Lateral parking space parking path planning method and system and storage medium

Abstract

The invention relates to a side parking space parking path planning method and system and a storage medium, and belongs to the technical field of automatic parking, and the method comprises the steps: collecting front / rear obstacle information of a target parking space, and determining front / rear boundary points of the target parking space based on the obstacle information; determining parking target position information based on the front / rear boundary point; based on the front / rear boundary point, the parking target position information and the turning posture information of the vehicle, path planning of each parking arc section is carried out; and performing connection straight line segment planning based on each parking arc segment path, and generating a parking path. According to the scheme, the problems that the requirement for obstacle detection accuracy is high and parking path planning is discontinuous in an existing parking path planning scheme are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic parking technology, and in particular to a side parking path planning method, a side parking path planning system and a storage medium. Background Art

[0002] With the rapid development of science and technology, the number of cars has been rising year by year. As the number of vehicles increases, the current traffic pressure and parking pressure are increasing. The number and area of ​​parking lots are increasingly unable to meet the parking needs, making it increasingly difficult to park vehicles in limited parking areas. When users have parking needs, there are more and more parking situations in crowded scenes. For example, common side parking spaces are often set at the edge of traffic roads. Because the total demand for parking is large, even if there are vacant parking spaces, the probability that there are parked vehicles in front and behind the corresponding parking spaces is very high. When parking in this situation, because there are fewer vacant spaces between the front and rear vehicles, there is a risk that vehicles in the parking path often scratch or get stuck with the vehicles in front and behind. In order to solve this problem, some intelligent solutions have emerged. For example, the solution with application number CN202010386906.7 and titled "An obstacle avoidance method and parking path planning system for automatic parking path planning" proposes to take obstacles detected during vehicle parking into consideration in parking planning, and then select several nodes on the parking path trajectory according to the preset step length, calculate the vehicle posture and contour corresponding to different nodes, and then determine whether the vehicle contour overlaps with the surrounding obstacles in the coordinate system to determine whether the node meets the obstacle avoidance requirements. Finally, all nodes that meet the requirements constitute the parking path planning. However, this method has problems such as high reliance on obstacle detection accuracy, discontinuity of the generated parking path planning, and large amount of calculation.

[0003] Other existing solutions are similar to this solution, and all have problems such as high reliance on obstacle detection accuracy and discontinuity in the generated parking path planning. To address this problem, it is necessary to create a new parallel parking path planning method. Summary of the invention

[0004] One of the purposes of the present invention is to provide a method, system and storage medium for parallel parking path planning to solve the problems of high obstacle detection accuracy and discontinuous parking path planning in existing parking path planning schemes.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A first aspect of the present invention provides a method for planning a parking path for a side parking space, the method comprising: collecting front / rear obstacle information of a target parking space, and determining the front / rear boundary points of the target parking space based on the obstacle information; determining the parking target position information based on the front / rear boundary points; planning each parking arc segment path based on the front / rear boundary points, the parking target position information and the turning posture information of the vehicle; planning a connecting straight line segment based on each parking arc segment path to generate a parking path.

[0007] Optionally, collecting the front / rear obstacle information of the target parking space includes: collecting contour information of the front / rear obstacles of the target parking space; and clustering the contour information to obtain clustered contour information.

[0008] Optionally, determining the front / rear boundary points of the target parking space based on the obstacle information includes: calculating the coordinates of the contour boundary points that affect the parking of the current vehicle based on the clustered contour information, and using them as the determined front / rear boundary points of the target parking space; wherein the contour boundary points that affect the parking of the current vehicle are contour vertices of the front / rear obstacles that are directly opposite the target parking space relative to the side line of the current vehicle.

[0009] Optionally, the determining of the parking target position information based on the front / rear boundary point includes: determining the farthest parking position for the target vehicle to be parked in the target parking space based on a preset safety distance between the rear of the vehicle and an obstacle behind the parking space after the current vehicle is parked in the target parking space; determining the closest parking position for the target vehicle to be parked in the target parking space based on a preset safety distance between the head of the vehicle and an obstacle in front of the parking space after the current vehicle is parked in the target parking space; and determining a parking target position interval based on the farthest parking position and the closest parking position as the parking target position information.

[0010] Optionally, the turning posture information of the vehicle includes: vehicle width information of the current vehicle, wheelbase information of the current vehicle, minimum turning radius information of the current vehicle, front overhang distance of the current vehicle, and rear overhang distance of the current vehicle.

[0011] Optionally, the parking is performed based on the front / rear boundary points, the parking target position information and the turning posture information of the vehicle.

[0012] Arc segment path planning, arc segment path planning rules include:

[0013]

[0014]

[0015]

[0016] R w =rb

[0017]

[0018]

[0019]

[0020]

[0021] Among them, R Bl is the turning radius of the front vertex of the current parking space in the left arc segment; R Ar is the turning radius of the rear vertex of the current parking space in the right arc segment; R Jr is the turning radius of the rear vertex opposite to the current parking space in the right arc segment; R w is the turning radius of the inner wheel; R Br is the turning radius of the front vertex of the current parking space in the right arc segment; R Kr is the turning radius of the front vertex on the opposite side of the current parking space in the right arc segment; R Al is the turning radius of the rear vertex of the current parking space in the left arc segment; R Jl is the turning radius of the rear vertex on the opposite side of the current vehicle parking space in the left arc segment; r is the minimum turning radius; b is half of the vehicle width; a is the wheelbase; dfront is the front overhang distance; drear is the rear overhang distance.

[0022] Optionally, the connecting straight line segment planning based on each parking arc segment path to generate a parking path includes: determining the parking posture restriction information of the current vehicle based on a preset safety distance between the current vehicle and the front / rear boundary points of the target parking space and the turning radius of the front vertex of the current vehicle parking space side in the left arc segment; traversing the center of the circle in the parking target position interval based on the arc segment planning rule until the distance between the center of the circle and the front obstacle boundary point is less than the parking posture restriction information, and determining the path information of the rear semi-arc segment; determining the rear semi-arc path segment based on the current parking posture angle, and determining the parking posture restriction information based on the calibration. The method is used to connect the straight line segments and determine the starting point of the straight line segment; based on the preset safety distance between the current vehicle and the front / rear boundary points of the target parking space and the turning radius of the side and rear vertex of the current vehicle parking space in the right circular arc segment, the front semi-circular arc segment posture restriction information is determined; based on the starting point of the straight line segment, the center traversal of the front semi-circular arc segment is performed again until the distance between the center of the circle and the rear obstacle boundary point obtained is greater than the front semi-circular arc segment posture restriction information, and the front semi-circular arc segment path information is obtained; the front semi-circular arc segment path information, the straight line segment and the rear semi-circular arc segment path information are combined as the parking path.

[0023] Optionally, the method further includes: automatically controlling the vehicle to perform steering wheel steering and gear shifting operations, and parking the vehicle into the target parking space along the parking path; after completing the parking of the vehicle, verifying whether the current vehicle is in a preset position; if not, adjusting the current vehicle posture until it reaches the preset position; if so, automatically entering the parking state.

[0024] A second aspect of the present invention provides a parallel parking path planning system, the parallel parking path planning system comprising: a collection unit, used to collect front / rear obstacle information of a target parking space, and determine the front / rear boundary points of the target parking space based on the obstacle information; a processing unit, used to determine the parking target position information based on the front / rear boundary points; a planning stage, used to plan each parking arc segment path based on the front / rear boundary points, the parking target position information and the turning posture information of the vehicle; and a path generation stage, used to plan the connecting straight line segments based on each parking arc segment path to generate a parking path.

[0025] A third aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, enables the computer to execute the above-mentioned parallel parking path planning method.

[0026] Beneficial effects of the present invention:

[0027] 1) The solution of the present invention only needs to collect the contour information of the obstacles in front and behind the target parking space, and the boundary points can be determined based on the contour information. The accuracy requirement for the complete contour of the obstacle is not high, so that the corresponding contour recognition calculation amount is smaller and the response speed is higher;

[0028] 2) Based on the determined boundary points and the expected point where the current vehicle enters the target parking space, segmented path planning is performed. First, the arc segment planning of parking is performed to adapt to the current vehicle during parking to avoid collision with front and rear obstacles;

[0029] 3) Finally, the straight line segments are connected based on the planned arc segments to ensure the continuity of the planned path and to ensure that the entire parking path is a complete and safe route generated based on the current vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A flowchart of the steps of a method for planning a parallel parking path provided by an embodiment of the present invention;

[0031] Figure 2 A side parking scene diagram provided in one embodiment of the present invention;

[0032] Figure 3 A schematic diagram of parking path planning provided by an embodiment of the present invention;

[0033] Figure 4 A flowchart of a method for planning a path for a side parking space provided in one embodiment of the present invention;

[0034] Figure 5 A system structure diagram of a parallel parking path planning system provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0036] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0037] With the rapid development of science and technology, the number of cars has been rising year by year. As the number of vehicles increases, the current traffic pressure and parking pressure are increasing. The number and area of ​​parking lots are increasingly unable to meet the parking needs, making it increasingly difficult to park vehicles in limited parking areas. When users have parking needs, there are more and more parking situations in crowded scenes. For example, common side parking spaces are often set at the edge of traffic roads. Because the total demand for parking is large, even if there are vacant parking spaces, the probability that there are parked vehicles in front and behind the corresponding parking spaces is very high. When parking in this situation, because there are fewer vacant spaces between the front and rear vehicles, there is a risk that vehicles in the parking path often scratch or get stuck with the vehicles in front and behind. In order to solve this problem, some intelligent solutions have emerged. For example, the solution with application number CN202010386906.7 and titled "An obstacle avoidance method and parking path planning system for automatic parking path planning" proposes to take obstacles detected during vehicle parking into consideration in parking planning, and then select several nodes on the parking path trajectory according to the preset step length, calculate the vehicle posture and contour corresponding to different nodes, and then determine whether the vehicle contour overlaps with the surrounding obstacles in the coordinate system to determine whether the node meets the obstacle avoidance requirements. Finally, all nodes that meet the requirements constitute the parking path planning. However, this method has problems such as high reliance on obstacle detection accuracy, discontinuity of the generated parking path planning, and large amount of calculation.

[0038] For example, the solution with application number CN201910220833.1 and titled "An automatic parking path planning method, system and process" discloses a method of continuously adjusting and optimizing the initial planned parking path by judging whether the vehicle contour collides with surrounding obstacles to ultimately find an optimal parking path. However, this method relies heavily on the accuracy of surrounding obstacle detection and requires huge computational effort.

[0039] Other existing solutions are similar to the above-mentioned solutions, and all have the problems of great dependence on obstacle detection accuracy and discontinuity in the generated parking path planning. To address this problem, the solution of the present invention proposes a new parking path planning method for side parking spaces. The solution of the present invention only needs to collect the contour information of the obstacles in front and behind the target parking space, and determine the boundary points based on the contour information. The accuracy requirement for the complete contour of the obstacle is not high, so that the corresponding contour recognition calculation amount is smaller and the response speed is higher; based on the determined boundary points and the expected point where the current vehicle enters the target parking space, segmented path planning is performed, and firstly, arc segment planning for parking is performed to adapt to the current vehicle in the parking process to avoid collision with the front and rear obstacles; finally, straight line segments are connected based on the planned arc segments to ensure the continuity of the planned path and to ensure that the overall parking path is a complete and safe route generated based on the current vehicle.

[0040] like Figure 1 According to a first aspect of the present invention, a method for planning a parking path for a parallel parking space is provided, the method comprising:

[0041] Step S10: collecting the front / rear obstacle information of the target parking space, and determining the front / rear boundary points of the target parking space based on the obstacle information.

[0042] Specifically, when the parking path is planned in the solution of the present invention, it is not necessary to accurately detect the complete outline of the fault object, but only the boundary point information that mainly affects the parking path needs to be understood. Figure 2 As shown, it shows a common side vacant parking space. There are obstacles in front and behind the parking space. The obstacles can be other vehicles that have been parked, or they can be road blockage information, other stacked objects, etc. Then, when a vehicle wants to park in the target parking space, the main boundary points that affect the parking of the vehicle are the outer boundary vertices of the two obstacles in front and behind. During the parking process, it is easy to collide with these two vertices. Based on this, the solution of the present invention only needs to obtain the coordinates of these two vertices to control the main collision risk points.

[0043] Preferably, collecting obstacle information in front of / behind the target parking space includes: collecting contour information of obstacles in front of / behind the target parking space; and clustering the contour information to obtain clustered contour information.

[0044] In one possible implementation, the parking space information is constructed based on FreeSpace (the area where the car can drive) and cluster (clustering) clustering information. Among them, FreeSpace is essentially semantic segmentation, which is generally of two types, namely vector envelope representation, 360 or 720 points in the polar coordinate system, which is used visually in most cases. The advantage is that the msgsize is small enough, but the disadvantage is that it cannot express the passable conditions behind the obstruction. The other is grid representation, which uses multiple lasers and has a large amount of data, but rich representations. It can express the passable conditions behind the obstruction and is used for complex planning a-star search. It is widely used in the field of autonomous driving. The solution of the present invention constructs the target parking space information based on FreeSpace, and obtains the corresponding boundary point information by identifying the front and rear obstacle information.

[0045] Specifically, based on the clustered contour information, the coordinates of the contour boundary points that affect the parking of the current vehicle are calculated as the front / rear boundary points of the determined target parking space; wherein the contour boundary points that affect the parking of the current vehicle are the contour vertices of the front / rear obstacles facing the target parking space relative to the side line of the current vehicle.

[0046] In the embodiment of the present invention, Figure 3 , which describes the possible path information of the current vehicle parking into the target parking space. There are obstacles in front and behind the target parking space. After clustering, the two vertices on the boundary side of the front and rear obstacles are used as the boundary points of the target parking space, namely (POX, POY) and (P1X, P1Y).

[0047] Step S20: determining parking target position information based on the front / rear boundary point.

[0048] Specifically, based on a preset safety distance between the rear of the current vehicle and the obstacle behind the parking space after the current vehicle has parked in the target parking space, the farthest parking position for the target vehicle to be parked in the target parking space is determined; based on a preset safety distance between the head of the current vehicle and the obstacle in front of the parking space after the current vehicle has parked in the target parking space, the closest parking position for the target vehicle to be parked in the target parking space is determined; based on the farthest parking position and the closest parking position, a parking target position interval is determined as parking target position information.

[0049] In the embodiment of the present invention, in order to reduce the risk of collision, after the vehicle is parked in the parking space, it is still necessary to ensure that there is a certain safety distance between the current vehicle and the front and rear obstacles to avoid the risk of scratches caused by the movement of the vehicle or the movement of the front and rear obstacles. Based on this, the safety interval range after the current vehicle is parked in the target parking space can be obtained through the predetermined front and rear safety distances. When the parking path is subsequently planned, it is necessary to ensure that the vehicle is parked within the safety interval range.

[0050] Step S30: planning paths for each parking arc segment based on the front / rear boundary points, the parking target position information and the turning posture information of the vehicle.

[0051] Specifically, the turning posture information of the vehicle includes: vehicle width information of the current vehicle, wheelbase information of the current vehicle, minimum turning radius information of the current vehicle, front overhang distance of the current vehicle, and rear overhang distance of the current vehicle.

[0052] In a possible implementation, when the function is activated, the sensors arranged on the vehicle body will detect surrounding obstacles, provide information on the clustering of the obstacle contours, and calculate the front boundaries P1X, P1Y and rear boundaries P0X, P0Y of the front and rear obstacles based on the obstacle clustering information. This parking space information can avoid collisions when the parking path is subsequently planned. When the vehicle is planning to enter the warehouse, in order to avoid the rear end of the vehicle colliding with the front obstacle, the safety distance S between the left rear corner of the vehicle, which is most likely to collide with the obstacle vehicle during the first arc of the entry, must be retained from the obstacle vehicle; similarly, in order to avoid the head of the vehicle colliding with the front obstacle, the safety distance S between the left front corner of the vehicle, which is most likely to collide with the obstacle vehicle during the last arc of the entry, must be retained from the obstacle vehicle. In addition, in order to ensure that the rear end of the vehicle collides with the rear obstacle during the last arc of the entry, the safety distance S between the rear end of the vehicle and the rear boundary must be considered when planning the end point of the path.

[0053] Furthermore, the path planning of each parking arc segment is performed based on the front / rear boundary point, the parking target position information and the turning posture information of the vehicle, and the arc segment path planning rules include:

[0054]

[0055]

[0056]

[0057] R w =rb

[0058]

[0059]

[0060]

[0061]

[0062] Among them, R Bl is the turning radius of the front vertex of the current parking space in the left arc segment; R Ar is the turning radius of the rear vertex of the current parking space in the right arc segment; RJr is the turning radius of the rear vertex opposite to the current parking space in the right arc segment; R w is the turning radius of the inner wheel; R Br is the turning radius of the front vertex of the current parking space in the right arc segment; R Kr is the turning radius of the front vertex on the opposite side of the current parking space in the right arc segment; R Al is the turning radius of the rear vertex of the current parking space in the left arc segment; R Jl is the turning radius of the rear vertex on the opposite side of the current vehicle parking space in the left arc segment; r is the minimum turning radius; b is half of the vehicle width; a is the wheelbase; dfront is the front overhang distance; drear is the rear overhang distance.

[0063] Preferably, the above scheme is based on Figure 3 For the parking plan of the parking space type shown, the target parking space is on the right side of the current vehicle's travel direction. If the target parking space is on the left side of the current vehicle's travel direction, it is only necessary to mirror the plan, that is, in this implementation, the first arc segment is the left arc segment. In the case of a right parking space, the first arc segment is the right arc segment.

[0064] Step S40: planning connecting straight line segments based on the parking arc segments to generate a parking path.

[0065] Specifically, the parking posture restriction information of the current vehicle is determined based on the preset safety distance between the current vehicle and the front / rear boundary points of the target parking space and the turning radius of the front vertex of the current vehicle parking space side in the left arc segment; the center of the circle is traversed in the parking target position interval based on the arc segment planning rule until the distance between the center of the circle and the front obstacle boundary point is less than the parking posture restriction information, and the path information of the rear semi-arc segment is determined; based on the current parking posture angle, the rear semi-arc path segment is determined, and the straight line segment is connected based on the calibration to determine the starting point of the straight line segment ; Determine the front semi-arc segment posture restriction information of the current vehicle based on the preset safety distance between the current vehicle and the front / rear boundary points of the target parking space and the turning radius of the rear vertex of the current vehicle parking space in the right circular arc segment; Based on the starting point of the straight line segment, perform the traversal of the center of the front semi-arc segment again until the distance between the center of the circle and the rear obstacle boundary point is greater than the front semi-arc segment posture restriction information, and obtain the front semi-arc segment path information; Combine the front semi-arc segment path information, the straight line segment and the rear semi-arc segment path information as the parking path.

[0066] In a possible implementation, Figure 4, firstly, the end position of the path planning can be calculated. The end point of the path (endx, endy) can be calculated based on the safe distance between the rear end of the vehicle and the rear boundary; then the end posture angle of the vehicle needs to be calculated. The posture angle calculation can be calculated by traversal. Different posture angles correspond to different centers of circles. By keeping the distance between the center of the circle and (P1X, P1Y) greater than RBl+S, the end point and the end posture angle of the path planning can be finally calculated. The end point, end posture angle and center of the path planning calculated by the above method ensure that the head of the vehicle will not collide with the front obstacle when the vehicle enters the warehouse. Then the slope of the straight line of the path planning can be obtained by calibration. Then the turning radius and center of the first arc are also obtained by traversal. The center of the traversal can be calculated by traversing the end point of the straight line and the starting point of the vehicle parking into the warehouse. Then, by ensuring that the distance between the traversal center of the circle and (P1X, P1Y) is greater than RAr+S, the final center of the circle that ensures that the rear end of the vehicle will not collide with the front obstacle can be obtained. Finally, the turning radius is obtained by calculating the distance between the center of the circle and the end point of the straight line.

[0067] Preferably, the method further includes: automatically controlling the vehicle to perform steering wheel steering and gear shifting operations, and parking the vehicle into the target parking space along the parking path; after completing the parking of the vehicle, verifying whether the current vehicle is in a preset position; if not, adjusting the current vehicle posture until it reaches the preset position; if so, automatically entering the parking state.

[0068] like Figure 5 According to a second aspect of the present invention, a system for planning a parking path for a parallel parking space is provided, the system comprising: a collection unit for collecting information about front / rear obstacles of a target parking space and determining front / rear boundary points of the target parking space based on the obstacle information; a processing unit for determining parking target position information based on the front / rear boundary points; a planning stage for planning paths for each parking arc segment based on the front / rear boundary points, the parking target position information and the turning posture information of the vehicle; and a path generation stage for planning connecting straight line segments based on the paths of each parking arc segment to generate a parking path.

[0069] In a possible implementation, the acquisition unit includes 4 high-definition global cameras + 12 ultrasonic radars + 5 millimeter-wave radars + 1 front-view camera. The acquisition unit senses the environment around the vehicle and provides FreeSpace and cluster information for obstacles. Based on the obstacle cluster information, the front and rear boundaries of the front and rear obstacles can be calculated.

[0070] The embodiment of the present invention further provides a computer-readable storage medium, on which instructions are stored, which, when executed on a computer, enable the computer to execute the above-mentioned parallel parking path planning method.

[0071] Those skilled in the art will understand that all or part of the steps in the method for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for making a single-chip microcomputer, a chip or a processor (processor) perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0072] The optional embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the technical concept of the embodiments of the present invention, the technical scheme of the embodiments of the present invention can be subjected to a variety of simple modifications, and these simple modifications all belong to the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0073] In addition, various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. A method for planning a parking path for a side parking space, characterized in that: The parallel parking space parking path planning method comprises: Collecting front / rear obstacle information of the target parking space, and determining the front / rear boundary points of the target parking space based on the obstacle information; determining parking target position information based on the front / rear boundary point; Performing path planning for each parking arc segment based on the front / rear boundary point, the parking target position information and the turning posture information of the vehicle; Based on the paths of each parking arc segment, connecting straight line segments are planned to generate a parking path.

2. The method for parallel parking path planning according to claim 1, characterized in that: The collecting of the front / rear obstacle information of the target parking space includes: Collect the outline information of the obstacles in front and behind the target parking space; The profile information is clustered to obtain clustered profile information.

3. The method for parallel parking path planning according to claim 2, characterized in that: The determining the front / rear boundary point of the target parking space based on the obstacle information includes: Based on the clustered contour information, coordinates of contour boundary points that affect the current parking of the vehicle are calculated as the front / rear boundary points of the determined target parking space; wherein, The contour boundary points that affect the parking of the current vehicle are contour vertices of the front / rear obstacles that face the side line of the current vehicle in the target parking space.

4. The method for parallel parking path planning according to claim 1, characterized in that: The determining of the parking target position information based on the front / rear boundary point includes: Determine the farthest parking position of the target vehicle in the target parking space based on the preset safety distance between the rear of the vehicle and the obstacle behind the parking space after the current vehicle is parked in the target parking space; Determine the closest parking position for the target vehicle to park in the target parking space based on the preset safety distance between the head of the vehicle and the obstacle in front of the parking space after the current vehicle parks in the target parking space; A parking target position interval is determined based on the farthest parking position and the closest parking position as parking target position information.

5. The method for parallel parking path planning according to claim 1, characterized in that: The turning posture information of the vehicle includes: The vehicle width information of the current vehicle, the wheelbase information of the current vehicle, the minimum turning radius information of the current vehicle, the front overhang distance of the current vehicle, and the rear overhang distance of the current vehicle.

6. The method for parallel parking path planning according to claim 5, characterized in that: In the step of performing path planning for each parking arc segment based on the front / rear boundary point, the parking target position information and the turning posture information of the vehicle, the arc segment path planning rules include: R w =r-b Among them, R Bl is the turning radius of the front vertex of the current parking space in the left arc segment; R Ar is the turning radius of the rear vertex of the current parking space in the right arc segment; R Jr is the turning radius of the rear vertex on the opposite side of the current parking space of the vehicle in the right arc segment; R w is the turning radius of the inner wheel; R Br is the turning radius of the front vertex of the current parking space in the right arc segment; R Kr is the turning radius of the front vertex on the opposite side of the current parking space of the vehicle in the right arc segment; R Al is the turning radius of the rear vertex of the current parking space in the left arc segment; R Jl is the turning radius of the rear vertex on the opposite side of the current parking space of the vehicle in the left arc segment; r is the minimum turning radius; b is half of the vehicle width; a is the wheelbase; dfront is the front overhang distance; drear is the rear overhang distance.

7. The method for parallel parking path planning according to claim 4 or 6, characterized in that: The step of planning the connecting straight line segments based on the parking arc segments to generate the parking path includes: Determine the parking posture restriction information of the current vehicle based on the preset safety distance between the current vehicle and the front / rear boundary point of the target parking space and the turning radius of the front vertex of the parking space side of the current vehicle in the left arc segment; Based on the arc segment planning rule, the center of the circle is traversed in the parking target position interval until the distance between the center of the circle and the boundary point of the front obstacle is less than the parking posture restriction information, and the path information of the second half of the arc segment is determined; Based on the current parking posture angle, determine the rear semicircular arc path segment, connect the straight line segment based on the calibration method, and determine the starting point of the straight line segment; Determine the front half arc segment posture restriction information of the current vehicle based on the preset safety distance between the current vehicle and the front / rear boundary point of the target parking space and the turning radius of the side rear vertex of the current vehicle parking space in the right arc segment; Based on the starting point of the straight line segment, the center traversal of the first half arc segment is performed again until the distance between the center of the circle and the boundary point of the rear obstacle is greater than the posture restriction information of the first half arc segment, and the path information of the first half arc segment is obtained; The path information of the first semicircular arc segment, the straight line segment and the path information of the second semicircular arc segment are combined to form a parking path.

8. The method for parallel parking path planning according to claim 1, characterized in that: The method further comprises: Automatically controlling the vehicle to perform steering wheel steering and gear shifting operations, and parking the vehicle into a target parking space along the parking path; After completing the parking, verify whether the vehicle is currently in the preset position; If not, adjust the current vehicle posture until the preset position is reached; If so, the vehicle automatically enters parking mode.

9. A parallel parking path planning system, characterized in that: The parallel parking path planning system includes: A collection unit, used to collect the front / rear obstacle information of the target parking space, and determine the front / rear boundary points of the target parking space based on the obstacle information; a processing unit, configured to determine parking target position information based on the front / rear boundary point; The planning stage is used to plan the paths of each parking arc segment based on the front / rear boundary points, the parking target position information and the turning posture information of the vehicle; The path generation stage is used to plan the connecting straight line segments based on the paths of each parking arc segment to generate a parking path.

10. A computer-readable storage medium having instructions stored thereon, which, when executed on a computer, enables the computer to execute the method for parallel parking path planning according to any one of claims 1 to 8.

Images