A parking path planning method, device and equipment of a vehicle and a storage medium

Abstract

A parking path planning method, device and equipment of a vehicle and a storage medium are disclosed. The method comprises: if a parking event of the vehicle is detected, a dynamic model of the vehicle is constructed, and constraint conditions corresponding to the dynamic model are determined; based on a current position and a target parking position of the vehicle, a preliminary path planning is performed according to the constraint conditions, and at least two candidate parking planning routes are determined; based on a preset adaptive cothermal start algorithm, the size of a convex polygon region corresponding to a target obstacle around the vehicle is iteratively adjusted according to attribute information of the target obstacle, and accurate path planning is performed according to the attribute information of the target obstacle after the iterative adjustment, and an optimal parking route is determined. By using the vehicle dynamic model, combining more comprehensive constraint conditions, and using the adaptive cothermal start algorithm, the optimal parking route of the vehicle is optimized in an iterative manner, and more accurate and effective automatic parking can be achieved.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving, and more particularly to a parking path planning method, apparatus, device, and storage medium for vehicles. Background Technology

[0002] With the development of intelligent vehicles and autonomous driving technology, automatic parking technology, as a key component of intelligent vehicle technology, has become a hot research topic. The purpose of automatic parking is to improve the safety and comfort of autonomous driving, enabling drivers to automatically drive the car and park it in the corresponding parking space. These operations often require a high level of driver skill and concentration. Automatic parking technology can safely and quickly complete parking operations without a driver, and while reducing the possibility of accidents during parking, it can effectively improve driving comfort. Furthermore, the development of automatic parking technology can, to a certain extent, effectively promote the development of intelligent vehicles and autonomous driving technology.

[0003] Therefore, how to better model vehicles and consider more comprehensive information about the vehicle itself and its surrounding environment to determine the most efficient parking route, thereby improving the safety and efficiency of automatic parking, is an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a parking path planning method, device, equipment, and storage medium for vehicles. Based on a vehicle dynamics model, combined with more comprehensive constraints, and employing an adaptive hot-start algorithm, iteratively optimizes the best parking route for the vehicle, enabling more precise and effective automatic parking.

[0005] According to one aspect of the present invention, a parking path planning method for a vehicle is provided, comprising:

[0006] If a parking event is detected, a dynamic model of the vehicle is constructed, and the constraints corresponding to the dynamic model are determined.

[0007] Based on the vehicle's current location and the target parking location, and according to the aforementioned constraints, preliminary path planning is performed to determine at least two candidate parking planning routes.

[0008] Based on the preset adaptive hot start algorithm, the size of the convex polygon region corresponding to the target obstacle is iteratively adjusted according to the attribute information of the target obstacle around the vehicle. Based on the attribute information of the target obstacle after iterative adjustment, accurate path planning is performed to determine the optimal parking route.

[0009] According to another aspect of the present invention, a parking path planning device for a vehicle is provided, comprising:

[0010] The condition determination module is used to construct a dynamic model of the vehicle and determine the constraint conditions corresponding to the dynamic model if a parking event is detected.

[0011] The candidate route determination module is used to perform preliminary path planning based on the vehicle's current location and the target parking location, according to the constraints, and determine at least two candidate parking planning routes.

[0012] The optimal route determination module is used to perform precise path planning based on a preset adaptive hot start algorithm, according to the attribute information of target obstacles around the vehicle, to determine the optimal parking route.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle parking path planning method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle parking path planning method according to any embodiment of the present invention.

[0018] The technical solution of this invention, upon detecting a parking event, constructs a dynamic model of the vehicle and determines the corresponding constraints. Based on the vehicle's current position and the target parking position, and according to the constraints, preliminary path planning is performed to determine at least two candidate parking routes. Based on a preset adaptive hot-start algorithm, the size of the convex polygon region corresponding to the target obstacle is iteratively adjusted according to the attribute information of the target obstacle around the vehicle. Then, based on the adjusted attribute information of the target obstacle, precise path planning is performed to determine the optimal parking route. In this way, based on the vehicle dynamic model, combined with more comprehensive constraints, and using an adaptive hot-start algorithm, the optimal parking route can be found iteratively, helping to achieve accurate and effective automatic parking and improving the safety of automatic parking.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0021] Figure 1A This is a flowchart of a vehicle parking path planning method provided in Embodiment 1 of the present invention;

[0022] Figure 1B This is a schematic diagram of the geometric structure of the vehicle provided in Embodiment 1 of the present invention;

[0023] Figure 1C This is a geometrical schematic diagram of the vehicle and the target obstacle provided in Embodiment 1 of the present invention;

[0024] Figure 1D This is a schematic diagram of target obstacle size scaling provided in Embodiment 1 of the present invention;

[0025] Figure 2 This is a structural block diagram of a vehicle parking path planning device provided in Embodiment 2 of the present invention;

[0026] Figure 3 This is a schematic diagram of the structure of the electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," "target," "candidate," "alternative," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1A This is a flowchart of a vehicle parking path planning method provided in Embodiment 1 of the present invention; Figure 1B This is a schematic diagram of the geometric structure of the vehicle provided in Embodiment 1 of the present invention; Figure 1C This is a geometrical schematic diagram of the vehicle and the target obstacle provided in Embodiment 1 of the present invention; Figure 1D This is a schematic diagram of target obstacle size scaling provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where a vehicle plans the optimal parking route based on a dynamic model, constraints, and obstacle attributes. This method can be executed by the vehicle's parking path planning device, which can be implemented in software and / or hardware and integrated into electronic devices that implement vehicle parking path planning functions, such as in autonomous or driverless vehicles, and executed by the vehicle's control module. Figure 1A As shown, the method includes:

[0031] S101. If a parking event for the vehicle is detected, construct a dynamic model of the vehicle and determine the corresponding constraints of the dynamic model.

[0032] A parking event refers to the event of parking the vehicle in a parking space. A dynamics model is a model that represents the vehicle's motion state. Constraints are the conditions that the relevant parameters in the pre-defined vehicle dynamics model must satisfy.

[0033] Optionally, the constraints may include at least one of the following: kinematic constraints, collision avoidance constraints, boundary condition constraints, and cost minimization constraints.

[0034] Optionally, boundary condition constraints refer to the conditions that the vehicle's velocity, acceleration, front wheel steering angle, and angular velocity are expected to be zero at the end of the operation. Specifically, this can be expressed as the following formula:

[0035] [v(t f ),φ(t f ),a(t f ),ω(t f )]=[0,0,0,0]

[0036] Where, v(t) f ),φ(t f ),a(t f ) and ω(t f ) represent the end time t of the vehicle's operation, respectively. f At that time, the vehicle's speed, the steering angle of the front wheels, acceleration, and angular velocity.

[0037] Optionally, the cost minimization constraint refers to the constraint conditions generated based on a preset cost calculation method, aiming to minimize the cost required for the vehicle to run along the planned route. For example, based on the idea of ​​minimizing the time the vehicle takes to travel along the planned route and maximizing the distance from surrounding obstacles during the journey, the following cost function can be determined:

[0038]

[0039] Where J represents the cost assessment value, t f λ represents the end time of the vehicle's operation. ω >0 represents the weight parameter, d ik (τ) can represent the Euclidean distance from the vehicle position x,y to the kth target obstacle at time τ, or it can represent the Euclidean distance from the i-th vehicle position x,y to the kth target obstacle at time τ.

[0040] Optionally, a dynamic model of the vehicle is constructed, including: based on the bicycle model, the dynamic model of the vehicle is constructed according to the calculation relationship between the vehicle-related parameters; the vehicle-related parameters include at least one of the following: the vehicle's running time, the vehicle's position information in the vehicle coordinate system, the vehicle's speed, acceleration, the steering angle and angular velocity of the vehicle's front wheels, the distance between the vehicle's front and rear wheels, and the time when the vehicle's running ends.

[0041] Here, the vehicle's running time t represents the time the vehicle spends running. The vehicle's position information in the vehicle coordinate system can include both horizontal and vertical coordinate information.

[0042] For example, considering that when a vehicle parks itself, it can be understood as navigating through an extremely narrow environment, therefore the vehicle speed will not be too high. This invention considers using a bicycle model to construct the dynamics model of the autonomous vehicle. The vehicle's geometry is as follows: Figure 1B As shown. The dynamic model of the autonomous vehicle is shown below:

[0043]

[0044] In this system, the x-axis represents the horizontal coordinate of the vehicle coordinate system; for example, true north can be pre-specified as the horizontal direction. The y-axis represents the vertical coordinate of the vehicle coordinate system; for example, true east can be pre-specified as the vertical direction. t represents the time of the vehicle's movement. t=0 indicates the vehicle's current time. f The endpoint of the vehicle's motion can be the moment the vehicle reaches the parking space. x(t) and y(t) represent the vehicle's horizontal and vertical coordinates at time t, respectively. v(t) represents the vehicle's velocity at time t, a(t) represents the vehicle's acceleration at time t, φ(t) represents the steering angle of the front wheels at time t, ω(t) represents the angular velocity of the car at time t, and L... w This represents the distance between the front and rear wheels of the car. θ refers to the angle between the vehicle's direction of travel and the x-axis. θ(t) refers to the angle between the vehicle's direction of travel and the x-axis at time t.

[0045] Optionally, kinematic constraints on vehicle acceleration, speed, front wheel steering angle, and angular velocity are determined based on preset maximum permissible acceleration, maximum permissible speed, maximum permissible front wheel steering angle, and maximum permissible angular velocity; collision avoidance constraints are determined based on the geometric relationship that must be satisfied between the rectangular region corresponding to the vehicle and the convex polygonal region corresponding to the target obstacle to avoid intersection; and boundary condition constraints are determined based on the expected values ​​of vehicle acceleration, speed, front wheel steering angle, and angular velocity when the vehicle reaches the target parking position.

[0046] For example, the maximum permissible acceleration, maximum permissible speed, maximum permissible front wheel steering angle, and maximum permissible angular velocity can be expressed as A, respectively. max V max Φ max Ω max Then the kinematic constraints can be as follows:

[0047]

[0048] Where v(t) represents the vehicle's velocity at time t, a(t) represents the vehicle's acceleration at time t, φ(t) represents the steering angle of the car's front wheels at time t, and ω(t) represents the car's angular velocity at time t.

[0049] Optionally, at every moment during vehicle operation, it is necessary to avoid collisions with every obstacle in the environment. Therefore, the area where the vehicle is located can be defined as a regular rectangular area, and the area where each target obstacle is located can be defined as a polygonal area based on the outline structure of each target obstacle around the vehicle. If the area where the target obstacle is located is a convex polygonal area, the collision avoidance constraint is determined based on the geometric relationship that the rectangular area corresponding to the vehicle and the convex polygonal area corresponding to the target obstacle must satisfy to avoid intersection.

[0050] Optionally, if the polygonal region where the target obstacle is located is a concave polygonal region, it can be decomposed into multiple convex polygonal regions. Using the method described above for determining the collision avoidance constraints between the vehicle rectangular region and the target obstacle convex polygonal region, the collision avoidance constraints between the vehicle rectangular region and each of the decomposed convex polygonal regions can be determined separately.

[0051] A convex polygon is a polygon in which every interior angle is either acute or obtuse, meaning it has no major angle greater than 180°. A concave polygon is a polygon in which there is at least one major angle.

[0052] For example, see Figure 1C A, B, C, and D represent the four vertices of the rectangular region of the vehicle, V jk Let represent the k-th vertex of the j-th target obstacle. The j-th target obstacle has Npol vertices. For the vehicle to avoid colliding with the j-th target obstacle, the following two conditions must be met, i.e., the geometric relationships required for non-intersection:

[0053] 1) The four vertices of the vehicle, namely points A, B, C and D, are all outside the j-th polygon.

[0054] 2) Each vertex on the j-th target obstacle, i.e., each V jk They are all located outside the rectangle formed by the four vertices A, B, C, and D.

[0055] It should be noted that if a point Q is located outside the convex polygon bounded by W1, W2, ..., Wm, the following formula must be satisfied:

[0056]

[0057] Among them, S Δ S represents the area of ​​the triangle. ΔW1,W2,...,Wm Represented by W1, W2, ..., W m The area of ​​the enclosed polygon. Based on the formula that point Q must satisfy to be located outside the convex polygon, and combined with the geometric relationship that must be satisfied for non-intersection, i.e., the two conditions for not colliding with the target obstacle, the collision avoidance constraint can be determined as follows:

[0058]

[0059] Among them, Npol j This refers to the number of vertices contained in the polygon corresponding to the j-th target obstacle. This refers to the point Q, the first vertex of the j-th target obstacle, and the Nth pole. j The area of ​​the triangle formed by the vertices. It refers to the area of ​​the triangle formed by point Q, the m-th vertex of the j-th target obstacle, and the (m+1)-th vertex. S refers to the area of ​​the polygonal region corresponding to the j-th target obstacle. ΔQAB S refers to the area of ​​the triangle formed by points Q, A, and B. ΔQBC S refers to the area of ​​the triangle formed by points Q, C, and B. ΔQCD S refers to the area of ​​the triangle formed by points Q, C, and D. ΔQDA S refers to the area of ​​the triangle formed by points Q, A, and D. ABCD This refers to the area of ​​the matrix region corresponding to the vehicle. It refers to the k-th vertex of the j-th target obstacle. It refers to the j-th vertex of the j-th target obstacle.

[0060] S102. Based on the vehicle's current location and the target parking location, and according to the constraints, perform preliminary path planning to determine at least two candidate parking routes.

[0061] Optionally, based on the vehicle's current location and the target parking location, preliminary path planning is performed according to the constraints to determine at least two candidate parking planning routes. This includes: taking the vehicle's current location as the starting point of the planned route and the target parking location as the ending point of the planned route, and performing preliminary path planning to determine at least two candidate parking planning routes when the vehicle is expected to reach each point on the planned route while meeting the constraints.

[0062] S103. Based on the preset adaptive same-position hot start algorithm, the size of the convex polygon region corresponding to the target obstacle is iteratively adjusted according to the attribute information of the target obstacle around the vehicle, and the optimal parking route is determined by performing precise path planning based on the attribute information of the target obstacle after iterative adjustment.

[0063] The Adaptively Homotopic Warm-Starting Approach (AHWS) decomposes the path planning problem (i.e., the original large problem) with the original target obstacle size into multiple iterative subproblems. Specifically, it decomposes the problem into subproblems that solve path planning for different scaled-down versions of the target obstacle. The target obstacle's attribute information can include its position and size.

[0064] For example, see Figure 1D If the target obstacle is formed by V j1 V j2 V j3 V j4、 V j5 V j6 V j7 and V jNpol The convex polygon region is decomposed into subproblems. In the process of finding the optimal route, the size of the obstacles can first be shrunk to a standard size, i.e., reduced to a minimum size based on a preset ratio. Then, in the subproblem-solving steps, the size of the target obstacles is gradually expanded until it returns to its original size. The geometric centers of target obstacles of different sizes are the same. The size of the target obstacles can be adjusted using a scalar γ∈[0,1].

[0065] Optionally, based on a preset adaptive in-situ hot start algorithm, the size of the convex polygon region corresponding to the target obstacle is iteratively adjusted according to the attribute information of the target obstacle around the vehicle. This includes: determining the original size of the convex polygon corresponding to the target obstacle based on the attribute information of the target obstacle around the vehicle using the preset adaptive in-situ hot start algorithm; determining the minimum size of the convex polygon corresponding to the target obstacle based on the original size and a preset reduction ratio to obtain the initially adjusted target obstacle; and iteratively increasing the size of the initially adjusted target obstacle based on a preset adjustment step size until the size of the target obstacle is adjusted to the original size.

[0066] Optionally, based on the attribute information of the target obstacle after iterative adjustment, precise path planning is performed, including: based on the initially adjusted target obstacle, path planning is performed under the condition of meeting obstacle avoidance conditions to determine the initial planned route; during the iterative adjustment of the target obstacle size, based on the attribute information of the target obstacle after each adjustment and the planned route determined in the previous adjustment, path planning is performed under the current target obstacle size condition to determine the adjusted planned route; the initial planned route, the adjusted planned route, and at least two candidate parking planned routes are analyzed to determine the final optimal parking route.

[0067] For example, suppose the j-th target obstacle has Npolj vertices, such as Then the geometric center (Xc) of the target obstacle j Yc j The definition of ) can be shown in the following formula:

[0068]

[0069]

[0070] Among them, Xv ji and Yv ji Let x and y represent the x and y coordinates of the i-th vertex of the j-th target obstacle, respectively.

[0071] Optionally, since target obstacles of different scaling sizes have similar shapes and the same geometric center, the x and y coordinates of the j-th target obstacle at different scaling sizes are... It can be obtained through the following formula:

[0072]

[0073]

[0074] As can be seen, the size of the target obstacle can change with the scalar γ. When γ = 1, the target obstacle becomes its original size, i.e. If γ = 0, the target obstacle shrinks to the geometric center point Xcj, Ycj. A series of subproblems, from easy to difficult, can be defined by changing the value of the scalar γ from 0 to 1. The goal of the adaptive hot-start algorithm is to find a suitable step increment for the scalar γ from 0 to 1. Initially, let γ = ε0 as the simplest subproblem, where ε0 is a number whose limit is close to 0. If this subproblem (i.e., determining the size of the target obstacle based on the scaling factor γ = ε0 and then performing path planning) fails, then the problem has no solution; otherwise, γ can be set... achieved =ε0 is used as the starting condition for subsequent calculations. In the next round of calculations, let γ = γ achieved +step is treated as a new subproblem to be solved, and the best solution achieved so far is recorded. If subproblem 1 is successfully solved, we let γ... achieved =γ, and serve as the initial condition for the next round of calculation. If the subproblem in this round fails to be solved, it may be due to the step value being too large. In this case, we set the value of step to step·α. reduce Continue iterating through the above steps until the scalar γ = 1. If, during the iterative solution of the subproblems, N-expand (i.e., the preset number of allowed iterative subproblems) consecutive subproblems are successfully solved, it can be understood that the value of step is set too small, and the value of step can be set to step / α. reduce If the value of step becomes too small during iteration, such that it falls below a set default value ε. exit If the iteration terminates, it is considered that the problem is unsolvable, meaning that the optimal parking route cannot be found.

[0075] Optionally, after determining the optimal parking route, the vehicle can be controlled to park based on the optimal parking route.

[0076] The technical solution of this invention, upon detecting a parking event, constructs a dynamic model of the vehicle and determines the corresponding constraints. Based on the vehicle's current position and the target parking position, and according to the constraints, preliminary path planning is performed to determine at least two candidate parking routes. Based on a preset adaptive hot-start algorithm, the size of the convex polygon region corresponding to the target obstacle is iteratively adjusted according to the attribute information of the target obstacle around the vehicle. Then, based on the adjusted attribute information of the target obstacle, precise path planning is performed to determine the optimal parking route. In this way, based on the vehicle dynamic model, combined with more comprehensive constraints, and using an adaptive hot-start algorithm, the optimal parking route can be found iteratively, helping to achieve accurate and effective automatic parking and improving the safety of automatic parking.

[0077] Example 2

[0078] Figure 2 This is a structural block diagram of a vehicle parking path planning device provided in Embodiment 2 of the present invention; the vehicle parking path planning device provided in this embodiment of the present invention can execute the vehicle parking path planning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0079] like Figure 2 As shown, the device includes:

[0080] The condition determination module 201 is used to construct a dynamic model of the vehicle and determine the constraint conditions corresponding to the dynamic model if a parking event of the vehicle is detected.

[0081] The candidate route determination module 202 is used to perform preliminary path planning based on the current vehicle position and the target parking position, according to the constraints, and determine at least two candidate parking planning routes.

[0082] The optimal route determination module 203 is used to perform iterative adjustment of the size of the convex polygon region corresponding to the target obstacle based on the attribute information of the target obstacle around the vehicle, according to the preset adaptive hot start algorithm, and to perform precise path planning based on the attribute information of the target obstacle after iterative adjustment, so as to determine the optimal parking route.

[0083] The technical solution of this invention, upon detecting a parking event, constructs a dynamic model of the vehicle and determines the corresponding constraints. Based on the vehicle's current position and the target parking position, and according to the constraints, preliminary path planning is performed to determine at least two candidate parking routes. Based on a preset adaptive hot-start algorithm, the size of the convex polygon region corresponding to the target obstacle is iteratively adjusted according to the attribute information of the target obstacle around the vehicle. Then, based on the adjusted attribute information of the target obstacle, precise path planning is performed to determine the optimal parking route. In this way, based on the vehicle dynamic model, combined with more comprehensive constraints, and using an adaptive hot-start algorithm, the optimal parking route can be found iteratively, contributing to the achievement of precise and effective automatic parking.

[0084] Furthermore, the condition determination module 201 is specifically used for:

[0085] Based on the bicycle model, a dynamic model of the vehicle is constructed according to the calculation relationship between the vehicle-related parameters. The vehicle-related parameters include at least one of the following: the vehicle's running time, the vehicle's position information in the vehicle coordinate system, the vehicle's speed, acceleration, the steering angle and angular velocity of the vehicle's front wheel, the distance between the vehicle's front and rear wheels, and the time when the vehicle's running ends.

[0086] Furthermore, the constraints include at least one of the following: kinematic constraints, collision avoidance constraints, boundary condition constraints, and cost minimization constraints.

[0087] Furthermore, the above-mentioned device is also used for:

[0088] Based on the preset maximum permissible acceleration, maximum permissible speed, maximum permissible front wheel steering angle, and maximum permissible angular velocity, determine the kinematic constraints on the vehicle's acceleration, speed, front wheel steering angle, and angular velocity;

[0089] Based on the geometric relationship that must be satisfied between the rectangular region corresponding to the vehicle and the convex polygon region corresponding to the target obstacle to avoid intersection, the collision avoidance constraints are determined.

[0090] The boundary condition constraints are determined based on the expected values ​​of vehicle acceleration, speed, front wheel steering angle, and angular velocity when the vehicle reaches the target parking position.

[0091] Furthermore, the candidate route determination module 202 is specifically used for:

[0092] Using the vehicle's current location as the starting point of the planned route and the target parking location as the ending point of the planned route, preliminary path planning is performed, under the condition that the constraints are met when the vehicle travels to each point on the planned route, to determine at least two candidate parking planning routes.

[0093] Furthermore, the optimal route determination module 203 is specifically used for:

[0094] Based on the preset adaptive same-position hot start algorithm, the original size of the convex polygon corresponding to the target obstacle is determined according to the attribute information of the target obstacle around the vehicle.

[0095] Based on the original dimensions and a preset reduction ratio, the minimum size of the convex polygon corresponding to the target obstacle is determined, resulting in the initially adjusted target obstacle.

[0096] Based on a preset adjustment step size, the size of the target obstacle after the initial adjustment is iteratively increased until the size of the target obstacle is adjusted to the original size.

[0097] Furthermore, the optimal route determination module 203 is also used for:

[0098] Based on the initially adjusted target obstacles, and under the condition of meeting obstacle avoidance requirements, path planning is carried out to determine the initial planned route.

[0099] During the iterative adjustment of the target obstacle size, based on the attribute information of the target obstacle after each adjustment and the planned route determined in the previous adjustment, path planning is performed under the current target obstacle size condition to determine the adjusted planned route.

[0100] The initial planned route, the adjusted planned route, and at least two candidate parking planned routes are analyzed to determine the final optimal parking route.

[0101] Example 3

[0102] Figure 3 This is a schematic diagram of the structure of the electronic device provided in Embodiment 3 of the present invention. Figure 3 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0103] like Figure 3As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0104] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0105] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as parking path planning methods for vehicles.

[0106] In some embodiments, the vehicle parking path planning method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle parking path planning method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle parking path planning method by any other suitable means (e.g., by means of firmware).

[0107] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0108] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0109] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0110] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0111] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0112] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0113] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0114] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for planning parking paths for vehicles, characterized in that, include: If a parking event is detected, a dynamic model of the vehicle is constructed, and the constraints corresponding to the dynamic model are determined. Based on the vehicle's current location and the target parking location, and according to the aforementioned constraints, preliminary path planning is performed to determine at least two candidate parking planning routes. Based on the preset adaptive same-position hot start algorithm, the size of the convex polygon region corresponding to the target obstacle is iteratively adjusted according to the attribute information of the target obstacle around the vehicle, and the optimal parking route is determined by precise path planning based on the attribute information of the target obstacle after iterative adjustment. Among them, based on the preset adaptive in-situ hot start algorithm, the size of the convex polygon region corresponding to the target obstacle is iteratively adjusted according to the attribute information of the target obstacle around the vehicle, including: Based on the preset adaptive same-position hot start algorithm, the original size of the convex polygon corresponding to the target obstacle is determined according to the attribute information of the target obstacle around the vehicle. Based on the original dimensions and a preset reduction ratio, the minimum size of the convex polygon corresponding to the target obstacle is determined, resulting in the initially adjusted target obstacle. Based on a preset adjustment step size, the size of the target obstacle after the initial adjustment is iteratively increased until the size of the target obstacle is adjusted to the original size.

2. The method according to claim 1, characterized in that, Constructing the vehicle's dynamic model includes: Based on the bicycle model, a dynamic model of the vehicle is constructed according to the calculation relationship between the vehicle-related parameters. The vehicle-related parameters include at least one of the following: the vehicle's running time, the vehicle's position information in the vehicle coordinate system, the vehicle's speed, acceleration, the steering angle and angular velocity of the vehicle's front wheel, the distance between the vehicle's front and rear wheels, and the time when the vehicle's running ends.

3. The method according to claim 1, wherein, The constraints include at least one of the following: kinematic constraints, collision avoidance constraints, boundary condition constraints, and cost minimization constraints.

4. The method according to claim 3, characterized in that, Also includes: Based on the preset maximum permissible acceleration, maximum permissible speed, maximum permissible front wheel steering angle, and maximum permissible angular velocity, determine the kinematic constraints on the vehicle's acceleration, speed, front wheel steering angle, and angular velocity; Based on the geometric relationship that must be satisfied between the rectangular region corresponding to the vehicle and the convex polygon region corresponding to the target obstacle to avoid intersection, the collision avoidance constraints are determined. The boundary condition constraints are determined based on the expected values ​​of vehicle acceleration, speed, front wheel steering angle, and angular velocity when the vehicle reaches the target parking position.

5. The method according to claim 1, characterized in that, Based on the vehicle's current location and the target parking location, and according to the aforementioned constraints, preliminary path planning is performed to determine at least two candidate parking routes, including: Using the vehicle's current location as the starting point of the planned route and the target parking location as the ending point of the planned route, preliminary path planning is performed, under the condition that the constraints are met when the vehicle travels to each point on the planned route, to determine at least two candidate parking planning routes.

6. The method according to claim 1, characterized in that, Based on the attribute information of the target obstacle after iterative adjustments, precise path planning is performed, including: Based on the initially adjusted target obstacles, and under the condition of meeting obstacle avoidance requirements, path planning is carried out to determine the initial planned route. During the iterative adjustment of the target obstacle size, based on the attribute information of the target obstacle after each adjustment and the planned route determined in the previous adjustment, path planning is performed under the current target obstacle size condition to determine the adjusted planned route. The initial planned route, the adjusted planned route, and at least two candidate parking planned routes are analyzed to determine the final optimal parking route.

7. A parking path planning device for vehicles, characterized in that, include: The condition determination module is used to construct a dynamic model of the vehicle and determine the constraint conditions corresponding to the dynamic model if a parking event is detected. The candidate route determination module is used to perform preliminary path planning based on the vehicle's current location and the target parking location, according to the constraints, and determine at least two candidate parking planning routes. The optimal route determination module is used to perform precise path planning based on the preset adaptive hot start algorithm, according to the attribute information of the target obstacles around the vehicle, to determine the optimal parking route. Specifically, the optimal route determination module is used for: Based on the preset adaptive same-position hot start algorithm, the original size of the convex polygon corresponding to the target obstacle is determined according to the attribute information of the target obstacle around the vehicle. Based on the original dimensions and a preset reduction ratio, the minimum size of the convex polygon corresponding to the target obstacle is determined, resulting in the initially adjusted target obstacle. Based on a preset adjustment step size, the size of the target obstacle after the initial adjustment is iteratively increased until the size of the target obstacle is adjusted to the original size.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the parking path planning method for the vehicle according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the parking path planning method for the vehicle as described in any one of claims 1-6.

Images