A sinusoidal-based parking path planning method and system

Abstract

The application is suitable for the technical field of intelligent parking, and provides a parking path planning method and system based on a sinusoidal curve, vehicle information and obstacle information around the vehicle are acquired in real time according to parking space information; a parking path is planned by fitting a sinusoidal curve according to the vehicle information and the obstacle information; and the vehicle is controlled to park along the planned parking path. By clicking an automatic parking button, the surrounding available parking spaces are searched automatically through a sensor, and after the driver selects an available parking space, the vehicle automatically parks in the parking space. The parking path designed by the system has continuous curvature and is easy to track and control; the path planning has high practicability and safety, and is suitable for any vehicle equipped with a panoramic image system and an ultrasonic parking radar auxiliary system.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent parking, and in particular relates to a parking path planning method and system based on a sine curve. Background Art

[0002] With the continuous increase in the number of cars and urban populations, and the expansion of urban construction land, driving space is becoming increasingly constricted, urban traffic is becoming increasingly congested, and parking spaces are gradually shrinking. This has made parking difficulties a major daily commuter problem. Reversing into a tight space is a headache for many drivers, especially beginners and some female drivers, who find it difficult to successfully reverse into a parking space. Traffic accidents caused by this are also increasing year by year, accounting for a significant proportion of all traffic accidents. As cars have gradually become an integral part of people's lives as a means of transportation, people's expectations for vehicle performance are constantly increasing. They not only demand high operational stability and good ride comfort, but also increasingly demand safety and intelligent features. The rapid development of artificial intelligence technology has also accelerated the development of autonomous driving technology.

[0003] The automatic parking system uses on-board sensors (including a fusion solution of 4 panoramic cameras and 12 ultrasonic radars) to identify effective parking spaces, and through the automatic parking assist control electronic control unit ECU, it coordinates the vehicle's chassis electric steering power system ESP, electronic stability system ESP and powertrain engine system EMS, transmission system TCU, etc., to control the vehicle for parallel parking, vertical parking and diagonal parking through orderly planning.

[0004] As a key feature of autonomous driving, the automatic parking system encompasses at least the following aspects: environmental perception, parking space detection, path planning, and motion control. Parking spaces can be identified using high-precision maps or by detecting them during low-speed cruising. Parking space detection typically relies on a combination of onboard sensors, such as cameras and ultrasonic radar. Cameras positioned around the vehicle capture surrounding images, process them, and detect parking spaces. Ultrasonic data is also integrated to determine whether there is sufficient space for parking. Once a parking space is determined, the system combines the vehicle's position information to plan a parking path that conforms to its motion patterns. Ultimately, this path information controls actuators such as the steering wheel, accelerator, and brakes to complete automatic parking.

[0005] The fully automatic parking system (APS) uses onboard sensors to identify information about the vehicle and its surroundings, assisting the driver in maneuvering the vehicle. This not only reduces driver stress and improves parking efficiency, but also, most importantly, prevents traffic accidents caused by backing out. Consequently, this system has attracted the attention of global automakers and research institutions. Currently, the automated parking technology used in many models is immature, and people are not entirely willing to trust and use automated parking systems. Therefore, researching and developing automated parking systems with independent intellectual property rights is of great theoretical and practical significance. Summary of the Invention

[0006] In order to solve the above problems, the present invention provides a parking path planning method based on a sine curve, which includes:

[0007] Obtain vehicle information and obstacle information around the vehicle in real time based on parking space information;

[0008] According to the vehicle information and obstacle information, a sine curve is used for fitting to plan the parking path;

[0009] Control the vehicle to park along the planned parking path.

[0010] Before acquiring the vehicle information and the obstacle information around the vehicle in real time according to the parking space information, the method further includes:

[0011] Obtain environmental information around the vehicle and record the location information of parking spaces that meet parking requirements;

[0012] The parking space information is selected from the recorded parking space position information.

[0013] The method of fitting a sine curve based on the vehicle information and the obstacle information to plan the parking path specifically includes:

[0014] Determine the initial parking position M0, the target parking position M1, the longitudinal distance D and the lateral distance L between the initial parking position and the target parking position based on the parking space information and the vehicle information;

[0015] Construct a coordinate system with the origin being the vertex O at the lower left corner of the parking space. p , the X-axis is the length direction of the parking space, and the Y-axis is the width direction of the parking space, with the side where the vehicle to be parked is the positive direction;

[0016] Construct a parking path curve model.

[0017] The parking path curve model is specifically:

[0018] y(x)=ax+b sin(cx)

[0019] Where a, b, and c are constants, and the solution is obtained based on the constraints of the initial parking position and the target parking position.

[0020] The control of the vehicle to perform parking operations along the planned parking path is accompanied by constraining the vehicle's own physical conditions to track and control the vehicle's trajectory.

[0021] The physical conditions of the vehicle itself are constrained as follows:

[0022]

[0023] Where: v is the speed of the vehicle when parking; a is the acceleration of the vehicle when parking; j is the rate of change of acceleration of the vehicle when parking; δ is the equivalent angle of the front wheel; ω is the equivalent angular velocity of the front wheel; v max is the maximum speed of the vehicle for parking; a max is the maximum acceleration of the vehicle during parking; j max is the maximum acceleration rate of the vehicle during parking; δ max is the maximum front wheel equivalent angle; ω max is the maximum front wheel equivalent angular velocity.

[0024] After planning the parking path by fitting a sine curve based on the vehicle information and the obstacle information, the method further includes:

[0025] Based on the obstacle information, determine whether the parking path passes through an obstacle;

[0026] If the parking path passes through an obstacle, the selected parking space will be unavailable;

[0027] If the parking path does not lead through obstacles, the selected parking space is available.

[0028] While controlling the vehicle to perform a parking operation along the planned parking path, the method further includes:

[0029] Obtain a bird's-eye view of the vehicle's surroundings in real time, and calibrate the vehicle's four vertices and obstacle locations from the bird's-eye view.

[0030] Four triangles are formed between any two adjacent vertices and the obstacle location point, and the total area of ​​the four triangles is determined to be greater than the area of ​​the quadrilateral enclosed by the four vertices;

[0031] When the total area of ​​the four triangles is greater than the area of ​​the quadrilateral enclosed by the four vertices, the obstacle is outside the vehicle and no collision occurs;

[0032] When the total area of ​​the four triangles is not greater than the area of ​​the quadrilateral enclosed by the four vertices, the planned parking path is unavailable and a new parking space is selected.

[0033] In another aspect, the present invention further provides a parking path planning system based on a sine curve, the system comprising:

[0034] The data processing module is used to obtain vehicle information and obstacle information around the vehicle in real time based on the parking space information;

[0035] The parking path fitting module is used to plan the parking path based on vehicle information and obstacle information using a sine curve fitting method.

[0036] The controller module is used to control the vehicle to perform parking operations along the planned parking path.

[0037] Wherein, the system further includes:

[0038] The body sensor module is also used to obtain environmental information around the vehicle and transmit it to the controller module;

[0039] A controller module, used to record the location information of parking spaces that meet parking requirements;

[0040] The human-computer interaction module is used to select parking space information from the recorded parking space position information.

[0041] The parking path curve model used in the parking path fitting module is specifically:

[0042] y(x)=ax+b sin(cx)

[0043] Where a, b, and c are constants, and the solution is obtained based on the constraints of the initial parking position and the target parking position.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] This invention provides a sine curve-based parking path planning method and system. With the click of an automatic parking button, sensors automatically search for available parking spaces nearby. Once the driver selects an available space, the vehicle automatically parks there. The parking path designed by this system features continuous curvature, making it easy to track and control. This path planning method is highly practical and safe, and is applicable to any vehicle equipped with a panoramic imaging system or ultrasonic parking radar assistance system.

[0046] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 A flowchart of a parking path planning based on a sine curve in an embodiment of the present invention is shown;

[0049] Figure 2 A schematic diagram of obstacle determination assistance in an embodiment of the present invention is shown;

[0050] Figure 3 A schematic diagram of a vehicle envelope generated during a parking process according to an embodiment of the present invention is shown;

[0051] Figure 4 A schematic structural diagram of a parking path planning system based on a sine curve in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0053] The technical problem to be solved by this invention is to propose a sinusoidal curve-based automatic parallel parking path planning method for parallel parking conditions. When the automatic parking button is pressed, sensors (ultrasonic radar and 360-degree surround-view camera) automatically search for available parking spaces in the surrounding area. Once the driver selects an available space, the vehicle automatically parks into the space. This path planning method is highly practical and safe, and is applicable to any vehicle equipped with a panoramic imaging system or ultrasonic parking radar assistance system.

[0054] Figure 1 A flowchart of a parking path planning based on a sine curve in an embodiment of the present invention is shown, which includes the following steps:

[0055] 1) When the driver drives the car from left to right, the parking space recognition function is turned on through the human-computer interaction module, and the car enters the parking space search stage.

[0056] 2) Obtaining environmental information around the vehicle and recording the location of parking spaces that meet the minimum parking requirements. Specifically, the vehicle's body sensors acquire environmental information, transmit it to the controller, and record the parking spaces that meet the minimum parking requirements.

[0057] 3) Selecting a parking space from the recorded parking space location information. Specifically, after parking, the driver turns on the automatic parking function and selects a designated parking space.

[0058] 4) Real-time acquisition of vehicle information and surrounding obstacle information based on parking space information. Specifically, the vehicle position and surrounding obstacle locations of the vehicle to be parked are acquired in real time through the vehicle information acquisition module or body sensors and data processing module.

[0059] 5) According to the vehicle information and obstacle information, a sine curve is used to fit and plan the parking path. Specifically, the car uses a sine curve to fit according to the starting position to plan an optimal path, such as Figure 3 A schematic diagram of a vehicle envelope generated during a parking process in an embodiment of the present invention is shown.

[0060] 5.1) The driver selects the target parking space, and the vehicle automatically identifies the target parking space information using the onboard ultrasonic radar and panoramic imaging system; the target parking space information includes the parking space length Lp, parking space width Wp and the parking space lower left corner position Op

[0061] 5.2) Determine the initial parking position, M0, which is the target position of the rear axle midpoint when the vehicle is parked in the initial parking space; and the target parking position, M1, which is the target position of the rear axle midpoint when the vehicle is parked in the target parking space, located on the longitudinal centerline of the target parking space and below the transverse centerline of the designated parking space. D is the longitudinal distance between the starting and ending points of the vehicle to be parked, and L is the transverse distance between the starting and ending points of the vehicle to be parked.

[0062] 5.3) Construct a geodetic coordinate system XOY, where the origin is the lower left corner Op of the parking space, the X-axis is the length of the parking space, with the side of the vehicle to be parked as the positive direction, and the Y-axis is the width of the parking space;

[0063] 5.4) Construct parking path model and track control:

[0064] 5.4.1) Based on the distance information provided by the ultrasonic radar and panoramic imaging system, D is the longitudinal distance between the starting and ending points of the vehicle to be parked, and L is the lateral distance between the starting and ending points of the vehicle to be parked;

[0065] 5.4.2) The basic expression of the parking path curve is as follows:

[0066] y(x)=ax+b sin(cx) (2)

[0067] Where a, b, and c are constants. The solution is based on the constraints of the initial parking position and the target parking position. The corresponding parameters for different vehicle models are inconsistent.

[0068] Furthermore, after the path is planned, it is determined whether the parking path passes through an obstacle based on the obstacle information;

[0069] If the parking path passes through an obstacle and there is an obstacle blocking the parking path, the selected parking space will be unavailable;

[0070] If the parking path does not lead through obstacles, the selected parking space is available.

[0071] 6) Control the vehicle to park along the planned parking path. Specifically, the controller outputs a control strategy to the actuator to perform parking maneuvers, so that the vehicle can drive along the reference trajectory to the parking end point.

[0072] Furthermore, if the vehicle is to be able to track the trajectory smoothly, the physical conditions of the vehicle itself should be constrained, that is, kinematic constraints should be imposed on the parking speed, acceleration, front wheel equivalent angle, and front wheel equivalent angle speed:

[0073]

[0074] Where: v is the speed of the vehicle when parking; a is the acceleration of the vehicle when parking; j is the rate of change of acceleration of the vehicle when parking; δ is the equivalent angle of the front wheel; ω is the equivalent angular velocity of the front wheel; v max is the maximum speed of the vehicle for parking; a max is the maximum acceleration of the vehicle during parking; j max is the maximum acceleration rate of the vehicle during parking; δ max is the maximum front wheel equivalent angle; ω max is the maximum front wheel equivalent angular velocity.

[0075] 7) During parking, the anti-collision function is always on.

[0076] Specifically, when performing parking operations, a bird's-eye view of the vehicle's surroundings is obtained in real time, and the four vertices of the vehicle and the location of obstacles are calibrated from the bird's-eye view of the surroundings;

[0077] Four triangles are formed between any two adjacent vertices and the obstacle location point, and the total area of ​​the four triangles is determined to be greater than the area of ​​the quadrilateral enclosed by the four vertices;

[0078] When the total area of ​​the four triangles is greater than the area of ​​the quadrilateral enclosed by the four vertices, the obstacle is outside the vehicle and no collision occurs;

[0079] When the total area of ​​the four triangles is not greater than the area of ​​the quadrilateral enclosed by the four vertices, the planned parking path is unavailable and a new parking space is selected.

[0080] Specifically, Figure 2 FIG1 shows an auxiliary diagram of obstacle determination in an embodiment of the present invention. The four-point method can be used to determine whether an obstacle falls inside the vehicle. Figure 2 As shown in the figure, ABCD represent the four vertices of the vehicle, and E represents the obstacle. When the obstacle is closer to the vehicle than the blind spot of the ultrasonic radar, the following constraints can be met:

[0081] S ΔEAB +S ΔEBC +S ΔECD +S ΔEDA >S ABCD (1)

[0082] Where S ΔEAB is the area of ​​triangle EAB, S ΔEBC is the area of ​​triangle EBC, S ΔECD is the area of ​​triangle ECD, S ΔEDA is the area of ​​triangle EDA, where S ABCD is the area of ​​the vehicle. When the area of ​​the four triangles is larger than the vehicle area, the obstacle is outside the vehicle. When the area of ​​the quadrilateral is smaller than the vehicle area, the path is unavailable and a new available parking space is searched. This method can monitor the surrounding environment within the ultrasonic radar blind spot, prevent obstacles from suddenly appearing around the vehicle during parking, and ensure the safety of the parking process. Combined with formulas (1), (2), and (3), the final path is planned and the parking vehicle is tracked.

[0083] 8) When the vehicle successfully reaches the parking end point, the automatic parking process ends.

[0084] Accordingly, Figure 4 A schematic diagram of the structure of a parking path planning system based on a sine curve in an embodiment of the present invention is shown. The system includes:

[0085] The data processing module is used to obtain vehicle information and obstacle information around the vehicle in real time based on the parking space information;

[0086] The parking path fitting module is used to plan the parking path based on vehicle information and obstacle information using a sine curve for fitting.

[0087] The parking path curve model used in the parking path fitting module is specifically:

[0088] y(x)=ax+b sin(cx)

[0089] Where a, b, and c are constants, and the solution is obtained based on the constraints of the initial parking position and the target parking position.

[0090] The controller module is used to control the vehicle to perform parking operations along the planned parking path.

[0091] Wherein, the system further includes:

[0092] The body sensor module is also used to obtain environmental information around the vehicle and transmit it to the controller module;

[0093] A controller module, used to record the location information of parking spaces that meet parking requirements;

[0094] The human-computer interaction module is used to select parking space information from the recorded parking space position information.

[0095] The above parallel parking solution has the following advantages:

[0096] 1) This path planning reduces the complexity of path planning and reduces tire wear, while improving parking efficiency and increasing comfort.

[0097] 2) This system is based on a geometric path method with high computational efficiency, good real-time performance, and is easy to implement in engineering. It is also robust, easy to use, and safe.

[0098] 3) This solution is applicable to any vehicle equipped with a panoramic imaging system or ultrasonic parking radar assistance system.

[0099] 4) The parking path designed by this system has continuous curvature and is easy to track and control.

[0100] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A parking path planning method based on a sine curve, the method comprising: Obtain vehicle information and obstacle information around the vehicle in real time based on parking space information; According to the vehicle information and obstacle information, a sine curve is used for fitting to plan the parking path; Control the vehicle to park along the planned parking path; The parking path planning using a sine curve fitting based on the vehicle information and obstacle information specifically includes: Determine the initial parking position M0, the target parking position M1, the longitudinal distance D and the lateral distance L between the initial parking position and the target parking position based on the parking space information and the vehicle information; Construct a coordinate system with the origin being the vertex O at the lower left corner of the parking space. p , the X-axis is the length direction of the parking space, and the Y-axis is the width direction of the parking space, with the side where the vehicle to be parked is the positive direction; Construct parking path curve model; The parking path curve model is specifically: Where a, b, and c are constants, and the solution is obtained based on the constraints of the initial parking position and the target parking position.

2. The parking path planning method based on sine curve according to claim 1, wherein: Before acquiring vehicle information and information about obstacles around the vehicle in real time based on the parking space information, the method further includes: Obtain environmental information around the vehicle and record the location information of parking spaces that meet parking requirements; The parking space information is selected from the recorded parking space position information.

3. The parking path planning method based on sine curve according to claim 1, wherein: The control unit controls the vehicle to perform parking operations along the planned parking path while constraining the vehicle's own physical conditions to track and control the vehicle's running trajectory; The physical conditions of the vehicle itself are constrained as follows: Where: the speed at which the vehicle is parked; The acceleration of the parking vehicle; is the acceleration change rate of the vehicle during parking; is the front wheel equivalent angle; is the front wheel equivalent angular velocity; The maximum speed for parking the vehicle; is the maximum acceleration of the vehicle when parking; is the maximum acceleration rate of the vehicle during parking; is the maximum front wheel equivalent angle; is the maximum front wheel equivalent angular velocity.

4. The parking path planning method based on sine curve according to claim 1, wherein: After planning the parking path by fitting a sine curve based on the vehicle information and the obstacle information, the method further includes: According to the obstacle information, determine whether the parking path passes through the obstacle; If the parking path passes through an obstacle, the selected parking space will be unavailable; If the parking path does not lead through obstacles, the selected parking space is available.

5. The parking path planning method based on a sine curve according to any one of claims 1 to 4, wherein: While controlling the vehicle to perform a parking operation along the planned parking path, the method further includes: Obtain a bird's-eye view of the vehicle's surroundings in real time, and calibrate the vehicle's four vertices and obstacle locations from the bird's-eye view. Four triangles are formed between any two adjacent vertices and the obstacle location point, and the total area of ​​the four triangles is determined to be greater than the area of ​​the quadrilateral enclosed by the four vertices; When the total area of ​​the four triangles is greater than the area of ​​the quadrilateral enclosed by the four vertices, the obstacle is outside the vehicle and no collision occurs; When the total area of ​​the four triangles is not greater than the area of ​​the quadrilateral enclosed by the four vertices, the planned parking path is unavailable and a new parking space is selected.

6. A parking path planning system based on a sine curve, the system comprising: The data processing module is used to obtain vehicle information and obstacle information around the vehicle in real time based on the parking space information; The parking path fitting module is used to plan the parking path based on vehicle information and obstacle information using a sine curve fitting method. A controller module is used to control the vehicle to perform parking operations along the planned parking path; The parking path planning using a sine curve fitting based on the vehicle information and obstacle information specifically includes: Determine the initial parking position M0, the target parking position M1, the longitudinal distance D and the lateral distance L between the initial parking position and the target parking position based on the parking space information and the vehicle information; Construct a coordinate system with the origin being the vertex O at the lower left corner of the parking space. p , the X-axis is the length direction of the parking space, and the Y-axis is the width direction of the parking space, with the side where the vehicle to be parked is the positive direction; Construct parking path curve model; The parking path curve model is specifically: Where a, b, and c are constants, and the solution is obtained based on the constraints of the initial parking position and the target parking position.

7. The parking path planning system based on sine curve according to claim 6, wherein: The system further comprises: The body sensor module is also used to obtain environmental information around the vehicle and transmit it to the controller module; A controller module, used to record the location information of parking spaces that meet parking requirements; The human-computer interaction module is used to select parking space information from the recorded parking space position information.

Images