Parallel parking path planning method and system

Abstract

The application relates to the technical field of automobile intelligentization, and provides a parallel parking path planning method, which comprises steps S1-S6, that is, through a vehicle sensor, data such as to-be-parked parking space data is perceived, a polynomial function relationship is established according to a vehicle parallel parking path, polynomial coefficient values are obtained according to a first constraint condition, a second constraint condition, a third constraint condition and a fourth constraint condition, and a polynomial function path planning curve is obtained; a hyperbolic tangent tanh function is used to obtain a hyperbolic tangent path planning curve; the polynomial function path planning curve and the hyperbolic tangent path planning curve are fused to obtain a parallel parking path planning curve; and the vehicle is tracked and controlled according to the parallel parking path planning curve to complete vehicle parking operation. The method can solve the problems of discontinuous parking path curvature, poor tracking, complex path structure composition, too many nodes and large fitting path error, guarantees smooth parking path, improves parking efficiency and improves parking effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automobile intelligent technology, and particularly relates to a parallel parking path planning method and system. BACKGROUND

[0002] Automatic parking path planning is to plan a safe, reasonable and easy-to-track path curve between the starting point and the ending point of parking, while meeting various parking constraints and combining with the surrounding parking environment. As an intermediate link connecting automatic parking space detection and tracking control, path planning plays a key role in whether the automatic parking system can quickly and safely park in the parking space. Automatic parking obtains the pose of the vehicle itself, the information of the parking space and the information of obstacles through various sensors, and performs path planning on the obtained information, so that the vehicle can park safely and efficiently without collision according to the planned path. A reliable and efficient automatic parking system can ensure the safety of the driver, reduce parking congestion, and effectively improve the driving comfort.

[0003] CN115384518A discloses a side parking space positioning method and device based on ultrasonic radar, comprising: obtaining a set of contour points of an obstacle on the side of a current vehicle through an ultrasonic radar during the forward movement of the current vehicle; segment fitting the contour of the obstacle on the side of the current vehicle according to the set of contour points to obtain the direction of the obstacle on the side of the current vehicle; and determining the direction of the parking space on the side of the current vehicle according to the direction of the obstacle on the side of the current vehicle.

[0004] JP2022173839A discloses an automatic parking system and an automatic parking system control method, which has a plurality of parking areas in which a plurality of parking spaces are parallel at least in a parallel direction. The automatic parking system obtains the number of parking spaces for each of the plurality of parking areas, the number of parking spaces being the number of parking spaces arranged in the parallel direction. For each of the plurality of parking lots, the number of empty spaces, i.e. the number of free parking spaces, is obtained. Based on the number of empty spaces, an empty space threshold value is calculated, which is a threshold value of the number of empty spaces for calculating the priority of the parking area in which the vehicle parked by automatic parking is parked. The priority is calculated so that the priority of the parking area in which the number of empty spaces is greater than or equal to the number of empty space threshold is higher than the priority of the parking area in which the number of empty spaces is less than the number of empty space threshold. The vehicle parked by automatic parking is preferentially parked in the parking space of the high-priority parking lot.

[0005] CN115303263A discloses a neural network-based automatic parking method and system, the method comprising: acquiring a panoramic surround view image of a vehicle around through a camera; acquiring a parking position through a deep neural network algorithm based on the panoramic surround view image; planning a parking path based on the parking position and the vehicle state; starting a vehicle control system to execute parking, and determining whether parking is ended every certain time threshold, and if so, ending the detection, otherwise, continuing to execute parking.

[0006] In the parking path planning of the existing automatic parking system, the geometric method is often used for path planning, including two-arc, arc-straight line, spiral curve, B-spline curve, polynomial curve and sine function curve, which are often difficult to complete high-precision automatic parking. SUMMARY

[0007] Through long-term practice, it is found that the method of arc and straight line has simple structure, but the path curvature is discontinuous, not easy to track, and additional pressure is added to the steering system and tires, which damages the comfort of passengers; although the spiral curve and B-spline curve have continuous curvature and are easy to track, the structure is complex and the calculation amount is large, and the multi-segment path increases the damage of the steering system and tires and the error of the actual parking path; the polynomial curve parking method has too large parking path curvature and long curve. In the existing parking path planning method, the path curvature is discontinuous, the curvature is too large and not easy to track, and the fitting path error is large, which affects the automatic parking effect and causes parking failure and other problems.

[0008] Therefore, the present application aims to provide a parallel parking path planning method, which comprises,

[0009] Step S1, sensing the parking space data and the initial position and attitude data of the vehicle through the vehicle sensor, and establishing a polynomial function relationship according to the parallel parking path of the vehicle,

[0010] y(x)=a5x 5 +a4x 4 +a3x 3 +a2x 2 +a1x+a0

[0011] The first constraint condition is established by the vehicle starting point coordinate and the parking end point coordinate

[0012]

[0013]

[0014] ​Wherein, the starting point coordinate value is obtained by the positioning system, and the terminal point coordinate value is obtained by the safety constraint between the vehicle and the parking space when the parking is finished; a0, a1, a2, a3, a4, a5 are polynomial coefficients respectively;

[0015] In step S2, the second constraint condition that the first derivative of the path curve at the starting point and the terminal point is 0 is obtained according to the position and posture constraint condition of the starting point and the terminal point of the path, that is,

[0016]

[0017]

[0018] In step S3, the third constraint condition that the second derivative of the path curve at the terminal point is 0 is obtained according to the fact that the steering wheel is returned to normal when the parking is finished, and the slope in the parking path does not change at this time, that is,

[0019]

[0020] In step S4, the fourth constraint condition that the center point of the rear axle is just at the point is obtained according to the constraint condition that the vehicle safely and collision-free drives out of the parking space, that is,

[0021]

[0022] Wherein, R1 is the minimum turning radius of the vehicle, and δ is the turning angle of the vehicle;

[0023] According to the first constraint condition, the second constraint condition, the third constraint condition and the fourth constraint condition, the values of the polynomial coefficients a0, a1, a2, a3, a4 and a5 are obtained, and the polynomial function path planning curve is obtained.

[0024] In step S5, the hyperbolic tangent path planning curve is obtained based on the hyperbolic tangent function,

[0025]

[0026] Wherein, a , b, c , d are function coefficients respectively;

[0027] In step S6, the parallel parking path planning curve is obtained by fusing the polynomial function path planning curve and the hyperbolic tangent path planning curve, that is,

[0028] f(x)=kg(x)+(1-k)y(x)

[0029] Wherein, k is a proportional coefficient, and the range is 0-1.

[0030] ​The vehicle tracks the parallel parking path planning curve to complete the vehicle parking operation.

[0031] Preferably, in step S5, the function coefficients a, b, c , d are obtained through the position and attitude constraint relationship of the vehicle in the parking process of the first constraint condition, the second constraint condition, the third constraint condition and the fourth constraint condition.

[0032] Preferably, in step S6, the proportional coefficient k is determined by an iterative optimization method.

[0033] Preferably, the relative position of the vehicle and the parking space is obtained through the vehicle sensor, and the center point of the rear axle of the vehicle is taken as the tracking control basis in the parallel parking path planning curve.

[0034] The application also discloses a system for executing the parallel parking path planning method, and the system comprises,

[0035] The first constraint unit comprises a sensor module, and the sensor module at least comprises a visual sensor and an ultrasonic sensor; the sensor module is used for sensing the parking space data and the initial position and attitude data of the vehicle through the vehicle sensor, and a polynomial function relationship is established according to the parallel parking path of the vehicle,

[0036] y(x)=a5x 5 +a4x 4 +a3x 3 +a2x 2 +a1x+a0

[0037] The first constraint condition is established by the coordinate of the starting point of the vehicle and the coordinate of the parking end point .

[0038]

[0039]

[0040] The coordinate value of the starting point is obtained through a positioning system, and the coordinate value of the end point is obtained through the safety constraint of the vehicle and the parking space when the parking is completed; a0, a1, a2, a3, a4 and a5 are polynomial coefficients.

[0041] The second constraint unit is used for obtaining the second constraint condition that the first derivative of the path curve at the starting point and the end point is 0 according to the position and attitude constraint condition of the starting point and the end point of the path, and the second constraint condition is

[0042]

[0043]

[0044] a third constraint unit configured to obtain a third constraint condition that a second derivative of the path curve at the end point is 0 according to the steering wheel returning to normal at the end of parking and no change in slope in the parking path,

[0045]

[0046] a fourth constraint unit including a calculation module configured to obtain a fourth constraint condition that a center point of the rear axle is just at the point according to a constraint condition that the vehicle safely exits the parking space without collision,

[0047]

[0048] wherein R1 is a minimum turning radius of the vehicle and δ is a turning angle of the vehicle;

[0049] the calculation module is configured to obtain a0, a1, a2, a3, a4, and a5 polynomial coefficient values according to the first constraint condition, the second constraint condition, the third constraint condition, and the fourth constraint condition, and obtain a polynomial function path planning curve;

[0050] a construction unit configured to obtain a hyperbolic tangent path planning curve based on a hyperbolic tangent tanh function,

[0051]

[0052] wherein a, b, c, and d are function coefficients;

[0053] a fusion unit including a tracking control module configured to fuse the polynomial function path planning curve and the hyperbolic tangent path planning curve to obtain a parallel parking path planning curve, i.e.,

[0054] f(x) = kg(x) + (1-k)y(x)

[0055] wherein k is a proportional coefficient in a range of 0-1;

[0056] the tracking control module is configured to perform tracking control of the vehicle according to the parallel parking path planning curve to complete vehicle parking operation.

[0057] Preferably, the first constraint unit further includes a positioning module including SLAM positioning configured to identify positions and relative positions of the vehicle and the parking space to be parked, and obtain boundary obstacle information and safety distance data of the parking space to be parked.

[0058] Preferably, the fusion unit further includes an iterative optimization module configured to determine the proportional coefficient k by an iterative optimization method.

[0059] ​​The application also discloses a vehicle loaded with the system or capable of implementing the parallel parking path planning method.

[0060] The application discloses an electronic device comprising a memory and a processor: the memory is used for storing a computer program; and the processor is used for implementing the parallel parking path planning method when executing the computer program.

[0061] The application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the method provided by the application.

[0062] Compared with the prior art, the parallel parking path planning method provided by the application comprises steps S1-S6, that is, the vehicle sensor is used to perceive parking space data and vehicle initial position and attitude data, a polynomial function relationship is established according to a parallel parking path of the vehicle, the first constraint condition is established according to the starting point coordinate and the parking end point coordinate of the vehicle, the second constraint condition that the first derivative of the path curve at the starting point and the end point is 0 is obtained according to the position and attitude constraint condition of the starting point and the end point of the path, the third constraint condition is obtained according to the position and attitude at the end of parking, the fourth constraint condition is established according to the constraint condition that the vehicle can safely drive out of the parking space without collision, the final polynomial coefficient value is obtained according to the first constraint condition, the second constraint condition, the third constraint condition and the fourth constraint condition, and the polynomial function path planning curve is obtained, the hyperbolic tangent path planning curve is obtained based on the hyperbolic tangent tanh function, the parallel parking path planning curve is obtained by fusing the polynomial function path planning curve and the hyperbolic tangent path planning curve, the vehicle is controlled according to the parallel parking path planning curve, and the vehicle parking operation is completed. The application also discloses a system for executing the above method. The method and the system fuse the polynomial function path planning curve and the hyperbolic tangent path planning curve obtained based on the hyperbolic tangent tanh function, the path curvature is continuous, easy to track, the hyperbolic tangent function compensates for the defect of excessive curvature of the commonly used quintic polynomial method in parking, relieves the steering pressure of the vehicle, can solve the defects of discontinuous path curvature, not easy to track, complex path structure composition, too many nodes and large fitting path error in parking, guarantees the smoothness of the parking path, improves the parking efficiency and the parking effect.

[0063] Other features and advantages of the application will be described in detail in the following specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0064] The accompanying drawings, which form a part of the present application, are intended to provide further understanding of the present application and are incorporated herein for a purpose of explanations. In the drawings:

[0065] Figure 1 Parallel parking coordinate system and constraint condition schematic diagram for the parallel parking path planning method of the present application;

[0066] Figure 2 Flow chart of the vehicle parallel parking for the present application;

[0067] Figure 3 Flow chart of the iterative method for obtaining the proportional coefficient k for the present application;

[0068] Figure 4 Parallel parking path trajectory diagram for the present application;

[0069] Figure 5 Path planning optimization curve comparison diagram for the present application. DETAILED DESCRIPTION

[0070] The specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to illustrate and explain the present application, and are not intended to limit the present application.

[0071] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts should fall within the scope of the present application.

[0072] It should be noted that the terms "first", "second", "third", "fourth" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0073] The arc and straight line method has simple structure, but the path curvature is discontinuous, not easy to track, and additional pressure is added to the steering system and tires, which damages the comfort of passengers. The spiral curve and B-spline curve are continuous in curvature and easy to track, but the structure is complex and the calculation amount is large, and the multi-path will increase the damage of the steering system and tires and the error of the actual parking path. The polynomial curve parking method has a large parking path curvature and a long curve. In order to solve the problems of the existing parking path planning method, such as discontinuous path curvature, large curvature, not easy to track, large fitting path error, which affects the automatic parking effect, and causes parking failure, a parallel parking path planning method is provided, as shown in Figures 1-3 The parallel parking path planning method comprises,

[0074] Step S1, the vehicle sensor senses the parking space data and the initial position and attitude data of the vehicle, and a polynomial function relationship is established according to the parallel parking path of the vehicle,

[0075] y(x)=a5x 5 +a4x 4 +a3x 3 +a2x 2 +a1x+a0

[0076] The first constraint condition is established by the starting point coordinate and the end point coordinate

[0077]

[0078]

[0079] The starting point coordinate value is obtained by the positioning system, and the end point coordinate value is obtained by the safety constraint of the vehicle and the parking space when parking is completed; a0, a1, a2, a3, a4 and a5 are polynomial coefficients;

[0080] Step S2, according to the position and attitude constraint condition of the starting point and the end point of the path, the second constraint condition that the first derivative of the path curve at the starting point and the end point is 0 is obtained, that is,

[0081]

[0082]

[0083] Step S3, according to the steering wheel back to normal when parking is completed, the slope in the parking path does not change at this time, the third constraint condition that the second derivative of the path curve at the end point is 0 is obtained, that is,

[0084] ​

[0085] Step S4, according to the vehicle safety no-collision driving out of the parking space constraint condition, the rear axle center point is just in The fourth constraint condition of the point is,

[0086]

[0087] Wherein, R1 is the minimum turning radius of the vehicle, and δ is the turning angle of the vehicle;

[0088] According to the first constraint condition, the second constraint condition, the third constraint condition, the fourth constraint condition, the a0, a1, a2, a3, a4, a5 polynomial coefficient values are obtained, and the polynomial function path planning curve is obtained;

[0089] Step S5, based on the hyperbolic tangent tanh function, a hyperbolic tangent path planning curve is obtained,

[0090]

[0091] Wherein, a, b, c, d are function coefficients respectively;

[0092] Step S6, the polynomial function path planning curve and the hyperbolic tangent path planning curve are fused, and a parallel parking path planning curve is obtained, that is,

[0093] f(x)=kg(x)+(1-k)y(x)

[0094] Wherein, k is a proportional coefficient, and the range is 0-1;

[0095] The vehicle is controlled according to the parallel parking path planning curve, and the vehicle parking operation is completed.

[0096] The parallel parking path planning method provided by the application comprises steps S1-S6, that is, the vehicle sensor is used to perceive the parking space data and the initial position and attitude data of the vehicle, a polynomial function relationship is established according to the vehicle parallel parking path, the vehicle starting point coordinates And the parking termination point coordinates The first constraint condition is established; the second constraint condition that the first derivative of the path curve at the starting point and the ending point is 0 is obtained according to the position and posture constraint condition of the starting point and the ending point of the path; the third constraint condition is obtained according to the position and posture at the end of parking and the constraint condition that the vehicle can safely drive out of the parking space without collision, and the fourth constraint condition is established at the position of the center point of the rear axle; finally, the polynomial coefficient value is obtained according to the first constraint condition, the second constraint condition, the third constraint condition and the fourth constraint condition, and the polynomial function path planning curve is obtained; the hyperbolic tangent path planning curve is obtained based on the hyperbolic tangent tanh function, and the parallel parking path planning curve is obtained by fusing the polynomial function path planning curve and the hyperbolic tangent path planning curve, the vehicle is controlled according to the parallel parking path planning curve, and the vehicle parking operation is completed. The method fuses the polynomial function path planning curve and the hyperbolic tangent path planning curve obtained based on the hyperbolic tangent tanh function, the path curvature is continuous, easy to track, the hyperbolic tangent function makes up for the defect of excessive curvature of the commonly used quintic polynomial method in parking, relieves the steering pressure of the vehicle, can solve the defects of discontinuous parking path curvature, not easy to track, complex path structure composition, too many nodes and large fitting path error, ensures the smoothness of the parking path, improves the parking efficiency and improves the parking effect.

[0097] Since the connection between the circular arc and the straight line is smoother and the curvature changes less, in order to facilitate the research and analysis of the parking process, the combination of the circular arc and the straight line is as shown in Figure 1 . The parking process is mainly divided into four sections, which are composed of circular arcs p1p2 and p3p4, and straight lines p0p1 and p2p3, and constitute a collision-free parallel parking curve path trajectory. O1 and O2 are the center points of the two circular arcs, H w is the distance between the parking space and the road boundary. P0 is the starting point of parking, p4 is the ending point of parking, K1 is the length of the straight line p0p1, K2 is the length of the straight line p2p3, and the coordinate system as shown in the figure is established with the left upper vertex O point of the parking space as the coordinate origin.

[0098] The coordinates of the vertex O of the parking space are: [x O , y O ] = [0, 0]

[0099] The coordinates of the vertex E of the parking space are: [x E , y E ] = [0, -W e ]

[0100] The coordinates of the vertex F of the parking space are: [x F , y F ] = [L e , -W e ]

[0101] The coordinates of the vertex G of the parking space are: [xG , y G ] = [L e , 0]

[0102] The coordinates of the left front vertex A of the vehicle are: [x A , y A ] = [L + S2, 0]

[0103] The coordinates of the right front vertex B of the vehicle are: [x B , y B ] = [L + S2, -W - S1]

[0104] The coordinates of the right rear vertex C of the vehicle are: [x C , y C ] = [S2, -W - S1]

[0105] The coordinates of the left rear vertex D of the vehicle are: [x D , y D ] = [S2, -S1]

[0106] The coordinates of the path point P0 are:

[0107] The coordinates of the path point P1 are:

[0108] The coordinates of the path point P2 are:

[0109] The coordinates of the path point P3 are:

[0110] The coordinates of the path point P4 are:

[0111] The expression of the straight line P2P3 is:

[0112] Since the hyperbolic tangent Tanh function curve is an S-shaped curve, the path planning design for the automatic driving lane changing trajectory has the advantages of curvature continuous path smoothing, Figure 5 As shown in the preferred case of the present application, in step S5, the function coefficients a, b, c, d are obtained through the position and attitude constraint relationship of the vehicle parking process of the first constraint condition, the second constraint condition, the third constraint condition and the fourth constraint condition.

[0113] The initial position and the terminal position of the hyperbolic tangent function have a small curvature, but the curvature in the middle part is large, which is easy to exceed the limit value of the steering mechanism, resulting in parking failure. The curvature change law of the quintic polynomial function and the hyperbolic tangent function is just opposite, the curvature of the starting and terminal position is large, and the curvature of the middle part is small. Therefore, in order to ensure the smoothness of the path, the continuity of the curvature and the more gentle change of the curvature, reduce the pressure of the steering mechanism, in the preferred case of the present application, the proportional coefficient k is determined by the iterative optimization method in step S6. The iterative process is shown in Figure 3 The path planning curve of the vehicle from a starting point to a terminal point can be seen from Figure 4 It can be seen that the parallel parking path planning method meets the collision constraint condition in the parking process, and the vehicle does not collide with the surrounding obstacles, and the path is smooth and meets the parking requirements.

[0114] The equivalent front wheel steering angle is close to 0 at the starting point and the terminal point of parking, and the maximum value does not exceed the limit value of the vehicle, which meets the constraint of the vehicle steering mechanism. The yaw angle of the vehicle at the starting point and the terminal point is 0, which meets the requirement that the vehicle pose is parallel to the parking space after parking. The curvature of the parking path at the starting point and the terminal point is 0, and the path curvature of the whole parking route is within the allowable range, and the curvature is continuous.

[0115] In order to better track the vehicle in the parking process in real time, and judge whether to park along the planned path, in the preferred case of the present application, the relative position of the vehicle and the parking space is obtained by the vehicle sensor, and the driving track of the center point of the rear axle of the vehicle is taken as the tracking control basis in the parallel parking path planning curve.

[0116] The present application also discloses a system for performing the above parallel parking path planning method, the system comprises,

[0117] The first constraint unit comprises a sensor module, and the sensor module at least comprises a visual sensor and an ultrasonic sensor; the sensor module is used for sensing the parking space data and the initial position and attitude data of the vehicle through the vehicle sensor, and establishing a polynomial function relationship according to the parallel parking path of the vehicle,

[0118] y(x)=a5x 5 +a4x 4 +a3x 3 +a2x 2 +a1x+a0

[0119] The first constraint condition is established by the starting point coordinates of the vehicle and the terminal point coordinates of parking,

[0120]

[0121]

[0122] Wherein, the starting point coordinate value is obtained by the positioning system, and the terminal point coordinate value is obtained by the safety constraint between the vehicle and the parking space when the parking is finished; a0, a1, a2, a3, a4, a5 are polynomial coefficients respectively;

[0123] The second constraint unit is used for obtaining a second constraint condition that the first derivative of the path curve at the starting point and the terminal point is 0 according to the position and posture constraint condition of the starting point and the terminal point of the path, that is,

[0124]

[0125]

[0126] The third constraint unit is used for obtaining a third constraint condition that the second derivative of the path curve at the terminal point is 0 according to the condition that the steering wheel is returned to normal when the parking is finished, that is, the slope in the parking path does not change at this time,

[0127]

[0128] The fourth constraint unit includes a calculation module, which is used for obtaining a fourth constraint condition that the center point of the rear axle is just at the point according to the constraint condition that the vehicle is safe and collision-free when driving out of the parking space, that is,

[0129]

[0130] Wherein, R1 is the minimum turning radius of the vehicle, and δ is the turning angle of the vehicle;

[0131] The calculation module is used for obtaining the polynomial coefficient values a0, a1, a2, a3, a4, a5 according to the first constraint condition, the second constraint condition, the third constraint condition and the fourth constraint condition, and obtaining the polynomial function path planning curve.

[0132] The construction unit is used for obtaining a hyperbolic tangent path planning curve based on the hyperbolic tangent tanh function,

[0133]

[0134] Wherein, a, b, c, d are function coefficients respectively;

[0135] The fusion unit includes a tracking control module, which is used for fusing the polynomial function path planning curve and the hyperbolic tangent path planning curve to obtain a parallel parking path planning curve, that is,

[0136] f(x)=kg(x)+(1-k)y(x) ​

[0137] wherein k is a proportionality coefficient, ranging from 0 to 1;

[0138] The tracking control module is used for tracking control of the vehicle according to the parallel parking path planning curve, so as to complete the vehicle parking operation.

[0139] The system provided by the application establishes a polynomial function relationship according to the vehicle parallel parking path, obtains the first constraint condition by the vehicle starting point coordinate and the parking end point coordinate , the second constraint unit obtains the second constraint condition that the first derivative of the path curve at the starting point and the end point is 0 according to the position and attitude constraint condition of the starting point and the end point of the path, the third constraint unit obtains the third constraint condition according to the position and attitude at the end of parking, the fourth constraint unit establishes the fourth constraint condition according to the constraint condition that the vehicle can safely drive out of the parking space without collision, and the rear axle center point establishes the fourth constraint condition, finally, the polynomial coefficient value is obtained according to the first constraint condition, the second constraint condition, the third constraint condition and the fourth constraint condition, and the polynomial function path planning curve is obtained, the hyperbolic tangent function tanh function is obtained based on the construction unit to obtain the hyperbolic tangent path planning curve, and the parallel parking path planning curve is obtained by fusing the polynomial function path planning curve and the hyperbolic tangent path planning curve through the fusion unit, the vehicle performs tracking control according to the parallel parking path planning curve, and the vehicle parking operation is completed. Figure 5 The system for executing the above method disclosed by the application fuses the polynomial function path planning curve and the hyperbolic tangent path planning curve obtained based on the hyperbolic tangent tanh function, the path curvature is continuous, easy to track, the hyperbolic tangent function compensates for the defect of excessive curvature of the commonly used quintic polynomial method in parking, relieves the steering pressure of the vehicle, can solve the defects of discontinuous parking path curvature, not easy to track, complex path structure composition, too many nodes and large fitting path error, ensures the smoothness of the parking path, improves the parking efficiency and the parking effect.

[0140] The path planning of the automatic parking system is performed by sensing the parking space information by the vision and ultrasonic sensors in the sensing module and determining the parking space type, combining the relative position of the vehicle and the parking space, the kinematics of the vehicle, the initial position and attitude of the vehicle, the collision of the vehicle and other constraint conditions, taking the driving track of the rear axle center point of the vehicle as the reference, generating the path curve from the starting point to the parking end point, and the path curve needs to meet the conditions of continuity, obstacle avoidance and easy tracking, and the specific process is shown in Figure 2 .

[0141] In order to better complete parking in the room, in the preferred case of the present application, the first constraint unit further comprises a positioning module, the positioning module comprising a simultaneous localization and mapping (SLAM) for identifying the position and relative position of the vehicle and the parking space to be parked, and obtaining the boundary obstacle information and safety distance data of the parking space to be parked.

[0142] In order to better determine the fusion coefficient k, in the preferred case of the present application, the fusion unit further comprises an iterative optimization module for determining the fusion coefficient k by an iterative optimization method.

[0143] The present application also discloses a vehicle loaded with the system comprising the above, or capable of realizing the parallel parking path planning method as described above.

[0144] The present application also discloses an electronic device comprising a memory and a processor: the memory is used for storing a computer program; and the processor is used for realizing the above method when the computer program is executed.

[0145] Further, the present application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the method provided by the present application.

[0146] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, some steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0147] In the above embodiments, the description of each embodiment is focused on, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0148] In the several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the units is only a logical function division. There can be another division during actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical or other forms.

[0149] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0150] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0151] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application, essentially or the part that contributes to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a mobile terminal, a server or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various program code storage media.

[0152] The above is only the preferred embodiment of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A parallel parking path planning method, characterized in that, The parallel parking path planning method includes, Step S1: Using vehicle sensors, data on the parking space and the vehicle's initial position and attitude are obtained. A polynomial function relationship is then established based on the vehicle's parallel parking path. From the vehicle's starting point coordinates [ [and the coordinates of the parking termination point] Establish the first constraint. The starting point coordinates are obtained through the positioning system, and the ending point coordinates are obtained through the safety constraints between the vehicle and the parking space when parking ends. , , , , , These are the polynomial coefficients; Step S2: Based on the position and attitude constraints of the starting and ending points of the path, the second constraint condition is obtained: the first derivative of the path curve at the starting and ending points is 0. Step S3: Based on the fact that when parking ends, the steering wheels are back to positive, and the slope of the parking path does not change at this time, the third constraint condition is obtained: the second derivative of the path curve at the termination point is 0. Step S4, based on the constraint that the vehicle safely exits the parking space without collision, the center point of the rear axle is exactly at P3 ( The fourth constraint condition for point is, in, , , This is the vehicle's minimum turning radius. The turning angle of the vehicle; Based on the first, second, third, and fourth constraints, the following is obtained: , , , , , The polynomial coefficients are calculated, and the polynomial function path planning curve is obtained. Step S5: Obtain the hyperbolic tangent path planning curve based on the hyperbolic tangent tanh function. Where a, b, c, and d are the function coefficients; Step S6: Combine the polynomial function path planning curve and the hyperbolic tangent path planning curve to obtain the parallel parking path planning curve, which is... Where k is the proportionality coefficient, ranging from 0 to 1; The vehicle is tracked and controlled according to the parallel parking path planning curve to complete the parking operation.

2. The parallel parking path planning method according to claim 1, characterized in that, In step S5, the function coefficients a, b, c, and d are obtained through the position and attitude constraint relationships during vehicle parking based on the first, second, third, and fourth constraint conditions.

3. The parallel parking path planning method according to claim 1, characterized in that, In step S6, the proportional coefficient k is determined by an iterative optimization method.

4. The parallel parking path planning method according to any one of claims 1-3, characterized in that, The relative position of the vehicle and the parking space is obtained by vehicle sensors, and the driving trajectory of the vehicle's rear axle center point is used as the basis for tracking control in the parallel parking path planning curve.

5. A system for performing the parallel parking path planning method as described in any one of claims 1-4, characterized in that, The system includes, The first constraint unit includes a sensor module, which includes at least a vision sensor and an ultrasonic sensor; it is used to perceive parking space data and vehicle initial position and attitude data through vehicle sensors, and to establish a polynomial function relationship based on the vehicle's parallel parking path. From the vehicle's starting point coordinates [ [and the coordinates of the parking termination point] Establish the first constraint. The starting point coordinates are obtained through the positioning system, and the ending point coordinates are obtained through the safety constraints between the vehicle and the parking space when parking ends. , , , , , These are the polynomial coefficients; The second constraint element is used to obtain the second constraint condition that the first derivative of the path curve at the starting and ending points is 0, based on the position and attitude constraints of the starting and ending points of the path. The third constraint unit is used to determine the third constraint condition where the second derivative of the path curve at the termination point is 0, based on the fact that when parking ends, the steering wheels are in the positive position, and the slope of the parking path does not change. The fourth constraint unit, including a calculation module, is used to determine the rear axle center point as being exactly at P3, based on the constraint condition that the vehicle safely exits the parking space without collision. The fourth constraint condition for point is, in, , , This is the vehicle's minimum turning radius. The turning angle of the vehicle; The calculation module is used to obtain the results based on the first constraint, the second constraint, the third constraint, and the fourth constraint. , , , , , The polynomial coefficients are calculated, and the polynomial function path planning curve is obtained. The building block is used to obtain the hyperbolic tangent path planning curve based on the hyperbolic tangent tanh function. Where a, b, c, and d are the function coefficients; The fusion unit, including the tracking control module, is used to fuse the polynomial function path planning curve and the hyperbolic tangent path planning curve to obtain the parallel parking path planning curve, i.e., Where k is the proportionality coefficient, ranging from 0 to 1; The tracking control module is used to track and control the vehicle according to the parallel parking path planning curve to complete the vehicle parking operation.

6. The system according to claim 5, characterized in that, The first constraint unit further includes a positioning module, which includes SLAM positioning, used to identify the position and relative position of the vehicle and the parking space, and to obtain information on obstacles at the boundary of the parking space and safe distance data.

7. The system according to any one of claims 5-6, characterized in that, The fusion unit also includes an iterative optimization module, which is used to determine the scaling factor k through an iterative optimization method.

8. A vehicle, characterized in that, The vehicle is equipped with a system including any one of claims 5-6, or is capable of implementing the parallel parking path planning method as described in any one of claims 1-4.

9. An electronic device, characterized in that, Includes a memory and a processor: the memory is used to store a computer program; the processor is used to implement the parallel parking path planning method as described in any one of claims 1-4 when the computer program is executed.

10. A machine-readable storage medium storing instructions for causing a machine to perform the parallel parking path planning method according to any one of claims 1-4 of this application.

Images