory and the out-of-parking-space parking trajectory into a second trajectory from the rotation starting point to the initial parking point.

5. The parking trajectory planning method according to claim 4, wherein, The determining the target rotation end point according to the first rotation end point after the vehicle rotates around the minimum rotation angle and the second rotation end point after the vehicle rotates around the maximum rotation angle includes: Sampling between the first rotation end point after the vehicle rotates around the minimum rotation angle and the second rotation end point after the vehicle rotates around the maximum rotation angle to obtain a plurality of sampling points; For each of the sampling points, a first candidate trajectory from the sampling point to the rotation starting point is determined by different trajectory planning algorithms. According to the trajectory cost of each first candidate trajectory, a target candidate trajectory is determined, and the sampling point corresponding to the target candidate trajectory is used as the target rotation end point; Correspondingly, the out-of-library parking trajectory is the target candidate trajectory.

6. The parking trajectory planning method according to claim 5, wherein, The trajectory cost of the first candidate trajectory is determined by at least one of the trajectory length of the first candidate trajectory, the single-wheel rotation angle of the vehicle in the first candidate trajectory, the collision risk value of the vehicle in the first candidate trajectory, and the number of gear shifts of the vehicle in the first candidate trajectory.

7. The parking trajectory planning method according to claim 5 or 6, characterized in that, The determining a target candidate trajectory according to the trajectory cost of each first candidate trajectory includes: When there is no collision risk between the vehicle in the first candidate trajectory and the surrounding obstacles, a target candidate trajectory is determined according to the trajectory cost of each first candidate trajectory; The method further includes: When there is a collision risk between the vehicle in the first candidate trajectory and the surrounding obstacles, second candidate trajectories from each sampling point to the initial parking point are sequentially determined by a trajectory search method until there is no collision risk between the vehicle in the obtained second candidate trajectory and the surrounding obstacles; The finally obtained second candidate trajectory is determined as the target candidate trajectory.

8. The parking trajectory planning method according to any one of claims 4-7, characterized in that The minimum rotation angle is greater than a first preset angle, and there is no collision risk between the vehicle and the obstacles around the target parking space during the process of driving straight out of the target parking space along the first rotation end point corresponding to the minimum rotation angle; The maximum rotation angle is less than a second preset angle, and there is no collision risk between the vehicle and the obstacles outside the target parking space during the process of the vehicle rotating along the maximum rotation angle.

9. The parking trajectory planning method according to any one of claims 4-7, characterized in that The determining the minimum rotation angle of the vehicle rotating around the axis of the target wheel in the parking-out trajectory includes: Determining an initial first rotation angle and repeatedly executing the following steps: determining an initial rotation end point after the vehicle rotates the first rotation angle around the axis of the target wheel with the rotation starting point, determining a straight-line trajectory between the initial rotation end point and the target rear axle center point of the vehicle, when there is a collision risk for the vehicle in the straight-line trajectory, increasing the first rotation angle by a first preset step length to obtain a new first rotation angle until there is no collision risk for the vehicle in the obtained straight-line trajectory, where the target rear axle center point is located in the part of the vehicle outside the target parking space and is at a preset distance from the initial rotation end point in the target direction, and the target direction is parallel to the short side of the target parking space; The finally obtained first rotation angle is determined as the minimum rotation angle of the vehicle rotating around the axis of the target wheel in the parking-out trajectory.

10. The parking trajectory planning method according to any one of claims 4-7, characterized in that The determining the maximum rotation angle of the vehicle rotating around the axis of the target wheel in the parking-out trajectory includes Determine an initial second rotation angle and loop to execute the following steps: Determine whether there is a collision risk when the vehicle rotates by the second rotation angle around the axis of the target wheel starting from the rotation starting point. When there is no collision risk for the vehicle, increase the second rotation angle by a second preset step length to obtain a new second rotation angle until there is a collision risk for the vehicle; Determine the rotation angle obtained by subtracting the second preset step length from the finally obtained second rotation angle as the maximum rotation angle of the vehicle rotating around the axis of the target wheel in the parking-out trajectory.

11. The parking trajectory planning method according to any one of claims 1-7, characterized in that, When the target parking space is located in the front right of the vehicle, the target wheel is the left front wheel of the vehicle, and correspondingly, the target parking trajectory is a front-end parking-in trajectory; or, When the target parking space is located in the rear right of the vehicle, the target wheel is the left rear wheel of the vehicle, and correspondingly, the target parking trajectory is a rear-end parking-in trajectory; or, When the target parking space is located in the front left of the vehicle, the target wheel is the right front wheel of the vehicle, and correspondingly, the target parking trajectory is a front-end parking-in trajectory; or, When the target parking space is located in the rear left of the vehicle, the target wheel is the right rear wheel of the vehicle, and correspondingly, the target parking trajectory is a rear-end parking-in trajectory.

12. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program is executed by a processor, it implements the parking trajectory planning method according to any one of claims 1-11.

13. A controller, characterized in that, Comprising: A storage device in which a computer program is stored; A control device for executing the computer program to implement the parking trajectory planning method according to any one of claims 1-11.

14. A vehicle, characterized in that, The vehicle includes the controller according to claim 13.

15. The vehicle according to claim 14, characterized in that, The vehicle includes four motors, and each motor drives one wheel correspondingly.

Images