An unmanned autonomous parking method and terminal based on reeds shepp curve

By using the ReedsShepp curve algorithm, the corner points of the autonomous vehicle are calculated and the route is planned in segments, which solves the problem of autonomous vehicles avoiding impassable areas when parking, and realizes safe automatic parking.

CN114701489BActive Publication Date: 2025-11-21JIANGSU SHENGHAI INTELLIGENT TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202210381499.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-04-12
Publication Date
2025-11-21
Estimated Expiration
2042-04-12

AI Technical Summary

Technical Problem

When autonomous vehicles attempt to park themselves, they often struggle to safely avoid impassable areas and generate parking routes.

Method used

The ReedsShepp curve algorithm is used to calculate the corner points through which vehicles can safely pass by by obtaining the location information of parking spaces and impassable areas. The route AB, BC, and CD are planned in segments to generate parking routes that avoid impassable areas.

Benefits of technology

It enables driverless vehicles to safely and automatically generate parking routes when encountering impassable areas, ensuring the safety and efficiency of the parking process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114701489B_ABST
    Figure CN114701489B_ABST
Patent Text Reader

Abstract

The application discloses an unmanned autonomous parking method and terminal based on a Reeds Shepp curve, acquires the position D and orientation of a parking space, acquires the position, length and width of an impassable area, and calculates a first corner point B and a second corner point C that can be safely passed by a vehicle according to the vehicle width, the position and the length and width of the impassable area; generates routes AB, BC and CD by using a Reeds Shepp curve algorithm according to the first corner point B, the direction of a vector BC, the second corner point C, the position D of the parking space, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle, so as to obtain a parking route; and drives to the parking space and parks according to the parking route, so that the unmanned tracing driving automatic parking is realized by automatically generating a safe parking route that avoids the impassable area by means of segmented planning when parking is needed.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned driving, in particular to an unmanned autonomous parking method and terminal based on ReedsShepp curve. BACKGROUND

[0002] Unmanned driving car is the main trend of future development in the field of automobile, in unmanned driving, unmanned car needs to autonomously complete various tasks, such as unmanned tracking driving, unmanned obstacle avoidance driving, unmanned obstacle driving, etc. Unmanned autonomous parking is also an important topic in unmanned driving. SUMMARY

[0003] The technical problem solved by the present application is to provide an unmanned autonomous parking method and terminal based on ReedsShepp curve, which can generate a parking route to avoid impassable areas and safely park.

[0004] In order to solve the above technical problems, the technical scheme adopted by the present application is:

[0005] An unmanned autonomous parking method based on ReedsShepp curve, comprising the steps of:

[0006] S1, obtaining the position D and orientation of the parking space;

[0007] S2, obtaining the position, length and width of the impassable area, and calculating the first corner point B and the second corner point C that the vehicle can safely pass through according to the vehicle width, the position and the length and width of the impassable area;

[0008] S3, generating route AB, BC and CD by using ReedsShepp curve algorithm according to the first corner point B, the direction of vector BC, the second corner point C, the position D of the parking space, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle, so as to obtain the parking route;

[0009] S4, tracking driving to the parking space according to the parking route and parking.

[0010] In order to solve the above technical problems, another technical scheme adopted by the present application is:

[0011] An unmanned autonomous parking terminal based on ReedsShepp curve, comprising a processor, a memory and a computer program stored in the memory and executable on the processor, the processor executes the computer program to realize the following steps:

[0012] S1, obtaining the position D and orientation of the parking space;

[0013] S2, acquire the position, length and width of the impassable area, and calculate the first corner point B and the second corner point C that the vehicle can safely pass through according to the vehicle width, the position and the length and width of the impassable area;

[0014] S3, generate the route AB, BC and CD by using the Reeds Shepp curve algorithm according to the first corner point B, the direction of the vector BC, the second corner point C, the position D of the parking space, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle, so as to obtain the parking route;

[0015] S4, drive to the parking space according to the parking route and park.

[0016] The application has the beneficial effects that the unmanned autonomous parking method and terminal based on the Reeds Shepp curve can automatically generate a safe parking route that avoids the impassable area by the way of segmented planning when parking is needed, and realize the automatic parking of unmanned tracing driving. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 It is a flow chart of the unmanned autonomous parking method based on the Reeds Shepp curve of the embodiment of the application;

[0018] Figure 2 It is a structure diagram of the unmanned autonomous parking terminal based on the Reeds Shepp curve of the embodiment of the application;

[0019] Figure 3 It is a route planning schematic diagram of the unmanned autonomous parking method based on the Reeds Shepp curve of the embodiment of the application;

[0020] REFERENCE NUMERALS:

[0021] 1, an unmanned autonomous parking terminal based on the Reeds Shepp curve; 2, a processor; 3, a memory. DETAILED DESCRIPTION

[0022] In order to explain the technical content, the achieved purposes and effects of the application in detail, the following will be explained in combination with the embodiments and the drawings.

[0023] Please refer to Figure 1 and Figure 3 An unmanned autonomous parking method based on the Reeds Shepp curve, comprising the steps of:

[0024] S1, acquiring the position D and the orientation of the parking space;

[0025] S2, acquire the position, length and width of the impassable area, and calculate a first corner point B and a second corner point C that the vehicle can safely pass through according to the vehicle width, the position and the length and width of the impassable area;

[0026] S3, generate a route AB, BC and CD by using a Reeds Shepp curve algorithm according to the first corner point B, the direction of the vector BC, the second corner point C, the position D of the parking space, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle, so as to obtain a parking route;

[0027] S4, drive to the parking space according to the parking route and park.

[0028] As can be seen from the above description, the beneficial effects of the present application are that the unmanned autonomous parking method and terminal based on the Reeds Shepp curve can automatically generate a safe parking route that avoids the impassable area by means of segmented planning when parking is needed, and realize unmanned tracing driving automatic parking.

[0029] Further, the step S1 and the step S2 further comprise a step:

[0030] S11, input the position A of the vehicle, the minimum turning radius, the heading angle, the position D of the parking space and the orientation of the parking space into the Reeds Shepp curve algorithm to obtain a path AD;

[0031] S12, judge whether there is an impassable area within a preset distance of the path AD, if there is the impassable area, enter the step S2, otherwise, drive to the parking space along the path AD and park, and no subsequent steps are executed.

[0032] As can be seen from the above description, before the generation of the obstacle-avoiding parking route, the route AD from the position A of the vehicle to the position D of the parking space is generated first, and only in the case that it is judged that there is an impassable area within a preset range of the route AD which may affect the vehicle driving, the subsequent generation of the obstacle-avoiding parking route is performed, otherwise, the tracing driving and parking are directly performed according to the route AD.

[0033] Further, the step S2 is specifically:

[0034] S21, acquire the position O of the center point of the impassable area, the east-west direction span and the north-south direction span, establish a rectangular frame diagram circumscribed around the impassable area on a map according to the position O, the east-west direction span and the north-south direction span, and compare the east-west direction span and the north-south direction span;

[0035] S22, if the east-west span is greater than the north-south span, it is determined whether the position O is located on the east side or the west side of the path AD, if it is located on the west side of the path AD, two corner points on the east side of the rectangular frame diagram are selected, and the first corner point B and the second corner point C are obtained by translating eastward according to the vehicle width, if it is located on the east side of the path AD, two corner points on the west side of the rectangular frame diagram are selected, and the first corner point B and the second corner point C are obtained by translating westward according to the vehicle width;

[0036] S23, if the east-west span is less than the north-south span, it is determined whether the position O is located on the south side or the north side of the path AD, if it is located on the south side of the path AD, two corner points on the north side of the rectangular frame diagram are selected, and the first corner point B and the second corner point C are obtained by translating northward according to the vehicle width, if it is located on the north side of the path AD, two corner points on the south side of the rectangular frame diagram are selected, and the first corner point B and the second corner point C are obtained by translating southward according to the vehicle width;

[0037] The distance between the first corner point B and the vehicle is less than the distance between the second corner point C and the vehicle.

[0038] From the above description, we establish a frame diagram that circumscribes the impassable area according to the horizontal and vertical lengths of the impassable area, and select which side of the impassable area to bypass the impassable area according to which side of the path AD the impassable area is located, so that the subsequent safe parking route is the shortest.

[0039] Further, the step S3 is specifically:

[0040] S31, according to the first corner point B, the direction of the vector BC, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle, the ReedsShepp curve algorithm is used to obtain the route AB;

[0041] S32, according to the first corner point B, the direction of the vector BC, the minimum turning radius of the vehicle and the second corner point C, the ReedsShepp curve algorithm is used to obtain the route BC;

[0042] S33, according to the second corner point C, the direction of the vector BC, the minimum turning radius of the vehicle, the position of the parking space and the orientation, the ReedsShepp curve algorithm is used to obtain the route CD;

[0043] S34, the route AB, the route BC and the route CD are connected to obtain the parking route.

[0044] From the above description, according to the determined first corner point B and second corner point C, the route is generated in three segments by using the Reeds Shepp curve algorithm: route AB, route BC and route CD, and the three generated segments are spliced to obtain the final parking route A->B->C->D which can safely bypass the impassable area.

[0045] Please refer to Figure 2 An unmanned autonomous parking terminal based on Reeds Shepp curve, comprising a processor, a memory and a computer program stored in the memory and executable on the processor, and the processor implements the following steps when executing the computer program:

[0046] S1, obtaining the position D and orientation of the parking space;

[0047] S2, obtaining the position, length and width of the impassable area, and calculating the first corner point B and the second corner point C which can be safely passed by the vehicle according to the vehicle width, the position and the length and width of the impassable area;

[0048] S3, according to the first corner point B, the direction of vector BC, the second corner point C, the position D of the parking space, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle, the route AB, BC and CD are generated by using the Reeds Shepp curve algorithm, thereby obtaining the parking route;

[0049] S4, according to the parking route, trace driving to the parking space and parking.

[0050] From the above description, the beneficial effects of the present application are that the unmanned autonomous parking method and terminal based on Reeds Shepp curve can automatically generate a safe parking route which avoids the impassable area by segmented planning when parking is needed, and realize unmanned trace driving automatic parking.

[0051] Further, the steps S1 and S2 further comprise the following steps:

[0052] S11, inputting the position A of the vehicle, the minimum turning radius, the heading angle, the position D of the parking space and the orientation of the parking space into the Reeds Shepp curve algorithm to obtain the path AD;

[0053] S12, judging whether there is an impassable area within a predetermined distance of the path AD, if the impassable area exists, entering step S2, otherwise, trace driving to the parking space along the path AD and parking, and no longer executing the subsequent steps.

[0054] From the above description, it can be seen that before the generation of the obstacle-avoiding parking route, the route AD from the vehicle position A to the parking space D is generated first. Only when it is judged that there is an impassable area in the preset range of the route AD which may affect the driving of the vehicle, the subsequent generation of the obstacle-avoiding parking route is performed, otherwise the route tracing driving and parking are directly performed according to the route AD.

[0055] Further, the step S2 is specifically:

[0056] S21, the position O of the center point of the impassable area, the east-west direction span and the north-south direction span are obtained, and a rectangular frame diagram circumscribed by the impassable area is established on the map according to the position O, the east-west direction span and the north-south direction span, and the east-west direction span and the north-south direction span are compared;

[0057] S22, if the east-west direction span is greater than the north-south direction span, it is judged whether the position O is located on the east side or the west side of the path AD, if it is located on the west side of the path AD, two corner points on the east side of the rectangular frame diagram are selected and translated eastward according to the vehicle width to obtain the first corner point B and the second corner point C, if it is located on the east side of the path AD, two corner points on the west side of the rectangular frame diagram are selected and translated westward according to the vehicle width to obtain the first corner point B and the second corner point C;

[0058] S23, if the east-west direction span is less than the north-south direction span, it is judged whether the position O is located on the south side or the north side of the path AD, if it is located on the south side of the path AD, two corner points on the north side of the rectangular frame diagram are selected and translated northward according to the vehicle width to obtain the first corner point B and the second corner point C, if it is located on the north side of the path AD, two corner points on the south side of the rectangular frame diagram are selected and translated southward according to the vehicle width to obtain the first corner point B and the second corner point C;

[0059] The distance between the first corner point B and the vehicle is less than the distance between the second corner point C and the vehicle.

[0060] From the above description, we establish a frame diagram circumscribed by the impassable area according to the horizontal and vertical lengths of the impassable area, and select which side of the impassable area to pass through the impassable area according to which side of the path AD the impassable area is located, so that the subsequent safe parking route is the shortest.

[0061] Further, the step S3 is specifically:

[0062] S31, the route AB is obtained by using the Reeds Shepp curve algorithm according to the first corner point B, the direction of the vector BC, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle.

[0063] S32, according to the first corner point B, the vector BC direction, the minimum turning radius of the vehicle and the second corner point C, a route BC is obtained by using a Reeds Shepp curve algorithm;

[0064] S33, according to the second corner point C, the vector BC direction, the minimum turning radius of the vehicle, the position and the orientation of the parking space, a route CD is obtained by using a Reeds Shepp curve algorithm;

[0065] S34, the routes AB, BC and CD are connected to obtain a parking route.

[0066] As can be known from the above description, according to the determined first corner point B and the second corner point C, the route generation is performed in three sections by using a Reeds Shepp curve algorithm: the route AB, the route BC and the route CD, and the three generated routes are spliced to obtain a final parking route A->B->C->D which can safely bypass the impassable area.

[0067] The unmanned autonomous parking method and terminal based on the Reeds Shepp curve are suitable for the scene that an unmanned vehicle needs to park and may encounter an impassable area that needs to be bypassed.

[0068] Please refer to Figure 1 and Figure 3 , the first embodiment of the present application is:

[0069] An unmanned autonomous parking method based on a Reeds Shepp curve, comprising the steps of:

[0070] S1, obtaining the position D and the orientation of a parking space.

[0071] In this embodiment, we need to obtain the pre-set parking space information, the parking space information includes the position (generally the center point position) of the parking space and the positions (latitude and longitude information) of the two points before and after the parking space, and the orientation of the parking space is calculated according to the positions of the two points before and after the parking space.

[0072] The step S1 and the step S2 further comprise the step of:

[0073] S11, inputting the position A of the vehicle, the minimum turning radius, the heading angle, the position D of the parking space and the orientation of the parking space into a Reeds Shepp curve algorithm to obtain a path AD.

[0074] In this embodiment, we input the position D and the orientation of the parking space obtained in the foregoing, the turning radius of the unmanned vehicle and the current position A of the unmanned vehicle into a Reeds Shepp curve algorithm module to obtain the shortest path AD.

[0075] S12, judge whether there is an impassable area within the preset distance of the path AD, if there is the impassable area, enter step S2, otherwise follow the path AD to drive to the parking space and park, no longer execute the subsequent steps.

[0076] In this embodiment, after the path AD is generated, it is judged whether the path AD passes through an impassable area (which can be an obstacle or a fence, etc.), i.e. the distance between the path AD and the impassable area is less than a preset threshold, which can be the vehicle width. If there is no impassable area, directly enter the follow-up driving according to the path AD to the parking space, otherwise subsequent path segmentation planning is needed.

[0077] S2, obtain the position, length and width of the impassable area, and calculate the first corner point B and the second corner point C that the vehicle can safely pass through according to the vehicle width, the position and the length and width of the impassable area;

[0078] The step S2 is specifically:

[0079] S21, obtain the position O of the center point of the impassable area, the east-west span and the north-south span, establish a rectangular frame diagram circumscribed by the impassable area on the map according to the position O, the east-west span and the north-south span, and compare the east-west span and the north-south span;

[0080] S22, if the east-west span is greater than the north-south span, judge whether the position O is located on the east side or the west side of the path AD, if it is located on the west side of the path AD, select two corner points on the east side of the rectangular frame diagram, and translate eastward according to the vehicle width to obtain the first corner point B and the second corner point C, if it is located on the east side of the path AD, select two corner points on the west side of the rectangular frame diagram, and translate westward according to the vehicle width to obtain the first corner point B and the second corner point C;

[0081] S23, if the east-west span is less than the north-south span, judge whether the position O is located on the south side or the north side of the path AD, if it is located on the south side of the path AD, select two corner points on the north side of the rectangular frame diagram, and translate northward according to the vehicle width to obtain the first corner point B and the second corner point C, if it is located on the north side of the path AD, select two corner points on the south side of the rectangular frame diagram, and translate southward according to the vehicle width to obtain the first corner point B and the second corner point C;

[0082] The distance between the first corner point B and the vehicle is less than the distance between the second corner point C and the vehicle.

[0083] In this embodiment, as Figure 3As shown, we generate a rectangular frame according to the east-west direction and north-south direction spans of the impassable area (obstacle, which can be a fence, etc.), that is, the black rectangular frame identified as the obstacle in the figure. By comparing the spans of the two directions of the obstacle, Figure 3 It is obvious that the north-south direction span of the obstacle in this embodiment, that is, the longitudinal span, is smaller, so it is determined to bypass the obstacle in the longitudinal direction. Then, it is necessary to determine whether the obstacle is located on the left side or the right side of the path AD according to the position of the center point of the obstacle.

[0084] The east-west direction is the horizontal line (also known as the parallel, latitude, or east-west line) direction in the earth coordinate system, and the north-south direction is the vertical line (also known as the parallel, latitude, or north-south line) direction in the earth coordinate system.

[0085] In this embodiment, we determine the coordinates of the point on the path AD and the center point position of the obstacle through the formula:

[0086] dist=sqrt((x1-x2)*(x1-x2)+(y1-y2)*(y1-y2));

[0087] determine the point on the path AD closest to the position of the center point of the impassable area, and take the two points (x_3,y_3) (x_4,y_4) 0.3m before and after the point on the path AD;

[0088] According to the formula:

[0089] Tmp=(y3–y4)*x_o+(x4–x3)*y_o+x3*y4–x4*y3;

[0090] Determine which side of the path AD the obstacle is located on by judging Tmp, if Tmp>0 on the left side, Tmp=0 on the line, and Tmp<0 on the right side.

[0091] For reference Figure 3 In this embodiment, the center point position of the obstacle is located on the right side of the path AD, so we want to bypass it from the left side. As shown, Figure 3 The two corner points O_B and O_C on the left side of the rectangular frame circumscribing the obstacle are translated to the right by a distance, to obtain the first corner point B and the second corner point C. In this embodiment, the translation distance is half the vehicle width, and in other equivalent embodiments or actual operations, to ensure safe passage and avoid any contact, the distance can be set to more than half the vehicle width.

[0092] S3, according to the first corner point B, the direction of the vector BC, the second corner point C, the position D of the parking space, the minimum turning radius of the vehicle, the position A of the vehicle, and the heading angle of the vehicle, a route AB, BC and CD are generated using the Reeds Shepp curve algorithm to obtain a parking route;

[0093] The step S3 is specifically:

[0094] S31, according to the first corner point B, the vector BC direction, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle, a route AB is obtained by using the ReedsShepp curve algorithm;

[0095] S32, according to the first corner point B, the vector BC direction, the minimum turning radius of the vehicle and the second corner point C, a route BC is obtained by using the ReedsShepp curve algorithm;

[0096] S33, according to the second corner point C, the vector BC direction, the minimum turning radius of the vehicle, the position of the parking space and the orientation, a route CD is obtained by using the ReedsShepp curve algorithm;

[0097] S34, the route AB, the route BC and the route CD are connected to obtain a parking route.

[0098] In this embodiment, the process of planning the trajectory is divided into three parts, A to B, B to C and C to D, and the ReedsShepp curve algorithm is used to plan the three routes, and the three routes are spliced into a complete parking route.

[0099] S4, according to the parking route, a driverless driving is performed to the parking space and parking.

[0100] In this embodiment, after obtaining the planned parking route, the vehicle performs a driverless driving along the parking route, so that the driverless vehicle drives into and parks in the parking space.

[0101] Please refer to Figure 2 Figure 2 , the second embodiment of the present application is:

[0102] An unmanned autonomous parking terminal 1 based on ReedsShepp curve includes a processor 2, a memory 3, and a computer program stored in the memory 3 and executable on the processor 2, and the processor 2 executes the computer program to realize the steps in the above first embodiment.

[0103] The main principle of the present application is to select which side to bypass the obstacle according to the position and length and width of the obstacle, so as to ensure the shortest bypass route, and finally splice the complete route by segmenting the route, so as to realize the planning of the bypass route.

[0104] In summary, the application provides an unmanned autonomous parking method and terminal based on Reeds Shepp curve, which can automatically generate a safe parking route avoiding the impassable area by the way of segmented planning when parking is needed, so as to realize the automatic parking of unmanned tracking driving, and ensure that the obstacle-avoiding route obtained by planning is the shortest according to the length, width and position of the obstacle.

[0105] The above is only an embodiment of the application, and does not limit the patent scope of the application. Any equivalent transformation or direct or indirect application in the related technical field based on the content of the specification and drawings is also included in the patent protection scope of the application.

Claims

1. A method for autonomous parking of an unmanned vehicle based on Reeds Shepp curve, characterized in that, The method comprises the steps of: S1, acquiring the position D and orientation of the parking space; S11, inputting the position A of the vehicle, the minimum turning radius, the heading angle, the position D of the parking space and the orientation of the parking space into a Reeds Shepp curve algorithm to obtain a path AD; S12, judging whether there is an impassable area within a preset distance of the path AD, if there is the impassable area, entering step S2, otherwise, following the path AD to drive to the parking space and park, and no subsequent steps are executed; S2, acquiring the position, length and width of the impassable area, and calculating a first corner point B and a second corner point C that can be safely passed by the vehicle according to the vehicle width, the position and the length and width of the impassable area; The step S2 is specifically: S21, acquiring the position O of the center point of the impassable area, the east-west direction span and the north-south direction span, establishing a rectangular frame diagram circumscribed by the impassable area on a map according to the position O, the east-west direction span and the north-south direction span, and comparing the east-west direction span and the north-south direction span; S22, if the east-west direction span is greater than the north-south direction span, judging whether the position O is located on the east side or the west side of the path AD, if located on the west side of the path AD, selecting two corner points on the east side of the rectangular frame diagram and translating eastward according to the vehicle width to obtain the first corner point B and the second corner point C, if located on the east side of the path AD, selecting two corner points on the west side of the rectangular frame diagram and translating westward according to the vehicle width to obtain the first corner point B and the second corner point C; S23, if the east-west direction span is less than the north-south direction span, judging whether the position O is located on the south side or the north side of the path AD, if located on the south side of the path AD, selecting two corner points on the north side of the rectangular frame diagram and translating northward according to the vehicle width to obtain the first corner point B and the second corner point C, if located on the north side of the path AD, selecting two corner points on the south side of the rectangular frame diagram and translating southward according to the vehicle width to obtain the first corner point B and the second corner point C; The distance between the first corner point B and the vehicle is less than the distance between the second corner point C and the vehicle; S3, generating routes AB, BC and CD by using the Reeds Shepp curve algorithm according to the first corner point B, the direction of the vector BC, the second corner point C, the position D of the parking space, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle, so as to obtain a parking route; S4, following the parking route to drive to the parking space and park.

2. The method of claim 1, wherein the Reeds Shepp curve is used to determine a path of the autonomous vehicle. The step S3 is specifically: S31, obtaining the route AB by using the Reeds Shepp curve algorithm according to the first corner point B, the direction of the vector BC, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle; S32, obtaining the route BC by using the Reeds Shepp curve algorithm according to the first corner point B, the direction of the vector BC, the minimum turning radius of the vehicle and the second corner point C; S33, obtaining the route CD by using the Reeds Shepp curve algorithm according to the second corner point C, the direction of the vector BC, the minimum turning radius of the vehicle, the position of the parking space and the orientation; S34, connecting the route AB, the route BC and the route CD to obtain a parking route.

3. An unmanned autonomous parking terminal based on Reeds Shepp curve, comprising a processor, a memory and a computer program stored in the memory and executable on the processor, characterized in that, The processor implements the following steps when executing the computer program: S1, obtaining a position D and an orientation of a parking space; S11, inputting a position A of a vehicle, a minimum turning radius, a heading angle, the position D of the parking space and the orientation of the parking space into a Reeds Shepp curve algorithm to obtain a path AD; S12, judging whether there is an impassable area within a preset distance of the path AD, if there is the impassable area, entering step S2, otherwise, driving along the path AD to the parking space and parking, and no subsequent steps are executed; S2, obtaining a position, a length and a width of the impassable area, and calculating a first corner point B and a second corner point C that can be safely passed by the vehicle according to a vehicle width, the position and the length and the width of the impassable area; The step S2 is specifically: S21, obtaining a position O of a center point of the impassable area, an east-west span and a south-north span, establishing a rectangular frame diagram circumscribed by the impassable area on a map according to the position O, the east-west span and the south-north span, and comparing the east-west span and the south-north span; S22, if the east-west span is greater than the south-north span, judging whether the position O is located on an east side or a west side of the path AD, if the position O is located on the west side of the path AD, selecting two corner points on the east side of the rectangular frame diagram, and translating eastward according to the vehicle width to obtain the first corner point B and the second corner point C, if the position O is located on the east side of the path AD, selecting two corner points on the west side of the rectangular frame diagram, and translating westward according to the vehicle width to obtain the first corner point B and the second corner point C; S23, if the east-west span is less than the south-north span, judging whether the position O is located on a south side or a north side of the path AD, if the position O is located on the south side of the path AD, selecting two corner points on the north side of the rectangular frame diagram, and translating northward according to the vehicle width to obtain the first corner point B and the second corner point C, if the position O is located on the north side of the path AD, selecting two corner points on the south side of the rectangular frame diagram, and translating southward according to the vehicle width to obtain the first corner point B and the second corner point C; The distance between the first corner point B and the vehicle is less than the distance between the second corner point C and the vehicle; S3, generating the route AB, the route BC and the route CD by using the Reeds Shepp curve algorithm according to the first corner point B, a direction of the vector BC, the second corner point C, the position D of the parking space, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle, so as to obtain a parking route; S4, driving along the parking route to the parking space and parking.

4. The Reeds Shepp curve based unmanned autonomous parking terminal according to claim 3, characterized in that, The step S3 is specifically: S31, obtaining the route AB by using the Reeds Shepp curve algorithm according to the first corner point B, the direction of the vector BC, the minimum turning radius of the vehicle, the position A of the vehicle and the heading angle of the vehicle; S32, obtaining the route BC by using the Reeds Shepp curve algorithm according to the first corner point B, the direction of the vector BC, the minimum turning radius of the vehicle and the second corner point C; S33, according to the second corner point C, the vector BC direction, the minimum turning radius of the vehicle, the position and the orientation of the parking space, the route CD is obtained by using the Reeds Shepp curve algorithm; S34, the route AB, the route BC and the route CD are connected to obtain the parking route.

Citation Information

Patent Citations

  • Unmanned obstacle avoidance method and terminal based on laser radar and GPS

    CN113296118A