Parking track real-time planning method and system

Abstract

The invention provides a parking track real-time planning method and system, and the method comprises the steps: obtaining an initial parking track for vehicle planning, and calculating the target point position of a parking space according to the four corner point positions of a pre-parking parking space if the current vehicle position is the last segment of the initial parking track; according to the current position of the vehicle, the position of the target point and the detected obstacle information, generating an extension node of a planned path through a hybrid A algorithm; and according to the expansion nodes and the Reeds-Shepp curve, a parking garage entering track is generated in a combined mode. Through the scheme, the success rate of track real-time planning can be improved, the time consumption of track planning is reduced, and the problems of long time consumption or planning failure and the like of traditional real-time parking route planning are avoided.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of automatic parking, and particularly relates to a parking trajectory real-time planning method and system. BACKGROUND

[0002] In the automatic parking process, the trajectory is generally re-planned when a new obstacle is encountered or the control error is not up to standard. However, starting to re-plan the trajectory only in the above two cases will lead to the inability to eliminate the positioning, perception and control errors in time, and further lead to the parking position attitude being not correct, and the occurrence of left deviation, right deviation or even line compression. At present, due to the limited computing power of the vehicle end, if the real-time planning method is used, the problems of long planning time or planning failure may occur. SUMMARY

[0003] Therefore, the embodiments of the present application provide a parking trajectory real-time planning method and system to solve the problems of long planning time or planning failure in the current parking real-time route planning.

[0004] In a first aspect of the embodiments of the present application, a parking trajectory real-time planning method is provided, comprising: obtaining an initial parking trajectory planned by a vehicle, and if a current vehicle position is a last segment of the initial parking trajectory, calculating a target point position of a parking space according to four corner point positions of a pre-parking space; generating an extended node of a planning path by a hybrid A algorithm according to the current vehicle position, the target point position and detected obstacle information; generating a parking-in warehouse trajectory by combination according to the extended node and a Reeds-Shepp curve.

[0005] In a second aspect of the embodiments of the present application, a parking trajectory real-time planning system is provided, comprising: a target point planning module, configured to obtain an initial parking trajectory planned by a vehicle, and if a current vehicle position is a last segment of the initial parking trajectory, calculate a target point position of a parking space according to four corner point positions of a pre-parking space; a path planning module, configured to generate an extended node of a planning path by a hybrid A algorithm according to the current vehicle position, the target point position and detected obstacle information; a trajectory generation module, configured to generate a parking-in warehouse trajectory by combination according to the extended node and a Reeds-Shepp curve.

[0006] In a third aspect of the embodiments of the present application, an electronic device is provided, comprising a memory, a processor and a computer program stored in the memory and executable in the processor, and the processor implements the steps of the method according to the first aspect of the embodiments of the present application when executing the computer program.

[0007] In a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present invention.

[0008] In this embodiment of the invention, based on the last segment of the initial parking trajectory, through hybrid A The algorithm, in conjunction with Reeds-Shepp curves, constructs parking trajectories, significantly improving the success rate of real-time trajectory planning and reducing its time consumption. This avoids the problems of long planning times or failures associated with traditional real-time parking route planning. Furthermore, the smooth and easily controllable parking trajectory ensures the vehicle's posture is centered in the final parking space, enhancing the effectiveness of automated parking. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating a real-time parking trajectory planning method according to an embodiment of the present invention. Figure 2 This is a schematic diagram of extended node pruning provided in one embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a real-time parking trajectory planning system provided in one embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0011] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0012] It should be understood that the terms "comprising" and other similar expressions in the specification, claims, and accompanying drawings of this invention are intended to cover a non-exclusive inclusion, such as a process, method, system, or apparatus that includes a series of steps or units and is not limited to the listed steps or units. Furthermore, "first" and "second" are used to distinguish different objects and are not intended to describe a specific order.

[0013] Please see Figure 1 A flowchart illustrating a real-time parking trajectory planning method provided in this embodiment of the invention includes: S101. Obtain the initial parking trajectory of the vehicle plan. If the current vehicle position is the last segment of the initial parking trajectory, calculate the target point position of the parking space based on the four corner positions of the pre-parking space. The initial parking trajectory generated by the vehicle decision module is obtained. The initial parking trajectory consists of multiple segments. When the vehicle is detected to be in the last segment of the parking trajectory, due to errors in vehicle perception and control, or the appearance of new obstacles, the last segment of the parking trajectory needs to be optimized and adjusted.

[0014] The initial parking trajectory is segmented based on changes in vehicle gear information. Since the vehicle needs to adjust its position during parking, the trajectory can be segmented based on gear shifts; for example, by dividing the trajectory into forward and reverse gears, each shift creates a segment of the parking trajectory.

[0015] By using vehicle-mounted cameras, ultrasonic radar, and other devices, the coordinates of the corner points of the pre-parking space can be detected in the vehicle's own coordinate system or in the overhead plane coordinate system, and then the target point position can be determined based on the positions of the four corner points of the parking space.

[0016] The target point location refers to the coordinates of the vehicle's rear axle center in an ideal state after the vehicle has been parked in the parking space. The ideal position of the vehicle in the parking space can be determined based on the rear axle center, that is, the final position of the center point between the two rear wheels of the vehicle within the parking space. To determine whether the vehicle is in an ideal parking state, the distances from the left and right sides to the edge of the parking space are equal, and the distances from the front and rear sides to the edge of the parking space are also equal.

[0017] S102. Based on the vehicle's current position, the target point's position, and the detected obstacle information, through a hybrid A... The algorithm generates extended nodes for the planned path; Mixed A (Hybrid A) The algorithm is a path planning algorithm specifically designed for vehicles with nonholonomic constraints. Due to the hybrid A To consider vehicle kinematics, compared to traditional A... The heading angle dimension has been added, and its extended nodes need to consider vehicle kinematics. Hybrid A The algorithm node expansion usually starts from the current node, and samples the vehicle's motion trajectory from the front and back according to the pre-set motion sampling step size and the maximum turning radius. Collision detection is performed on the sampled motion trajectory, and the motion trajectory that meets the vehicle motion conditions can be used as the candidate node, that is, the expanded child node.

[0018] Optionally, for mixture A The algorithm prunes the expanded nodes, restricting their expansion direction to a backward direction. Since the current vehicle is in the last segment of the parking trajectory, it's necessary to restrict its expanded nodes to a backward direction, such as... Figure 2 As shown, the gray dots represent new nodes that expand backward.

[0019] It is understandable that a mixture of A The generated path is usually continuous, but due to its discrete search characteristics, there may be some non-smooth parts (such as abrupt changes in curvature). Therefore, numerical optimization methods can be used to solve the problem and smooth the coarse trajectory.

[0020] S103. Based on the extended nodes and the Reeds-Shepp curve, generate the parking trajectory.

[0021] The Reeds-Shepp curve, or RS curve for short, is an algorithm used for path planning in vehicles or robots. It solves the shortest path problem for vehicles moving in a plane, considering both forward and backward motion. Its core is to add a backward movement function to the Dubins curve, generating paths by combining different motion modes (forward, backward, left turn, right turn). In this embodiment, only backward trajectories are selected from the RS curve; that is, only the L-shaped path is retained. - R - S - These three curve combinations, L - Indicates that the vehicle is turning left and reversing, R - Indicates that the vehicle is turning right and reversing, S - This indicates that the vehicle is moving straight or reversing.

[0022] Specifically, when it is detected that the extended node child node and the target point can be connected based on the Reeds-Shepp curve, a connection curve between the extended node child node and the parent node is constructed, as well as a Reeds-Shepp curve between the extended node child node and the target point. The connection curve and the Reeds-Shepp curve are combined to generate a parking trajectory.

[0023] Mixed A The algorithm searches a discrete grid map, where each expanded node represents a state (including position and orientation). As it expands from one node to the next, it generates a curve that satisfies vehicle kinematic constraints. These constraints include the vehicle's turning radius and forward / reverse direction. If a child node of the expanded node can be connected to the target point using a Reeds-Shepp curve, the current child node and the target point are connected using an RS curve. This indicates successful planning and no collisions, allowing the generation of a parking trajectory.

[0024] Treating the next node of the extended node as a child node, the current node becomes the parent node, and a connection curve is constructed between them. If the parent node also has a parent node above it, a connection curve is also constructed between them. (Mixed A) During the search process, each node records the curve segments extending from its parent node to that node. The final path is a continuous path composed of these curve segments, plus the RS curve. The combination of the continuous path and the RS curve yields the parking trajectory.

[0025] In this embodiment, by obtaining the last segment of the initial parking trajectory, the mixed A By combining the algorithm with Reeds-Shepp curves to construct the corresponding parking trajectory, the success rate of real-time trajectory planning can be greatly improved, the planning time can be reduced, the computational load is small, and the planning process is relatively simple. At the same time, the parking trajectory is smooth and easy to control, ensuring that the vehicle's posture is centered when it finally enters the parking space.

[0026] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0027] Figure 3 This is a schematic diagram of a real-time parking trajectory planning system provided in an embodiment of the present invention. The system includes: The target point planning module 310 is used to obtain the initial parking trajectory of the vehicle. If the current vehicle position is the last segment of the initial parking trajectory, the target point position of the parking space is calculated based on the four corner positions of the pre-parking space. The acquisition of the initial parking trajectory for vehicle planning includes: The initial parking trajectory is segmented based on changes in vehicle gear information.

[0028] Preferably, the target point is the coordinate position of the rear axle center of the vehicle under ideal conditions after the vehicle has been parked in the parking space.

[0029] Path planning module 320 is used to plan the path based on the vehicle's current position, the target point position, and detected obstacle information, through a hybrid A / B algorithm. The algorithm generates extended nodes for the planned path; Optionally, the path planning module includes: Pruning unit, used for mixing A The algorithm prunes the expanded nodes, restricting their expansion direction to a backward direction.

[0030] The trajectory generation module 330 is used to generate a parking trajectory by combining the extended nodes and the Reeds-Shepp curve.

[0031] The step of generating the parking trajectory by combining the extended nodes and the Reeds-Shepp curve includes: When it is detected that the extended node child node and the target point can be connected based on the Reeds-Shepp curve, a connection curve between the extended node child node and the parent node is constructed, as well as a Reeds-Shepp curve between the extended node child node and the target point. The connection curve and the Reeds-Shepp curve are combined to generate the parking trajectory.

[0032] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system and modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0033] Figure 4 This is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device is used for real-time parking path planning. Figure 4 As shown, the electronic device 4 in this embodiment includes a memory 410, a processor 420, and a system bus 430. The memory 410 includes an executable program 4101 stored thereon. As those skilled in the art will understand, Figure 4 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0034] The following is combined with Figure 4 A detailed introduction to each component of the electronic device: The memory 410 can be used to store software programs and modules. The processor 420 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 410. The memory 410 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as cached data), etc. In addition, the memory 410 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0035] The memory 410 contains an executable program 4101 for a network request method. This executable program 4101 can be divided into one or more modules / units, which are stored in the memory 410 and executed by the processor 420 to achieve automatic parking trajectory planning, etc. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, describing the execution process of the computer program 4101 in the electronic device 4. For example, the computer program 4101 can be divided into functional modules such as a target point planning module, a path planning module, and a trajectory generation module.

[0036] The processor 420 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 410, and by calling data stored in the memory 410, it performs various functions and processes data, thereby monitoring the overall status of the electronic device. Optionally, the processor 420 may include one or more processing units; preferably, the processor 420 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, application programs, etc., and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 420.

[0037] The system bus 430 is used to connect various functional components inside the computer, transmitting data, address, and control information. Its type can be, for example, a PCI bus, an ISA bus, or a CAN bus. Instructions from the processor 420 are transmitted to the memory 410 via the bus, and the memory 410 sends data back to the processor 420. The system bus 430 is responsible for data and instruction exchange between the processor 420 and the memory 410. Of course, the system bus 430 can also connect to other devices, such as network interfaces and display devices.

[0038] In this embodiment of the invention, the executable program executed by the processor 420 included in the electronic device includes: Obtain the initial parking trajectory planned by the vehicle. If the current vehicle position is the last segment of the initial parking trajectory, calculate the target point position of the parking space based on the positions of the four corner points of the pre-parking space. Based on the vehicle's current location, the target point's location, and detected obstacle information, through a hybrid A... The algorithm generates extended nodes for the planned path; Based on the extended nodes and the Reeds-Shepp curve, a parking trajectory is generated.

[0039] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0040] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0041] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions 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 real-time parking trajectory planning method, characterized in that, include: Obtain the initial parking trajectory planned by the vehicle. If the current vehicle position is the last segment of the initial parking trajectory, calculate the target point position of the parking space based on the positions of the four corner points of the pre-parking space. Based on the vehicle's current location, the target point's location, and detected obstacle information, through a hybrid A... The algorithm generates extended nodes for the planned path; Based on the extended nodes and the Reeds-Shepp curve, a parking trajectory is generated.

2. The method according to claim 1, characterized in that, The process of obtaining the initial parking trajectory planned for the vehicle includes: The initial parking trajectory is segmented based on changes in vehicle gear information.

3. The method according to claim 1, characterized in that, The target point location is the ideal coordinate position of the rear axle center of the vehicle after it has been parked in the parking space.

4. The method according to claim 1, characterized in that, The method of mixing A The extended nodes generated by the algorithm for the planned path also include: For mixture A The algorithm prunes the expanded nodes, restricting their expansion direction to a backward direction.

5. The method according to claim 1, characterized in that, The step of generating the parking trajectory based on the extended nodes and the Reeds-Shepp curve includes: When it is detected that the extended node child node and the target point can be connected based on the Reeds-Shepp curve, a connection curve between the extended node child node and the parent node is constructed, as well as a Reeds-Shepp curve between the extended node child node and the target point. The connection curve and the Reeds-Shepp curve are combined to generate the parking trajectory.

6. A real-time parking trajectory planning system, characterized in that, include: The target point planning module is used to obtain the initial parking trajectory of the vehicle. If the current vehicle position is the last segment of the initial parking trajectory, the target point position of the parking space is calculated based on the four corner positions of the pre-parking space. The path planning module is used to determine the path based on the vehicle's current position, the target point's position, and detected obstacle information, through a hybrid A / B algorithm. The algorithm generates extended nodes for the planned path; The trajectory generation module is used to generate a parking trajectory by combining the extended nodes and the Reeds-Shepp curve.

7. The system according to claim 6, characterized in that, The path planning module includes: Pruning unit, used for mixing A The algorithm prunes the expanded nodes, restricting their expansion direction to a backward direction.

8. The system according to claim 6, characterized in that, The process of generating the parking trajectory by combining the extended nodes and the Reeds-Shepp curve includes: When it is detected that the extended node child node and the target point can be connected based on the Reeds-Shepp curve, a connection curve between the extended node child node and the parent node is constructed, as well as a Reeds-Shepp curve between the extended node child node and the target point. The connection curve and the Reeds-Shepp curve are combined to generate the parking trajectory.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of a real-time parking trajectory planning method as described in any one of claims 1 to 5.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed, it implements the steps of a real-time parking trajectory planning method as described in any one of claims 1 to 5.

Images