A parking path planning method, device and medium

Abstract

The present application provides a parking path planning method, device and medium, including: determining multiple i-th moving distances of the i-th parking operation based on the i-th position of the vehicle, vehicle parameters and parking area information. For each i-th moving distance, determine the i+1-th position of the vehicle after moving the i-th moving distance. Update i with i+1, iterate the above steps until the parking condition is met when the vehicle moves to the i+1-th position, determine the candidate parking path based on the i moving distances associated with the i+1-th position, and obtain multiple candidate parking paths based on multiple i+1-th positions. Through this method, multiple different candidate parking paths can be planned and a target parking path that meets user needs can be selected. For example, the number of movements during automatic parking is reduced, and the accuracy of automatic parking is improved, thereby meeting the different needs of users.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a parking path planning method, device and medium. Background Art

[0002] As the number of cars continues to increase, parking spaces are becoming increasingly scarce. The narrow parking space makes parking operations more difficult, and automatic parking technology comes into being. Automatic parking technology can obtain information about the vehicle itself and obstacles through various sensors, and plan parking paths based on parking space, which can effectively save parking time, reduce parking difficulty, and improve parking safety.

[0003] During the parking process, it is usually difficult to park the vehicle in the parking space through a single reversing process, and multiple parking maneuvers are required to complete parking. That is, the vehicle needs to be controlled to move forward or backward repeatedly to achieve parking. The current method of realizing automatic parking usually uses the occurrence of a collision as the condition for ending the parking maneuvering operation. For example, when controlling the vehicle to move into the parking space, the vehicle is controlled to turn right and move forward until a collision occurs, and then the vehicle is controlled to turn left and move backward until a collision occurs, and the parking maneuvers are repeated. However, this parking method will increase the number of parking maneuvers, and when the vehicle is parked in the parking space (parking is completed), the distance between the longitudinal axis of the vehicle and the center line of the parking space is far, resulting in poor accuracy of automatic parking. Summary of the invention

[0004] In view of this, the present application is dedicated to providing a parking path planning method, device and medium, so as to reduce the number of movements during automatic parking, improve the accuracy of automatic parking, and meet the different needs of users.

[0005] In a first aspect, the present application provides a parking path planning method, the method comprising:

[0006] Determining a plurality of i-th moving distances for an i-th parking operation based on an i-th position of the vehicle, vehicle parameters, and parking area information;

[0007] For each i-th moving distance, determining an i+1-th position of the vehicle after the vehicle moves the i-th moving distance;

[0008] Updating i by using i+1, iteratively performing the above steps until the vehicle satisfies the parking condition when moving to the i+1th position, determining a candidate parking path based on i moving distances associated with the i+1th position, thereby obtaining a plurality of candidate parking paths based on a plurality of the i+1th positions, wherein i is an integer greater than or equal to 1;

[0009] Based on the plurality of candidate parking paths, a target parking path is determined.

[0010] In a possible implementation, determining a plurality of i-th moving distances of the i-th parking operation based on the i-th position of the vehicle, the vehicle parameters, and the parking area information includes:

[0011] determining an i-th maximum moving distance of an i-th parking operation based on the i-th position, the vehicle parameters, and the parking area information;

[0012] Based on a preset step length and the i-th maximum moving distance, a plurality of the i-th moving distances are determined.

[0013] In a possible implementation, the vehicle parameters include four corner points of the vehicle, the parking area information includes four vertices of the parking area, and determining the i-th maximum moving distance of the i-th parking operation based on the i-th position, the vehicle parameters, and the parking area information includes:

[0014] determining an i-th target position after the vehicle moves the i-th maximum moving distance, wherein a corner point of the vehicle is located on a safety line of the parking area when the vehicle is at the i-th target position, and the safety line is determined based on a vertex of the parking area;

[0015] Based on the i-th position and the i-th target position, the i-th maximum moving distance is determined.

[0016] In a possible implementation, determining the i-th target position after the vehicle moves the i-th maximum moving distance, wherein a corner point of the vehicle is located on a safety line of a parking area when the vehicle is at the i-th target position, includes:

[0017] When the driving direction corresponding to the i-th maximum moving distance is turning right and moving forward, determining the i-th target position after the vehicle moves the i-th maximum moving distance, when the vehicle is at the i-th target position, the right front corner point of the vehicle is located at the right safety line of the parking area, and the right safety line is determined based on the vertex on the right side of the parking area;

[0018] When the driving direction corresponding to the i-th maximum moving distance is left turn and backward, determining the i-th target position after the vehicle moves the i-th maximum moving distance, when the vehicle is at the i-th target position, the right rear corner point of the vehicle is located at the lower safety line of the parking area, or when the vehicle is at the i-th target position, the left rear corner point of the vehicle is located at the left safety line of the parking area;

[0019] When the driving direction corresponding to the i-th maximum moving distance is turning left and reversing, determining the i-th maximum moving distance based on the i-th position and the i-th target position includes:

[0020] When the vehicle is at the i-th target position and the right rear corner point of the vehicle is located at the lower safety line of the parking area, determining a lower maximum moving distance based on the i-th position and the i-th target position;

[0021] When the vehicle is at the i-th target position and the left rear corner point of the vehicle is located at the left safety line of the parking area, determining a left maximum moving distance based on the i-th position and the i-th target position;

[0022] The smaller value between the bottom maximum moving distance and the left maximum moving distance is determined as the i-th maximum moving distance.

[0023] In a possible implementation, determining a plurality of i-th moving distances based on a preset step size and the i-th maximum moving distance includes:

[0024] Taking the preset step length as the initial value, increasing the preset step length each time to obtain multiple initial i-th distances, and stopping iteration when the obtained initial i-th distance is greater than the i-th maximum moving distance;

[0025] When the safety line is located in the parking area, determining the i+1th target position after the vehicle moves based on the initial i-th distance greater than the i-th maximum moving distance; when the vehicle is located at the i+1th target position and satisfies that the vehicle does not exceed the boundary of the parking area, determining multiple initial i-th distances as multiple i-th moving distances; otherwise, repeatedly executing the process of updating the initial i-th distance greater than the i-th maximum moving distance by using a preset multiple until the vehicle is located at the updated i+1th target position and satisfies that the vehicle does not exceed the boundary of the parking area, determining multiple i-th moving distances based on the updated initial i-th distance and the original multiple initial i-th distances;

[0026] When the safety line is located at the boundary of the parking area, the initial i-th distance greater than the i-th maximum moving distance is deleted, and a plurality of i-th moving distances are determined based on the remaining plurality of initial i-th distances and the i-th maximum moving distance.

[0027] In a possible implementation, determining a target parking path based on the plurality of candidate parking paths includes:

[0028] The target parking path is determined based on at least one of a number of movements corresponding to the candidate parking path, an error between an (i+1)th position corresponding to the candidate parking path and a target parking position in the parking area, and a length of the candidate parking path.

[0029] In a possible implementation, determining a target parking path based on the plurality of candidate parking paths includes:

[0030] Determining the number of movements corresponding to each of the candidate parking paths;

[0031] The target parking path is determined based on a minimum value among a plurality of the movement times.

[0032] In a possible implementation, determining the target parking path based on a minimum value among the plurality of movement times includes:

[0033] When there are multiple identical minimum values ​​among the multiple movement times, determining the i+1th position of the candidate parking path corresponding to the multiple identical minimum values;

[0034] determining errors between a plurality of the (i+1)th positions and a target parking position within the parking area;

[0035] Based on the error, the target parking path is determined.

[0036] In a possible implementation, the method of determining the target parking position includes:

[0037] When the width of the parking area is greater than a first threshold, determining the target parking position based on the width of the parking area, the width of the vehicle, and the vehicle depth of the parking position;

[0038] When the width of the parking area is less than a second threshold, the target parking position is determined based on the width of the parking area, the width of the vehicle, and a safety distance from a lower boundary of the parking area, and the first threshold is greater than the second threshold.

[0039] In a possible implementation, determining the target parking position based on the width of the parking area, the width of the vehicle, and the depth of the parking position includes:

[0040] Calculating a first difference between the width of the parking area, half the width of the vehicle, and the vehicle depth of the parking position;

[0041] determining the target parking position based on the first difference;

[0042] The determining the target parking position based on the width of the parking area, the width of the vehicle, and the safety distance from the lower boundary of the parking area includes:

[0043] calculating a second difference between the width of the parking area and half the width of the vehicle and a safety distance from a lower boundary of the parking area;

[0044] The target parking position is determined based on the second difference.

[0045] In a possible implementation, during parallel parking, the parking condition includes: a heading angle of the vehicle is less than a preset angle.

[0046] In a possible implementation, when i is 1, the first position represents any position where the vehicle enters the parking area for the first time.

[0047] In a second aspect, the present application provides a method for controlling a vehicle to park, the method comprising:

[0048] Determine a target parking path based on the vehicle position, vehicle parameters, and parking area information, wherein the target parking path is determined based on the parking path planning method described in any one of the implementations of the first aspect above;

[0049] The vehicle is controlled to park in the parking area based on the target parking path.

[0050] In a third aspect, the present application provides a parking path planning device, the device comprising:

[0051] a moving distance determining unit, configured to determine a plurality of i-th moving distances of an i-th parking operation based on an i-th position of the vehicle, vehicle parameters, and parking area information;

[0052] a position determination unit, for determining, for each i-th moving distance, an i+1th position of the vehicle after the vehicle moves the i-th moving distance;

[0053] an iterative unit, configured to update i by using i+1, iteratively perform the above steps until the vehicle satisfies the parking condition when moving to the i+1th position, determine a candidate parking path based on i moving distances associated with the i+1th position, and thereby obtain a plurality of candidate parking paths based on a plurality of the i+1th positions, wherein i is an integer greater than or equal to 1;

[0054] The path planning unit is used to determine a target parking path based on the plurality of candidate parking paths.

[0055] In a fourth aspect, the present application provides a device for controlling a vehicle to park, the device comprising:

[0056] a path determination unit, configured to determine a target parking path based on the position of the vehicle, vehicle parameters, and parking area information, wherein the target parking path is determined based on the parking path planning method described in any one of the implementations of the first aspect;

[0057] A control unit is used to control the vehicle to park in the parking area based on the target parking path.

[0058] In a fifth aspect, the present application provides an electronic device, the device comprising: a memory and a processor;

[0059] The memory is used to store relevant program codes;

[0060] The processor is used to call the program code to execute the parking path planning method described in any one of the implementations of the first aspect or the method of controlling a vehicle to park described in any one of the implementations of the second aspect.

[0061] In a sixth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, wherein the computer program is used to execute the parking path planning method described in any one of the implementations of the first aspect or the method of controlling a vehicle to achieve parking described in any one of the implementations of the second aspect.

[0062] In a seventh aspect, the present application provides a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, the parking path planning method described in any one of the implementations of the first aspect or the method of controlling a vehicle to achieve parking described in any one of the implementations of the second aspect are implemented.

[0063] In the above implementation of the present application, the planning of the parking path can be implemented in the following manner: after obtaining the i-th position of the vehicle, multiple i-th moving distances of the i-th parking operation can be determined based on the i-th position of the vehicle, the vehicle parameters and the parking area information. For each i-th moving distance, the i+1th position after the vehicle moves the i-th moving distance is determined, that is, multiple i-th moving distances can obtain multiple corresponding i+1th positions. Then, i is updated by i+1, and the above steps are iteratively performed until the parking condition is met when the vehicle moves to the i+1th position, and the iteration is stopped. The candidate parking path is determined based on the i moving distances associated with the i+1th position, so as to obtain multiple candidate parking paths based on multiple i+1th positions. Wherein, i is an integer greater than or equal to 1. For example, based on the first position of the vehicle, the vehicle parameters and the parking area information, multiple first moving distances of the first parking operation are determined. For each first moving distance, the second position after the vehicle moves the first moving distance is determined. For each second position, based on the second position of the vehicle, the vehicle parameters and the parking area information, multiple second moving distances of the second parking operation are determined. For each second moving distance, determine the third position after the vehicle moves the second moving distance, thereby obtaining multiple third positions. For each third position, determine whether the parking condition is met when the vehicle moves to the third position. If it is met, the process corresponding to the third position stops iterating; if it is not met, continue to execute multiple third moving distances and subsequent steps for determining the third parking operation based on the third position, vehicle parameters and parking area information. After all iterations are completed, multiple candidate parking paths can be obtained. Then, based on the multiple candidate parking paths, a target parking path that meets the needs can be determined. Through the method provided by the present application, in each parking operation, multiple possible moving distances of the current parking operation can be determined, so that based on each possible moving distance, multiple different candidate parking paths can be planned, and a target parking path that meets the user's needs can be selected from the multiple candidate parking paths, so as to control the vehicle to achieve automatic parking based on the target parking path. For example, a candidate parking path with fewer moving times during the parking process can be selected, or a candidate parking path with a parking position closer to the center of the parking area can be selected, thereby reducing the number of moving times during automatic parking, improving the accuracy of automatic parking, and meeting different needs of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. It is obvious that the drawings described below are only some embodiments provided in the present application, and a person skilled in the art can also obtain other drawings based on these drawings.

[0065] Figure 1aA schematic diagram of a parallel parking method provided in an embodiment of the present application.

[0066] Figure 1b A schematic diagram of a vertical parking method provided in an embodiment of the present application.

[0067] Figure 2 A flowchart of a parking path planning method provided in an embodiment of the present application.

[0068] Figure 3 A schematic diagram of a parking area provided in an embodiment of the present application.

[0069] Figure 4a A schematic diagram of another parking area provided in an embodiment of the present application.

[0070] Figure 4b A schematic diagram of another parking area provided in an embodiment of the present application.

[0071] Figure 5a A schematic diagram of a parking operation provided in an embodiment of the present application.

[0072] Figure 5b A schematic diagram of another parking operation provided in an embodiment of the present application.

[0073] Figure 5c A schematic diagram of another parking operation provided in an embodiment of the present application.

[0074] Figure 6a A schematic diagram of determining a minimum turning radius provided in an embodiment of the present application.

[0075] Figure 6b A schematic diagram of determining a maximum moving distance provided in an embodiment of the present application.

[0076] Figure 7a A schematic diagram of parking provided in an embodiment of the present application.

[0077] Figure 7b A schematic diagram of another parking method provided in an embodiment of the present application.

[0078] Figure 8 A flowchart of a method for controlling a vehicle to park is provided in an embodiment of the present application.

[0079] Fig. 9 A schematic diagram of a parking path planning device provided in an embodiment of the present application.

[0080] Fig.10 A schematic diagram of a device for controlling a vehicle to park provided in an embodiment of the present application.

[0081] Fig.11A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0082] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. The described embodiments are only exemplary implementation methods of the present application, not all implementation methods. Those skilled in the art can combine the embodiments of the present application to obtain other embodiments without creative work, and these embodiments are also within the scope of protection of the present application.

[0083] Automatic parking technology can obtain the vehicle's own information and obstacle information through various sensors, and plan the parking path based on the parking space. It can effectively save parking time, reduce parking difficulty, and improve parking safety.

[0084] During the parking process, it is usually difficult to park the vehicle in the parking space through a single reversing process, and multiple parking maneuvers are required to complete parking. That is, the vehicle needs to be controlled to move forward or backward repeatedly to achieve parking. The current method of realizing automatic parking usually uses the occurrence of a collision as the condition for ending the parking maneuvering operation. For example, when controlling the vehicle to move into the parking space, the vehicle is controlled to turn right and move forward until a collision occurs, and then the vehicle is controlled to turn left and move backward until a collision occurs, and the parking maneuvers are repeated. However, this parking method will increase the number of parking maneuvers, and when the vehicle is parked in the parking space (parking is completed), the distance between the longitudinal axis of the vehicle and the center line of the parking space is far, resulting in poor accuracy of automatic parking.

[0085] Based on this, the embodiment of the present application provides a parking path planning method, which can reduce the number of movements during automatic parking, improve the accuracy of automatic parking, and meet the different needs of users. In specific implementation, after obtaining the i-th position of the vehicle, multiple i-th moving distances of the i-th parking operation can be determined based on the i-th position of the vehicle, vehicle parameters, and parking area information. For each i-th moving distance, the i+1th position after the vehicle moves the i-th moving distance is determined, that is, multiple i-th moving distances can obtain multiple corresponding i+1th positions. Then, i is updated by i+1, and the above steps are iteratively performed until the parking condition is met when the vehicle moves to the i+1th position, and the iteration is stopped to obtain multiple candidate parking paths. Among them, i is an integer greater than or equal to 1. Through the method provided by the embodiment of the present application, in each parking operation, multiple possible moving distances of the current parking operation can be determined, so that multiple different candidate parking paths can be planned based on each possible moving distance, and a target parking path that meets the user's needs is selected from multiple candidate parking paths, so as to control the vehicle to achieve automatic parking based on the target parking path. For example, you can choose a candidate parking path that requires fewer movements during parking, or choose a candidate parking path whose parking position is closer to the center of the parking area. This can reduce the number of movements during automatic parking, improve the accuracy of automatic parking, and meet the different needs of users.

[0086] In order to facilitate understanding of the method provided in the embodiments of the present application, a detailed description will be given below in conjunction with the drawings of the embodiments.

[0087] Automatic parking mainly includes two parking modes, one is parallel parking and the other is perpendicular parking. Figure 1a As shown, Figure 1a A schematic diagram of a parallel parking method provided in an embodiment of the present application. Figure 1a There are three parallel parking areas, namely parking area 1, parking area 2, and parking area 3. Parallel parking refers to the process of parking a vehicle in a parallel position with a parking space. The parking space is parallel to the driving direction of the vehicle. The vehicle needs to be moved horizontally to the parking space and ensure that the front or rear of the vehicle is kept at a certain distance from the edge of the parking space. Figure 1b As shown, Figure 1b A schematic diagram of a vertical parking method provided in an embodiment of the present application. Figure 1b There are 4 vertical parking areas, namely parking area a, parking area b, parking area c, and parking area d. Vertical parking means parking a vehicle in a vertical parking space, that is, the parking space is perpendicular to the direction of travel of the vehicle. Usually, the vehicle needs to be parked vertically in the parking space by reversing into the garage.

[0088] When the method of the embodiment of the present application is applied to perform parking path planning, the principles of parallel parking and perpendicular parking are the same, and in the subsequent embodiments, parallel parking is taken as an example for explanation.

[0089] See also Figure 2 As shown, Figure 2 A flowchart of a parking path planning method provided in an embodiment of the present application.

[0090] Optionally, the parking path planning method may be executed by an automatic parking system of the vehicle. The automatic parking system may plan a parking path based on vehicle information and parking area information when the vehicle needs to park, and help the vehicle to achieve automatic parking.

[0091] The method may include the following steps:

[0092] S201: Determine a plurality of i-th moving distances of an i-th parking operation based on an i-th position of the vehicle, vehicle parameters, and parking area information.

[0093] In the embodiment of the present application, the parking operation is also a parking operation, that is, an operation of controlling the vehicle to move during the parking process. One parking operation can be understood as controlling the vehicle to move once, and the moving distance can have multiple possibilities. Different from the prior art that determines the moving distance based on the collision of the vehicle in each parking operation, that is, the prior art has only one moving distance for each parking operation, in the embodiment of the present application, there are multiple possibilities for the moving distance corresponding to each parking operation, and the vehicle does not necessarily collide with the safety line of the parking area after moving according to the moving distance.

[0094] i in the present application corresponds to the number of parking operations (ie, the number of movements). For example, in a first parking operation, a plurality of first movement distances of the first parking operation are determined based on the first position of the vehicle, vehicle parameters, and parking area information.

[0095] Optionally, the vehicle's location information, vehicle parameters, parking area information, etc. can be collected by a device with an image collection function in the vehicle. For example, it can be a camera, a vehicle-mounted radar, or other device with an image collection function. The collected information is then sent to the automatic parking system.

[0096] The vehicle parameters may include the four corners of the vehicle (left front corner, right front corner, left rear corner, right rear corner), the length and width of the vehicle, the center of the rear axle of the vehicle, etc. The parking area information includes the four vertices of the parking area (left front corner, right front corner, left rear corner, right rear corner). Figure 3FIG. 1 is a schematic diagram of a parking area provided in an embodiment of the present application. In an embodiment of the present application, an actual vehicle can be simulated as a flat rectangular vehicle model, and the movement of the vehicle can be equivalent to the movement of the center of the rear axle of the vehicle, that is, Figure 3 The rear axle center t shown in the figure can represent the intersection of the vehicle centerline and the rear axle of the vehicle. The actual parking space can also be simulated as a flat rectangular parking area, that is, a rectangular area composed of p1, p2, p3, and p4. The left and right sides of the vehicle can be determined based on the perspective of the driver sitting in the driving position, and the left and right sides of the parking area can be determined based on the perspective of looking down at the parking area. Figure 3 It can be seen that c1 represents the left front corner of the vehicle, c2 represents the right front corner of the vehicle, c3 represents the left rear corner of the vehicle, and c4 represents the right rear corner of the vehicle. p1 represents the left front vertex of the parking area, p2 represents the right front vertex of the parking area, p3 represents the left rear vertex of the parking area, and p4 represents the right rear vertex of the parking area.

[0097] In one possible implementation, the automatic parking system can establish a coordinate system with any vertex of the parking area as the coordinate origin. The automatic parking system can determine the length and width of the parking area based on the captured image of the parking area, and thus can determine the coordinates of the four vertices of the parking area based on the length and width of the parking area. After establishing the coordinate system of the parking area, the automatic parking system can determine the coordinates of the vehicle based on the relative position of the vehicle and the parking area. For example, the coordinates of the four corner points are determined based on the distance between the four corner points of the vehicle and the coordinate origin. The coordinates of the center of the rear axle are determined based on the distance between the center of the rear axle of the vehicle and the coordinate origin, and the coordinates of the center of the rear axle represent the position of the vehicle.

[0098] In the above embodiment, a ground coordinate system is established with any vertex of the parking area as the coordinate origin. Since the parking area is fixed, a fixed coordinate system is established, and the coordinates of the four vertices of the parking area are also fixed, which can simplify the calculation process of the parking area in subsequent calculations.

[0099] It should be noted that the method of establishing a coordinate system and determining coordinates provided in the above embodiment is only an exemplary description and is not limited to the above implementation method. For example, the automatic parking system can also establish a coordinate system with the center of the rear axle of the vehicle as the coordinate origin. At this time, since the structure of the vehicle itself is fixed, that is, the relative position relationship between the four corner points of the vehicle and the center of the rear axle is fixed. Therefore, even if the vehicle moves to different positions, the coordinates of the four corner points of the vehicle are fixed, which can simplify the calculation process of the coordinates of the vehicle corner points.

[0100] After determining the position of the vehicle, vehicle parameters and parking area information, multiple moving distances of the parking operation can be calculated. That is, during the parking process, there may be multiple possible moving distances corresponding to each parking operation. The parking operation can be understood as the operation of moving the vehicle forward or backward, and the vehicle is finally parked in the parking area by repeatedly controlling the vehicle to move forward or backward.

[0101] S202: For each i-th moving distance, determine the (i+1)th position of the vehicle after the vehicle moves the i-th moving distance.

[0102] After determining multiple i-th moving distances in step S201, for each i-th moving distance, the i+1th position of the vehicle after moving the i-th moving distance can be estimated. Since there are multiple i-th moving distances, multiple i+1th positions can be determined, and each i-th moving distance corresponds to an i+1th position.

[0103] S203: Update i with i+1, iterate the above steps until the parking condition is satisfied when the vehicle moves to the i+1th position, determine a candidate parking path based on the i moving distances associated with the i+1th position, and thereby obtain multiple candidate parking paths based on multiple i+1th positions. Wherein, i may be an integer greater than or equal to 1.

[0104] The above steps S201 and S202 are repeated execution processes, that is, after determining the i+1th position, i+1 is used as a new i and re-substituted into steps S201 and S202 to obtain a new i+1th position. The above steps are iteratively executed until after determining the i+1th position, when the vehicle moves to the i+1th position, the parking condition is satisfied, and then the iterative process is stopped. In the above manner, all i+1th positions that satisfy the parking condition can be found, and the parking is completed when the vehicle moves to the i+1th position that satisfies the parking condition.

[0105] Optionally, the parking condition may include that the heading angle of the vehicle is less than a preset angle, and the heading angle may represent the angle between the vehicle's center of mass velocity and the horizontal axis. In the embodiment of the present application, it can be understood as the angle between the centerline of the longitudinal axis of the vehicle and the horizontal direction. In the scenario of parallel parking, when the heading angle of the vehicle is less than a preset angle, it can be understood that the vehicle's driving direction is already parallel to the parking area, satisfying the conditions for parallel parking. Among them, the vehicle's heading angle can be measured by the vehicle's inertial navigation system, magnetometer, etc., which is not introduced in the embodiment of the present application.

[0106] After the iteration process is stopped, the vehicle reaches the i+1th position that meets the parking condition, and the i+1th position is the position reached after moving i moving distances. That is, the vehicle moves the first moving distance, the second moving distance, ..., and reaches the i+1th position after moving the i-th moving distance, and a candidate parking path can be formed based on the i moving distances associated with the i+1th position. That is, each i+1th position corresponds to a candidate parking path, and the candidate parking path is composed of i moving distances to move to the i+1th position. Since multiple i-th moving distances can be determined for each parking operation, multiple i+1th positions that meet the parking condition can be determined in the end, so that multiple candidate parking paths corresponding to multiple i+1th positions can be obtained.

[0107] S204: Determine a target parking path based on multiple candidate parking paths.

[0108] Each candidate parking path is obtained only when the position of the vehicle after moving meets the parking conditions. Different moving distances in one parking operation will affect the position after moving and the moving distance in the next parking operation, so that the number of moving distances (number of moves) included in each candidate parking path may be the same or different. That is, the value of i corresponding to each candidate parking path is not necessarily the same. After obtaining multiple candidate parking paths, a target parking path can be determined from the multiple candidate parking paths. Optionally, when determining the target parking path, different evaluation factors can be determined in combination with different user needs, and the target parking path can be determined from the multiple candidate parking paths based on the evaluation factors, so that the subsequent automatic parking system can control the vehicle to automatically park to the parking area based on the target parking path.

[0109] It should be noted that the processes of determining the moving distance and the position after the movement described in the above embodiments are theoretical calculation processes and do not actually control the vehicle to move in the parking area. After determining the target parking path, the automatic parking system can control the vehicle to move in the parking area based on the target parking path to complete automatic parking.

[0110] Through the method provided in the embodiment of the present application, instead of using the occurrence of a collision as the stop condition for each parking operation, multiple possible moving distances for each parking operation can be determined, so that multiple different candidate parking paths can be planned, and a target parking path that meets the user's needs can be determined from the multiple candidate parking paths. For example, a candidate parking path with a small number of moves during the parking process can be selected, or a candidate parking path with a parking position close to the center of the parking area can be selected, thereby reducing the number of moves during automatic parking, improving the accuracy of automatic parking, and meeting different user needs.

[0111] The specific implementation process of the above steps and the technical effects that can be further produced will be described in detail below in conjunction with the embodiments.

[0112] In order to more clearly understand the technical solution of the embodiment of the present application, the above-mentioned iterative process is first described in detail in conjunction with the embodiment.

[0113] First, the automatic parking system can obtain the first position of the vehicle, the vehicle parameters and the parking area information, and then determine multiple first moving distances of the first parking operation based on the first position, the vehicle parameters and the parking area information. Among them, the first position can represent any position where the vehicle enters the parking area for the first time. That is, the angle at which the vehicle enters the parking area is not limited in the embodiment of the present application, and the vehicle can enter the parking area for the first time at any angle or position. After the vehicle enters the parking area for the first time, the first position of the vehicle can be obtained. The first moving distance is used to indicate the distance moved by the vehicle in the first parking operation. Taking the parallel parking scenario as an example, the vehicle is controlled to first enter the parking area at an angle of right turn and backward, that is, to reach the first position. At this time, in order to adjust the position of the vehicle to achieve parallel parking, the vehicle can be controlled to move in the direction of right turn forward, and the distance moved in the first parking operation (kneading the warehouse) is the first moving distance.

[0114] Since the embodiment of the present application can determine multiple first moving distances, when performing path planning later, it is necessary to determine the second position after moving for each first moving distance, so as to continue path planning based on multiple second positions. Specifically, for each first moving distance, determine the second position of the vehicle after moving the first moving distance. It can be understood that the process of determining the second position of the vehicle is a theoretical calculation process, that is, it belongs to the pre-planned path, and does not really control the movement of the vehicle. Since the above process is performed for each first moving distance, multiple second positions can be determined, and each second position uniquely corresponds to a first moving distance.

[0115] After multiple second positions are determined, for each second position, it is determined whether the parking condition is satisfied when the vehicle moves to the second position. If satisfied, the second position is the final parking position, and a candidate parking path corresponding to the second position is obtained, that is, the candidate parking path is composed of the first moving distance, and the parking position corresponding to the candidate parking path is the second position. Since there are multiple second positions, it is determined whether the parking condition is satisfied for each second position, so it is possible to determine multiple second positions that satisfy the parking condition, and thus multiple candidate parking paths can be obtained.

[0116] For each second position, if the parking condition is not satisfied when the vehicle moves to the second position, multiple second moving distances for the second parking operation are determined based on the second position of the vehicle, the vehicle parameters, and the parking area information. For each second moving distance, a third position after the vehicle moves the second moving distance is determined, thereby obtaining multiple third positions corresponding to the multiple second moving distances.

[0117] For each third position, it is determined whether the parking condition is satisfied when the vehicle moves to the third position. If satisfied, the third position is the final parking position, and a candidate parking path corresponding to the third position is obtained. The candidate parking path is composed of the first moving distance and the second moving distance, and the parking position corresponding to the candidate parking path is the third position.

[0118] Since there are multiple third positions, it is determined whether each third position satisfies the parking condition. Therefore, multiple third positions satisfying the parking condition may be determined, and multiple candidate parking paths may be obtained. Each candidate parking path uniquely corresponds to one third position.

[0119] If the parking condition is not satisfied when the vehicle moves to the third position, the path planning is continued based on the third position. That is, multiple third moving distances for the third parking operation are determined based on the third position, vehicle parameters, and parking area information. For each third moving distance, the fourth position after the vehicle moves the third moving distance is determined, thereby obtaining multiple fourth positions corresponding to the multiple third moving distances.

[0120] For each fourth position, it is determined whether the parking condition is satisfied when the vehicle moves to the fourth position. If satisfied, the fourth position is the final parking position, and a candidate parking path corresponding to the fourth position is obtained. The candidate parking path is composed of the first moving distance, the second moving distance, and the third moving distance, and the parking position corresponding to the candidate parking path is the fourth position. If the parking condition is not satisfied when the vehicle moves to the fourth position, the path planning is continued based on the fourth position, and the above process is repeated until the parking condition is satisfied when the vehicle moves to a certain position, and the candidate parking path is formed based on each moving distance before reaching the position, that is, the candidate parking path includes all moving distances before reaching the position.

[0121] The following will describe in detail step S202 "for each i-th moving distance, determining the (i+1)th position of the vehicle after the vehicle moves the i-th moving distance" in conjunction with the embodiment.

[0122] In a possible implementation, after the i-th position of the vehicle, the vehicle parameters, and the parking area information are determined, the i-th maximum moving distance of the i-th parking operation may be determined first. For example, the i-th maximum moving distance may be determined by the safety line of the parking area when the vehicle moves. Then, based on the preset step length and the i-th maximum moving distance, multiple i-th moving distances are determined. That is, the i-th maximum moving distance may be used as a reference, and multiple i-th moving distances may be determined by increasing the preset step length.

[0123] That is, when determining the moving distance of the vehicle in each parking operation, the embodiment of the present application does not determine the moving distance based on the collision between the vehicle and the safety line of the parking area, but determines multiple possible moving distances based on the range of the maximum moving distance. After the vehicle moves based on the determined multiple moving distances, it does not necessarily collide with the safety line of the parking area, so that multiple candidate parking paths can be determined.

[0124] In a specific implementation, in order to determine the i-th maximum moving distance of the i-th parking operation, the i-th target position after the vehicle moves the i-th maximum moving distance may be first determined, wherein the i-th target position is determined in the following manner: when the vehicle is at the i-th target position, the corner point of the vehicle is located on the safety line of the parking area. That is, the collision of the corner point of the vehicle with the safety line of the parking area is used as the stop condition of the current parking operation, and the i-th maximum moving distance may be determined based on the current i-th target position. Based on the i-th position and the i-th target position, the i-th maximum moving distance is determined. The safety line may be determined based on the vertices of the parking area.

[0125] In order to more clearly understand the technical solution, in the embodiments of the present application, parallel parking is taken as an example for explanation. The principle of perpendicular parking is similar to that of parallel parking and will not be described in detail.

[0126] See also Figure 4a As shown, it is a schematic diagram of another parking area provided by an embodiment of the present application. In this application scenario, the lower boundary composed of the left rear vertex p3 and the right rear vertex p4 of the parking area can be used as the lower safety line, the left boundary composed of the left front vertex p1 and the left rear vertex p3 can be used as the left safety line, and the right boundary composed of the right front vertex p2 and the right rear vertex p4 can be used as the right safety line. This implementation method can provide the vehicle with the maximum space to move, making it more convenient for the vehicle to park. A larger moving space can also determine more moving distances, providing the vehicle with more candidate parking paths to meet different needs.

[0127] See also Figure 4bAs shown, it is a schematic diagram of another parking area provided in an embodiment of the present application. Optionally, a safety distance can be pre-set to prevent the vehicle from colliding with the boundary of the parking area. That is, at a position where there is a lower safety distance from the lower boundary of the parking area, the lower safety line in the parking area is determined. At a position where there is a left safety distance from the left boundary of the parking area, the left safety line of the parking area is determined. At a position where there is a right safety distance from the right boundary of the parking area, the right safety line of the parking area is determined. By setting the safety distance, the vehicle can be prevented from colliding with the boundary of the parking area during movement, thereby improving the safety of automatic parking. It should be noted that the safety distances from different boundaries of the parking area (left safety distance, right safety distance, bottom safety distance) can be the same or different, and the embodiment of the present application does not limit this.

[0128] When the direction of the vehicle is different, the safety line that collides with the parking area is also different. When determining the i-th target position, it is determined by the position that first collides with the safety line of the parking area. The following will be explained in combination with different scenarios.

[0129] See also Figure 5a As shown, it is a schematic diagram of a parking operation provided by an embodiment of the present application. When the vehicle is moving in the direction of turning right in the i-th parking operation, it can be known that the vehicle may collide with the right safety line of the parking area, and the i-th maximum moving distance is determined accordingly. Among them, during the parking process, the vehicle can be assumed to move with the minimum turning radius, and the minimum turning radius of the vehicle can be measured in advance. That is, in the embodiment of the present application, the minimum turning radius is a known parameter.

[0130] In this application scenario, the i-th position of the vehicle is v1, that is, the position of the rear axle center of the vehicle, and the position of the right front corner point of the vehicle is w1. When the vehicle is moving in the right turn, since the vehicle moves with the minimum turning radius r, the rear axle center and the right front corner point move on two circles respectively, and the two circles are concentric circles with the center at point o. When the right front corner point of the vehicle moves to the right safety line of the parking area, the i-th parking operation is completed, and the rear axle center of the vehicle is at the i-th target position. The length of the arc between the i-th position v1 and the i-th target position v2 can be calculated to determine the i-th maximum moving distance.

[0131] When the vehicle is turning left and backing up in the i-th parking operation, the vehicle may collide with the left safety line of the parking area first, that is, the left rear corner of the vehicle is located at the left safety line of the parking area when the vehicle is at the i-th target position. Alternatively, the vehicle may collide with the lower safety line of the parking area first, that is, the right rear corner of the vehicle is located at the lower safety line of the parking area when the vehicle is at the i-th target position. Therefore, it is necessary to consider the two collision situations and determine the i-th maximum moving distance with the smaller value of the two maximum moving distances.

[0132] See also Figure 5b , which is a schematic diagram of another parking operation provided by an embodiment of the present application. In this application scenario, when the vehicle turns left and backs up, the left rear corner of the vehicle collides with the left safety line of the parking area. When the left rear corner of the vehicle moves from position w1 to position w2, it collides with the left safety line of the parking area, and then the i-th maximum moving distance of the rear axle center from position v1 in the parking operation is calculated.

[0133] See also Figure 5c , which is a schematic diagram of another parking operation provided by an embodiment of the present application. In this application scenario, when the vehicle turns left and backs up, the right rear corner of the vehicle collides with the lower safety line of the parking area. When the right rear corner of the vehicle moves from position w1 to position w2, it collides with the lower safety line of the parking area, and then the i-th maximum moving distance of the rear axle center from position v1 in the parking operation is calculated.

[0134] Specifically, the i-th maximum moving distance can be determined in the following manner: when the vehicle is at the i-th target position and the right rear corner of the vehicle is located at the lower safety line of the parking area, the lower maximum moving distance is determined based on the i-th position and the i-th target position; when the vehicle is at the i-th target position and the left rear corner of the vehicle is located at the left safety line of the parking area, the left maximum moving distance is determined based on the i-th position and the i-th target position. Then, the lower maximum moving distance is compared with the left maximum moving distance, and the smaller value between the lower maximum moving distance and the left maximum moving distance is determined as the i-th maximum moving distance.

[0135] The following will be combined Figure 5a The illustrated embodiment introduces the principle of determining the i-th maximum moving distance.

[0136] Optionally, a coordinate system may be established with the left front vertex p1 of the parking area as the origin, and the x-axis and y-axis directions may be as follows: Figure 5a As shown, the coordinates of the i-th position v1 of the rear axle center, the coordinates of the position w1 of the right front corner point of the vehicle, and the horizontal coordinate corresponding to the right safety line can be calculated in advance.

[0137] See also Figure 6a As shown, it is a schematic diagram of determining the minimum turning radius provided by an embodiment of the present application. Since the minimum turning radius r of the rear axle center is a known parameter, the distance between the intersection point c of the radius r and the right side boundary of the vehicle and the center v1 of the rear axle is half the width of the vehicle, and the coordinates of v1 are known, the coordinates of the intersection point c can be obtained. The coordinates of w1 are known, the coordinates of the intersection point c are known, the length of cw1 can be calculated, the length of oc is known, and the radius r is perpendicular to the right side boundary of the vehicle, so the minimum turning radius R when the right front corner moves can be calculated.

[0138] See also Figure 6b FIG. 1 is a schematic diagram of determining the maximum moving distance provided by an embodiment of the present application. The heading angle of the vehicle is expressed as ,according to Figure 6b It can be seen that the horizontal coordinate difference between the rear axle center v1 and the center o is r Since the coordinates of the rear axle center v1 are known, the horizontal coordinate O1 of the circle center o can be calculated. The vertical coordinate difference between the rear axle center v1 and the circle center o is r Since the coordinates of the rear axle center v1 are known, the ordinate O2 of the center o can be calculated, and the coordinates of the center O are (O1, O2).

[0139] Then the equation of the circle can be determined based on the coordinates of the center o (O1, O2) and the minimum turning radius R when the right front corner moves. The horizontal coordinate of w2 is the position of the safety line, so the horizontal coordinate of w2 can be known, and w2 is on the circle, so the vertical coordinate of w2 can be determined based on the equation of the circle and the horizontal coordinate of w2.

[0140] After knowing the coordinates of w1 and w2, we can use (x1, y1) to represent the coordinates of w1 and (x2, y2) to represent the coordinates of w2. We can establish simultaneous equations based on the positional relationship between w1, w2 and the center o of the circle: , .

[0141] in, represents the angle between w1 and the x-axis direction, Represents the angle between w2 and the x-axis

[0142] According to the above equation, we can calculate and , we can find the angle between the two ,Right now , represents the angle of vehicle movement. Then the distance moved by the rear axle center v1, i.e. the i-th maximum moving distance, can be expressed as the minimum turning radius r and the moving angle The product of .

[0143] It should be noted that the above process of calculating the maximum moving distance is only an exemplary description and is not limited to the above calculation method. Other methods that can calculate the maximum moving distance are also within the protection scope of this application.

[0144] In a possible implementation, after determining the i-th maximum moving distance, multiple i-th moving distances can be determined based on a preset step length and the i-th maximum moving distance, so that the i+1-th position after the vehicle moves the i-th moving distance can be determined based on each i-th moving distance. Optionally, multiple initial i-th distances can be obtained based on a preset step length. In a specific implementation, the preset step length is used as the initial value as the first initial i-th distance, and then the preset step length is increased each time to obtain an initial i-th distance, so that multiple initial i-th distances can be obtained (that is, the lengths of the multiple initial i-th distances are different, and each initial i-th distance is a multiple of the preset step length), until the initial i-th distance obtained after increasing the preset step length is greater than the i-th maximum moving distance, and the iteration is stopped. For example, the preset step length is first used as the first initial i-th distance. Then, based on the first initial i-th distance, the preset step length is increased to obtain a second initial i-th distance, which is increased successively until the iteration is stopped when the initial i-th distance obtained is greater than the i-th maximum moving distance. All initial i-th distances before the last initial i-th distance (greater than the i-th maximum moving distance) can be retained as multiple i-th moving distances, and then it can be determined whether to retain the last initial i-th distance as the i-th moving distance according to different application scenarios.

[0145] It should be noted that the embodiments of the present application do not limit the specific method for determining the preset step length, and can be determined in combination with the maximum moving distance and the actual application scenario. For example, the minimum moving distance of a vehicle in a single step can be used as the preset step length, and the minimum moving distance of a vehicle in a single step can be understood as the minimum distance that the vehicle can move each time. In other words, the minimum distance that the vehicle can move each time is used as the preset step length.

[0146] In a possible implementation, when the safety line is located at the boundary of the parking area, since the i-th maximum moving distance is determined by the collision with the safety line, and the safety line is located at the boundary of the parking area, when the i-th moving distance of the vehicle is greater than the i-th maximum moving distance, it indicates that the parking area has been exceeded. At this time, it is necessary to delete the last initial i-th distance greater than the i-th maximum moving distance and retain the remaining multiple initial i-th distances. Then, multiple i-th moving distances are determined based on the remaining multiple initial i-th distances and the i-th maximum moving distance.

[0147] Specifically, when the previous initial i-th distance of the last initial i-th distance (the second to last initial i-th distance) is less than the i-th maximum moving distance, the i-th maximum moving distance can be determined as an i-th moving distance, and thus multiple i-th moving distances can be determined based on the remaining multiple initial i-th distances and the i-th maximum moving distances.

[0148] When the last initial i-th distance is equal to the i-th maximum moving distance, the remaining multiple initial i-th distances are determined to be multiple i-th moving distances.

[0149] In a possible implementation, when the safety line is within the parking area, although the last initial i-th distance is greater than the i-th maximum moving distance, the vehicle does not necessarily collide with the boundary of the parking area. In this case, whether to retain the last initial i-th distance can be adjusted by judging whether the vehicle collides with the boundary of the parking area. In this way, the space of the parking area can be maximized, more possible moving distances can be determined, and more candidate parking paths can be obtained. A target parking path that meets user needs can be selected from more candidate parking paths. For example, the number of movements during the parking process can be reduced, and the accuracy of automatic parking can be improved.

[0150] Specifically, when the safety line is within the parking area, the i+1th target position after the vehicle moves based on the last initial i-th distance greater than the i-th maximum moving distance is determined. The process of determining the i+1th target position can refer to the above embodiment and will not be described in detail here. When the vehicle is located at the i+1th target position and the vehicle does not exceed the boundary of the parking area, it indicates that although the vehicle exceeds the safety line, it does not exceed the boundary of the parking area, and the vehicle can be allowed to move, then multiple initial i-th distances are determined as multiple i-th moving distances.

[0151] When the vehicle is located at the i+1th target position and exceeds the boundary of the parking area, it indicates that the last initial i-th distance (the initial i-th distance greater than the i-th maximum moving distance) does not meet the condition, and the process of updating the last initial i-th distance (the initial i-th distance greater than the i-th maximum moving distance) by the preset multiple is repeated until the vehicle is located at the updated i+1th target position and the vehicle is within the boundary of the parking area. That is, the last initial i-th distance (the initial i-th distance greater than the i-th maximum moving distance) is multiplied by the preset multiple to obtain the updated initial i-th distance. Among them, the preset multiple is a preset value less than 1. That is, at this time, the last initial i-th distance is reduced by the preset multiple, and the new i+1th position is determined based on the reduced initial i-th distance. However, the embodiment of the present application does not limit the specific value of the preset multiple. It should be noted that, each time the preset multiple is used to update the last initial i-th distance (the initial i-th distance greater than the i-th maximum moving distance), the preset multiple can be a plurality of different values, and one of the preset multiples is selected to multiply the last initial i-th distance each time the update is performed, and the preset multiple can be a smaller and smaller value during the updating process. That is, the last initial i-th distance (the initial i-th distance greater than the i-th maximum moving distance) is updated in order from large to small.

[0152] Specifically, first, the last initial i-th distance is multiplied by a preset multiple to obtain an updated initial i-th distance. The i+1th target position after the vehicle moves based on the updated initial i-th distance is determined, and it is judged whether the vehicle does not exceed the boundary of the parking area when the vehicle is located at the updated i+1th target position. If it is satisfied, the updated initial i-th distance is retained. Then, the retained original multiple initial i-th distances and the updated initial i-th distance can be determined as all possible i-th moving distances. If it is not satisfied, the last initial i-th distance is continuously multiplied by a new preset multiple, and the subsequent process is repeated, that is, the i+1th target position after the move is obtained based on the re-determined initial i-th distance, and it is judged whether the updated i+1th target position satisfies the boundary of the parking area. If it is satisfied, the updating process is stopped, the updated initial i-th distance is retained, and multiple i-th moving distances are determined based on the updated initial i-th distance and the original multiple initial i-th distances. In this embodiment, by updating the last initial i-th distance by a preset multiple, the i+1-th position between the preset step lengths can be found, which can provide a basis for finding more parking paths.

[0153] Optionally, if after repeatedly performing the last initial i-th distance multiplied by the preset multiple for the preset number of times, the updated i+1th target position still does not satisfy that the vehicle does not exceed the boundary of the parking area, that is, if the vehicle exceeds the boundary of the parking area after moving based on the initial i-th distance after the previous multiple updates, the iterative calculation is stopped. Optionally, the preset number of times can be set as needed, for example, it can be 3 times or 5 times, without specific limitation. In this embodiment, by setting the preset number of times to determine whether the update process continues, the calculation efficiency can be greatly improved.

[0154] The original multiple initial i-th distances represent the multiple initial i-th distances obtained when the preset step size satisfies the stop iteration condition, after removing an initial i-th distance greater than the i-th maximum moving distance, and the remaining multiple initial i-th distances.

[0155] In the above embodiment, by adjusting the initial i-th distance by a preset multiple to determine the moving distance, multiple moving distances can be determined as much as possible, thereby obtaining more candidate parking paths, so that a preferred target parking path can be determined from more candidate parking paths. For example, a parking path with the least number of moves during the parking process can be selected, or a parking path with the highest accuracy can be selected, etc., to meet different needs of users.

[0156] After obtaining multiple i-th moving distances, for each i-th moving distance, the i+1th position after the vehicle moves the i-th moving distance can be determined, and multiple candidate parking paths can be obtained by judging whether the parking condition is satisfied when the vehicle moves to the i+1th position.

[0157] When the vehicle reaches the i+1th position that meets the parking condition, the iteration process is stopped. The i+1th position is the position reached after moving i moving distances. That is, the vehicle moves the first moving distance, the second moving distance, ..., and reaches the i+1th position after moving the i-th moving distance. A candidate parking path can be formed based on the i moving distances associated with the i+1th position. Each i+1th position corresponds to a candidate parking path, and the candidate parking path is composed of the i moving distances to the i+1th position. Since multiple i-th moving distances can be determined for each parking operation, multiple i+1th positions that meet the parking condition can be determined eventually, so that multiple candidate parking paths corresponding to multiple i+1th positions can be obtained. After obtaining multiple candidate parking paths, step S204 "determining a target parking path based on multiple candidate parking paths" will be described in detail in conjunction with the embodiment below.

[0158] When determining the target parking path, different evaluation factors can be determined in combination with different user needs, and the target parking path can be determined from multiple candidate parking paths based on the evaluation factors, so that the subsequent automatic parking system can control the vehicle to automatically park in the parking area based on the target parking path.

[0159] In a possible implementation, evaluation factors such as the number of moves corresponding to each candidate parking path, the error between the i+1th position corresponding to the candidate parking path and the target parking position in the parking area, and the length of the candidate parking path can be determined. Among them, the number of moves corresponding to the candidate parking path can be understood as the value corresponding to i when the iteration is stopped, that is, the number of times the parking lot needs to be rubbed during the parking process. The i+1th position corresponding to the candidate parking path represents the final parking position of the vehicle, and the target parking position can be understood as the ideal position for automatic parking. The accuracy of automatic parking can be measured based on the error between the final parking position of the vehicle and the target parking position. The length of the candidate parking path can be obtained by calculating the sum of the first i moving distances corresponding to the i+1th position. Different target candidate paths can be obtained according to different user needs.

[0160] In a possible implementation, the target parking position of the parking area can be determined in the following manner: when the width of the parking area is greater than a first threshold, the target parking position can be determined based on the width of the parking area, the width of the vehicle, and the vehicle depth of the parking position. The vehicle depth of the parking position can represent the distance between the left edge of the vehicle and the upper boundary of the parking area. In other words, the width of the parking area is relatively large. The embodiment of the present application does not limit the specific value of the first threshold, and it can be set in combination with actual needs. Optionally, the threshold can be set as a multiple of the vehicle width, and the multiple is greater than 1. For example, the first threshold can be set to 1.2 times the vehicle width.

[0161] See also Figure 7a , which is a schematic diagram of a parking method provided by an embodiment of the present application. Specifically, firstly, a first difference between the width of the parking area and half of the width of the vehicle and the vehicle depth of the parking position is calculated. Then, a target parking position is determined based on the first difference. The target parking position can be understood as a position parallel to a target line of the parking space.

[0162] The above process determines the longitudinal coordinate of the target parking position, that is, the longitudinal center of the vehicle coincides with the target line. Optionally, the transverse coordinate of the target parking position can be further determined. That is, the target parking position is determined by the transverse coordinate and the longitudinal coordinate. The target parking position can represent that when the rear axle center of the vehicle is located at the target parking position, the distance between the front boundary of the vehicle and the right safety line of the parking area is equal to the distance between the rear boundary of the vehicle and the left safety line of the parking area. That is, the difference can be obtained by subtracting the length of the vehicle from the distance between the left safety line and the right safety line. Based on half of the difference and the transverse coordinate of the left safety line, the transverse coordinate of the rear boundary of the vehicle is determined. Then, based on the distance between the rear axle center of the vehicle and the rear boundary of the vehicle, the transverse coordinate of the rear axle center of the vehicle, that is, the transverse coordinate of the target parking position, can be determined, so that the target parking position composed of the transverse and longitudinal coordinates can be obtained.

[0163] In a possible implementation, when the width of the parking area is less than the second threshold, the target parking position can be determined based on the width of the parking area, the width of the vehicle, and the safety distance from the lower boundary of the parking area. That is, at this time, the width of the parking area is small, and the embodiment of the present application does not limit the specific value of the second threshold. For example, when the right boundary of the vehicle is parked at the lower safety line of the parking area, the left boundary of the vehicle just coincides with the upper boundary of the parking area. At this time, it can be determined that the width of the parking area is equal to the distance between the lower safety line and the lower boundary of the parking area plus the width of the vehicle, and the second threshold can be determined based on the sum.

[0164] See also Figure 7b , which is a schematic diagram of another parking method provided by an embodiment of the present application. Specifically, firstly, the second difference between the width of the parking area and half of the width of the vehicle and the safety distance between the lower safety line and the lower boundary of the parking area is calculated, and then the target parking position is determined based on the second difference.

[0165] Similarly, it can be known that the above process determines the longitudinal coordinate of the target parking position, that is, the longitudinal center of the vehicle coincides with the target line. Optionally, the horizontal coordinate of the target parking position can be further determined. That is, the target parking position is determined by the horizontal coordinate and the vertical coordinate. The target parking position can represent that when the rear axle center of the vehicle is located at the target parking position, the distance between the front boundary of the vehicle and the right safety line of the parking area is equal to the distance between the rear boundary of the vehicle and the left safety line of the parking area. That is, the difference can be obtained by subtracting the length of the vehicle from the distance between the left safety line and the right safety line. Based on half of the difference and the horizontal coordinate of the left safety line, the horizontal coordinate of the rear boundary of the vehicle is determined. Then, based on the distance between the rear axle center of the vehicle and the rear boundary of the vehicle, the horizontal coordinate of the rear axle center of the vehicle, that is, the horizontal coordinate of the target parking position, can be determined, so that the target parking position composed of the horizontal and vertical coordinates can be obtained.

[0166] It should be noted that the three evaluation factors provided in the above embodiment are only exemplary descriptions and are not limited to the above three forms. Other evaluation factors may also be considered according to the actual application scenario, and the embodiments of the present application do not limit this.

[0167] In a possible implementation, when the user's requirement is to obtain a parking path with the least number of moves, the number of moves corresponding to the candidate parking paths may be used as an evaluation factor to determine the target parking path. That is, after determining the number of moves corresponding to each candidate parking path, the minimum value among multiple numbers of moves may be determined, and the candidate parking path corresponding to the minimum number of moves may be determined as the target parking path.

[0168] In a possible implementation, when the user's requirement is for higher accuracy of automatic parking, the error between the i+1th position corresponding to the candidate parking path and the target parking position in the parking area can be used as an evaluation factor to determine the target parking path. That is, the error between the i+1th position of each candidate parking path and the target parking position in the parking area can be calculated, and then the minimum value of multiple errors can be determined, and the candidate parking path corresponding to the minimum error can be determined as the target parking path.

[0169] In a possible implementation, when the user's requirement is to minimize the parking distance, the length of the candidate parking paths can be used as an evaluation factor to determine the target parking path. That is, the length of each candidate parking path can be calculated, and then the minimum value among multiple lengths can be determined, and the candidate parking path corresponding to the minimum length can be determined as the target parking path.

[0170] Optionally, the embodiment of the present application can also combine the above-mentioned multiple evaluation factors in different ways to determine the target parking path. For example, any two evaluation factors can be combined, or three evaluation factors can be combined, and the priority order can be set for the multiple evaluation factors in combination with user needs. For example, when considering the three evaluation factors in combination, the priority order of the above-mentioned three evaluation factors can be set to give priority to the number of moves corresponding to the candidate parking path, then consider the error between the i+1th position corresponding to the candidate parking path and the target parking position in the parking area, and finally consider the length of the candidate parking path. By combining different evaluation elements to determine the target parking path, different parking needs of users can be met, such as reducing the number of moves for automatic parking and improving the accuracy of automatic parking.

[0171] For example, after all i+1 positions are selected based on parking conditions (e.g., including the heading angle of the vehicle being less than a preset angle), for each i+1 position that meets the parking conditions, the parking path corresponding to the i+1 position is determined by connecting the moving distances associated with the i+1 position, that is, each i+1 position that meets the parking conditions corresponds to a parking path. However, since each parking operation corresponds to a plurality of different moving distances, the number of moves corresponding to the parking paths that meet the parking conditions, the error between the i+1 position and the target parking position in the parking area, and the length of the parking path are different. The user can filter according to different needs. For example, the parking path with the least number of moves can be selected first. When the parking path with the least number of moves is not unique, the parking path with the least number of moves that has been selected can be filtered based on the error between the i+1 position and the target parking position in the parking area.

[0172] In a specific implementation, the number of moves corresponding to each candidate parking path is first determined. The target parking path is determined based on the minimum value among the multiple move times corresponding to the multiple candidate parking paths. Specifically, when there is only one minimum value among the multiple move times, the candidate parking path corresponding to the minimum value can be determined as the target parking path. When there are multiple identical minimum values ​​among the multiple move times, the i+1th position of the candidate parking path corresponding to the multiple identical minimum values ​​is first determined, and then the error between each i+1th position and the target parking position in the parking area is calculated. The target parking path is determined based on the multiple errors. For example, the candidate parking path corresponding to the minimum value among the multiple errors is determined as the target parking path.

[0173] Optionally, when there are multiple identical minimum values ​​among the multiple errors, the lengths of the candidate parking paths corresponding to the multiple minimum errors may be determined, and the candidate parking path corresponding to the minimum value among the multiple lengths may be determined as the target parking path.

[0174] Through the method provided in the embodiment of the present application, multiple different candidate parking paths can be planned, and a target parking path that meets the user's needs can be selected from the multiple candidate parking paths. For example, a candidate parking path with fewer moves during parking can be selected, or a candidate parking path with a parking position closer to the center of the parking area can be selected, or a parking path with the shortest length can be selected, etc., to meet different user needs.

[0175] Based on the above method embodiment, the present application embodiment also provides a method for controlling a vehicle to park. Figure 8 As shown, Figure 8 A flowchart of a method for controlling a vehicle to park is provided in an embodiment of the present application.

[0176] Optionally, the method may be performed by an automatic parking system of the vehicle. The method may include the following steps:

[0177] S801: Determine a target parking path based on the vehicle's position, vehicle parameters, and parking area information.

[0178] The target parking path is determined based on the parking path planning method described in the above method embodiment.

[0179] S802: Controlling the vehicle to park in a parking area based on the target parking path.

[0180] Through the method provided in the embodiment of the present application, after planning and determining the target parking path, the vehicle is controlled to automatically park at the parking area based on the target parking path, which can save parking time, improve parking safety, and meet the different needs of users.

[0181] Based on the above method embodiment, the present application embodiment provides a parking path planning device. Fig. 9 As shown, Fig. 9 A schematic diagram of a parking path planning device provided in an embodiment of the present application.

[0182] The device 900 comprises:

[0183] a moving distance determining unit 901, configured to determine a plurality of i-th moving distances of an i-th parking operation based on an i-th position of the vehicle, vehicle parameters, and parking area information;

[0184] A position determination unit 902, configured to determine, for each i-th moving distance, an i+1th position of the vehicle after the vehicle moves the i-th moving distance;

[0185] an iterative unit 903, configured to update i by using i+1, iteratively perform the above steps until the parking condition is satisfied when the vehicle moves to the i+1th position, determine a candidate parking path based on i moving distances associated with the i+1th position, and thereby obtain a plurality of candidate parking paths based on a plurality of the i+1th positions, wherein i is an integer greater than or equal to 1;

[0186] The path planning unit 904 is configured to determine a target parking path based on the plurality of candidate parking paths.

[0187] In a possible implementation, the moving distance determination unit 901 is specifically used to determine the i-th maximum moving distance of the i-th parking operation based on the i-th position, the vehicle parameters and the parking area information; and determine multiple i-th moving distances based on a preset step size and the i-th maximum moving distance.

[0188] In a possible implementation, the moving distance determination unit 901 is specifically used to determine the i-th target position after the vehicle moves the i-th maximum moving distance, when the vehicle is at the i-th target position, the corner point of the vehicle is located on the safety line of the parking area, and the safety line is determined based on the vertices of the parking area; based on the i-th position and the i-th target position, the i-th maximum moving distance is determined.

[0189] In a possible implementation, the moving distance determining unit 901 is specifically configured to, when the driving direction corresponding to the i-th maximum moving distance is a right turn forward, determine the i-th target position after the vehicle moves the i-th maximum moving distance, and when the vehicle is at the i-th target position, the right front corner point of the vehicle is located at the right safety line of the parking area, and the right safety line is determined based on the vertex on the right side of the parking area; when the driving direction corresponding to the i-th maximum moving distance is a left turn backward, determine the i-th target position after the vehicle moves the i-th maximum moving distance, and when the vehicle is at the i-th target position, the right rear corner point of the vehicle is located at the lower safety line of the parking area, or when the vehicle is at the i-th target position, the left rear corner point of the vehicle is located at the left safety line of the parking area;

[0190] When the driving direction corresponding to the i-th maximum moving distance is turning left and backing up, the moving distance determining unit 901 is specifically used to determine the lower maximum moving distance based on the i-th position and the i-th target position when the vehicle is at the i-th target position and the right rear corner point of the vehicle is located at the lower safety line of the parking area; determine the left maximum moving distance based on the i-th position and the i-th target position when the vehicle is at the i-th target position and the left rear corner point of the vehicle is located at the left safety line of the parking area; and determine the smaller value between the lower maximum moving distance and the left maximum moving distance as the i-th maximum moving distance.

[0191] In a possible implementation, the moving distance determining unit 901 is specifically configured to use the preset step length as an initial value, increase the preset step length each time, obtain multiple initial i-th distances, and stop iteration when the obtained initial i-th distance is greater than the i-th maximum moving distance; when the safety line is located in the parking area, determine the i+1th target position of the vehicle after moving based on the initial i-th distance greater than the i-th maximum moving distance; when the vehicle is located at the i+1th target position and satisfies the requirement that the vehicle does not exceed the boundary of the parking area, determine the multiple initial i-th distances as multiple i-th distances. i moving distance; otherwise, repeatedly executing the process of updating the initial i-th distance greater than the i-th maximum moving distance by using a preset multiple until the vehicle is located at the updated i+1th target position and it is satisfied that the vehicle does not exceed the boundary of the parking area, and determining a plurality of i-th moving distances based on the updated initial i-th distance and the original plurality of initial i-th distances; when the safety line is located at the boundary of the parking area, deleting the initial i-th distance greater than the i-th maximum moving distance, and determining a plurality of i-th moving distances based on the remaining plurality of initial i-th distances and the i-th maximum moving distance.

[0192] In a possible implementation, the path planning unit 904 is specifically configured to determine the target parking path based on at least one of a number of moves corresponding to the candidate parking path, an error between an i+1th position corresponding to the candidate parking path and a target parking position in the parking area, and a length of the candidate parking path.

[0193] In a possible implementation, the path planning unit 904 is specifically configured to determine the number of movements corresponding to each of the candidate parking paths; and determine the target parking path based on a minimum value of a plurality of the number of movements.

[0194] In a possible implementation, the path planning unit 904 is specifically configured to, when there are multiple identical minimum values ​​in the multiple movement times, determine the i+1th position of the candidate parking path corresponding to the multiple identical minimum values; determine the errors between the multiple i+1th positions and the target parking position in the parking area; and determine the target parking path based on the errors.

[0195] In a possible implementation, the method for determining the target parking position includes: when the width of the parking area is greater than a first threshold, determining the target parking position based on the width of the parking area, the width of the vehicle, and the vehicle depth of the parking position; when the width of the parking area is less than a second threshold, determining the target parking position based on the width of the parking area, the width of the vehicle, and a safety distance from a lower boundary of the parking area, and the first threshold is greater than the second threshold.

[0196] In a possible implementation, the path planning unit 904 is specifically configured to calculate a first difference between a width of the parking area and half of a width of the vehicle and a vehicle depth of the parking position; and determine the target parking position based on the first difference;

[0197] The path planning unit 904 is specifically configured to calculate a second difference between the width of the parking area and half the width of the vehicle and a safety distance from a lower boundary of the parking area; and determine the target parking position based on the second difference.

[0198] In a possible implementation, during parallel parking, the parking condition includes: a heading angle of the vehicle is less than a preset angle.

[0199] In a possible implementation, when i is 1, the first position represents any position where the vehicle enters the parking area for the first time.

[0200] In addition, the present application also provides a device for controlling a vehicle to park. Fig.10 As shown, Fig.10 A schematic diagram of a device for controlling a vehicle to park provided in an embodiment of the present application.

[0201] The device 1000 comprises:

[0202] A path determination unit 1001 is used to determine a target parking path based on the vehicle position, vehicle parameters and parking area information; the target parking path is determined based on the parking path planning method described in the above method embodiment;

[0203] The control unit 1002 is configured to control the vehicle to park in the parking area based on the target parking path.

[0204] Based on the above method embodiment and device embodiment, the present application embodiment further provides an electronic device, which will be described below in conjunction with the accompanying drawings.

[0205] See also Fig.11 , Fig.11 A schematic diagram of an electronic device provided in an embodiment of the present application.

[0206] The device 1100 includes: a memory 1101 and a processor 1102;

[0207] The memory 1101 is used to store relevant program codes;

[0208] The processor 1102 is used to call the program code to execute the parking path planning method or the method of controlling the vehicle to achieve parking described in the above method embodiment.

[0209] In addition, an embodiment of the present application further provides a computer-readable storage medium, which is used to store a computer program, and the computer program is used to execute the parking path planning method or the method of controlling a vehicle to achieve parking described in the above method embodiment.

[0210] An embodiment of the present application further provides a computer program product, which includes a computer program / instruction. When the computer program / instruction is executed by a processor, the parking path planning method or the method of controlling a vehicle to achieve parking described in the above method embodiment is implemented.

[0211] It should be noted that the technical features of the higher-level means provided in the embodiments of the present application are clear to those skilled in the art, and the problems to be solved by the higher-level means are also clear. The means for obtaining the corresponding features can be selected by those skilled in the art according to specific implementation requirements. The means provided in this application should not be regarded as a limitation on the solution or as the only means of implementation.

[0212] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can refer to each other. In particular, for the system or device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only exemplary, in which the units or modules described as separate components may or may not be physically separated, and the components displayed as units or modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units, and some or all of the units or modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0213] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the method, device and equipment etc. of various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0214] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0215] It should also be noted that, in this application, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0216] The steps of the method or algorithm described in conjunction with the embodiments disclosed in this application can be implemented directly by hardware, software modules executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0217] The above description of the disclosed embodiments enables professionals and technicians in the field to implement or use the present application. Various modifications to these embodiments will be apparent to professionals and technicians in the field, and the general principles defined in this application can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown in the present application, but will conform to the widest range consistent with the principles and novel features disclosed in the present application.

Claims

1. A parking path planning method, characterized in that: The method comprises: Determining a plurality of i-th moving distances for an i-th parking operation based on an i-th position of the vehicle, vehicle parameters, and parking area information; For each i-th moving distance, determining an i+1-th position of the vehicle after the vehicle moves the i-th moving distance; Updating i by using i+1, iteratively performing the above steps until the vehicle satisfies the parking condition when moving to the i+1th position, determining a candidate parking path based on i moving distances associated with the i+1th position, thereby obtaining a plurality of candidate parking paths based on a plurality of the i+1th positions, wherein i is an integer greater than or equal to 1; Determining a target parking path based on the plurality of candidate parking paths; The determining of a plurality of i-th moving distances of the i-th parking operation based on the i-th position of the vehicle, the vehicle parameters and the parking area information includes: determining an i-th maximum moving distance of an i-th parking operation based on the i-th position, the vehicle parameters, and the parking area information; Based on a preset step length and the i-th maximum moving distance, a plurality of the i-th moving distances are determined.

2. The method according to claim 1, characterized in that The vehicle parameters include four corner points of the vehicle, the parking area information includes four vertices of the parking area, and determining the i-th maximum moving distance of the i-th parking operation based on the i-th position, the vehicle parameters, and the parking area information includes: determining an i-th target position after the vehicle moves the i-th maximum moving distance, wherein a corner point of the vehicle is located on a safety line of the parking area when the vehicle is at the i-th target position, and the safety line is determined based on a vertex of the parking area; Based on the i-th position and the i-th target position, the i-th maximum moving distance is determined.

3. The method according to claim 2, characterized in that The step of determining a plurality of i-th moving distances based on a preset step length and the i-th maximum moving distance comprises: Based on the preset step length, a plurality of initial i-th distances are obtained, and iteration is stopped until the obtained initial i-th distance is greater than the i-th maximum moving distance; When the safety line is located in the parking area, determining the i+1th target position after the vehicle moves based on the initial i-th distance greater than the i-th maximum moving distance; when the vehicle is located at the i+1th target position and satisfies that the vehicle does not exceed the boundary of the parking area, determining multiple initial i-th distances as multiple i-th moving distances; otherwise, repeatedly executing the process of updating the initial i-th distance greater than the i-th maximum moving distance by using a preset multiple until the vehicle is located at the updated i+1th target position and satisfies that the vehicle does not exceed the boundary of the parking area, determining multiple i-th moving distances based on the updated initial i-th distance and the original multiple initial i-th distances; When the safety line is located at the boundary of the parking area, the initial i-th distance greater than the i-th maximum moving distance is deleted, and a plurality of i-th moving distances are determined based on the remaining plurality of initial i-th distances and the i-th maximum moving distance.

4. The method according to claim 1, characterized in that: The determining of a target parking path based on the plurality of candidate parking paths comprises: The target parking path is determined based on at least one of a number of movements corresponding to the candidate parking path, an error between an (i+1)th position corresponding to the candidate parking path and a target parking position in the parking area, and a length of the candidate parking path.

5. The method according to claim 1, characterized in that The determining of a target parking path based on the plurality of candidate parking paths comprises: Determining the number of movements corresponding to each of the candidate parking paths; The target parking path is determined based on a minimum value among a plurality of the movement times.

6. The method according to claim 5, characterized in that The step of determining the target parking path based on a minimum value among the plurality of movement times comprises: When there are multiple identical minimum values ​​among the multiple movement times, determining the i+1th position of the candidate parking path corresponding to the multiple identical minimum values; determining errors between a plurality of the (i+1)th positions and a target parking position within the parking area; Based on the error, the target parking path is determined.

7. The method according to claim 6, characterized in that The method for determining the target parking position includes: When the width of the parking area is greater than a first threshold, determining the target parking position based on the width of the parking area, the width of the vehicle, and the vehicle depth of the parking position; When the width of the parking area is less than a second threshold, the target parking position is determined based on the width of the parking area, the width of the vehicle, and a safety distance from a lower boundary of the parking area, and the first threshold is greater than the second threshold.

8. A parking path planning device, characterized in that: The device comprises: a moving distance determining unit, configured to determine a plurality of i-th moving distances of an i-th parking operation based on an i-th position of the vehicle, vehicle parameters, and parking area information; the moving distance determining unit is specifically configured to determine an i-th maximum moving distance of the i-th parking operation based on the i-th position, the vehicle parameters, and the parking area information; and to determine a plurality of the i-th moving distances based on a preset step length and the i-th maximum moving distance; a position determination unit, for determining, for each i-th moving distance, an i+1th position of the vehicle after the vehicle moves the i-th moving distance; an iterative unit, configured to update i by using i+1, iteratively perform the above steps until the vehicle satisfies the parking condition when moving to the i+1th position, determine a candidate parking path based on i moving distances associated with the i+1th position, and thereby obtain a plurality of candidate parking paths based on a plurality of the i+1th positions, wherein i is an integer greater than or equal to 1; The path planning unit is used to determine a target parking path based on the plurality of candidate parking paths.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method according to any one of claims 1 to 7.

Images