Path planning method, path planning device and computer readable storage medium

Abstract

The present disclosure provides a path planning method, a path planning device and a computer-readable storage medium, and relates to the field of computer technology. The path planning method includes: taking the time required for a vehicle to move along a planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point as optimization targets, constructing a first objective function; the smooth path passes through each given track reference point; taking the vehicle's kinematic equation, the vehicle's starting state, the vehicle's ending state, and the minimum distance between the smooth path and each track reference point not greater than a preset value as a first constraint condition; when the first constraint condition is met, using an optimization method to solve the smooth path that minimizes the value of the first objective function. The present disclosure can plan a smooth path that meets the vehicle's motion characteristics based on given track reference points, thereby more accurately, directly and objectively guiding the vehicle to quickly pass through each track reference point.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a path planning method, a path planning device, and a computer-readable storage medium. Background Art

[0002] With the development of driverless car technology, the application areas of driverless cars have become more extensive.

[0003] In the working process of the unmanned vehicle, it is generally necessary to plan the driving path of the unmanned vehicle in advance, and then control the unmanned vehicle to drive along the planned path. Therefore, the path planned in advance can play a role in navigation and guidance for the driving of the unmanned vehicle. Summary of the invention

[0004] The inventors have found that the paths planned for unmanned vehicles in related technologies are usually composed of several track reference points, which form broken lines between them. However, it is difficult for unmanned vehicles to pass through each track reference point along a broken line in the actual driving process, so it is necessary to smooth the path composed of each track reference point. If the path is smoothed only based on geometric knowledge, the generated smooth path may not meet the motion characteristics of the vehicle. On the one hand, the speed, acceleration, wheel deflection angle, wheel deflection angular velocity and other parameter indicators of the vehicle during movement may make it impossible for the vehicle to actually travel along the path obtained by smoothing based on geometric knowledge; on the other hand, in order to make the vehicle travel along the path obtained by smoothing based on geometric knowledge, the speed, acceleration and other parameter indicators of the vehicle during movement will be restricted.

[0005] The technical problem solved by the present disclosure is how to plan a smooth path that meets the vehicle's motion characteristics based on given track reference points, so as to more accurately, directly and objectively guide the vehicle to quickly pass through each track reference point.

[0006] According to one aspect of an embodiment of the present disclosure, a path planning method is provided, including: taking the time required for a vehicle to move along a planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point as optimization targets, constructing a first objective function; the smooth path passes through each given track reference point; taking the kinematic equation of the vehicle, the starting state of the vehicle, the ending state of the vehicle, and the minimum distance between the smooth path and each track reference point being no greater than a preset value as a first constraint condition; and adopting an optimization method to solve the smooth path that minimizes the value of the first objective function when the first constraint condition is satisfied.

[0007] In some embodiments, the time required for the vehicle to move along the planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point are taken as optimization targets, and constructing the first objective function includes: taking the weighted sum of the time required for the vehicle to move along the planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point to obtain the first objective function.

[0008] In some embodiments, the first objective function is Among them, t f represents the time when the unknown vehicle passes the last track reference point, t0 represents the time when the known vehicle passes the first track reference point, λ is a known preset constant greater than zero, i is the identifier of the track reference point, N is the total number of known track reference points, x(τ) is the horizontal coordinate of the midpoint of the rear axle of the vehicle on the smooth path at the unknown time τ, and y(τ) is the vertical coordinate of the midpoint of the rear axle of the vehicle on the smooth path at the unknown time τ. i is the horizontal coordinate of the known track reference point i, y i is the ordinate of the known track reference point i.

[0009] In some embodiments, the first constraint condition that the minimum distance between the smooth path and each track reference point is not greater than a preset value is: m is a preset value greater than zero; the first constraint condition on the initial state of the vehicle is [a(t0),ω(t0),v(t0),φ(t0),x(t0),y(t0),θ(t0)]=[0,0,v st ,0,x(t0),y(t0),θ(t0)], where a represents the acceleration of the vehicle along the longitudinal axis at time t0, ω(t0) represents the front wheel deflection angular velocity of the vehicle at time t0, v(t0) represents the speed of the vehicle along the longitudinal axis at time t0, φ(t0) represents the front wheel deflection angle of the vehicle at time t0, x(t0) represents the horizontal coordinate of the midpoint of the rear wheel axle of the vehicle at time t0, y(t0) represents the vertical coordinate of the midpoint of the rear wheel axle of the vehicle at time t0, θ(t0) represents the attitude angle of the vehicle at time t0, and v st represents the speed of the vehicle moving uniformly along the planned smooth path; the first constraint condition on the vehicle's terminal state is [a(t f ),ω(t f ),v(t f ),φ(t f ),x(t f ),y(t f ),θ(t f )]=[0,0,v st ,0,x(t f ),y(tf ),θ(t f )], where a(t f ) indicates that the vehicle is at t f The acceleration along the longitudinal axis of the vehicle body at the moment, ω(t f ) represents the front wheel yaw angular velocity of the vehicle at time t0, v(t f ) indicates that the vehicle is at t f The speed along the longitudinal axis of the vehicle body at the moment, φ(t f ) indicates that the vehicle is at t f The front wheel deflection angle at time, x(t f ) indicates that the midpoint of the rear axle of the vehicle is at t f The horizontal axis of the time, y(t f ) indicates that the midpoint of the rear axle of the vehicle is at t f The vertical coordinate of the time, θ(t f ) indicates that the vehicle is at t f The attitude angle at the moment; the first constraint condition on the vehicle's kinematic equation is: L represents the wheelbase between the front and rear wheels of the vehicle.

[0010] In some embodiments, while satisfying the first constraint, an optimization method is used to find a smooth path that minimizes the value of the first objective function: using a nonlinear programming solver, find the path represented by the relationship between the variable x(t) and the variable y(t) that minimizes the value of the first objective function while satisfying the first constraint.

[0011] In some embodiments, a nonlinear programming solver is used to solve the path represented by the relationship between the variable x(t) and the variable y(t) when the first objective function is minimized while the first constraint is satisfied, including: taking part of the constraints in the first constraint as the second constraint; using a nonlinear programming solver to solve the path represented by the relationship between the variable x(t) and the variable y(t) when the first objective function is minimized while the second constraint is satisfied, to obtain a first solution result; using the first solution result as an initial solution, using a nonlinear programming solver to solve the path represented by the relationship between the variable x(t) and the variable y(t) when the first objective function is minimized while the first constraint is satisfied, to obtain a final solution result.

[0012] In some embodiments, taking part of the constraints in the first constraints as the second constraints includes: taking the kinematic equation of the vehicle, the starting state of the vehicle, and the ending state of the vehicle as the second constraints.

[0013] In some embodiments, a nonlinear programming solver is used to solve the path represented by the relationship between the variable x(t) and the variable y(t) when the first objective function is minimized while the second constraint is satisfied, and obtaining a first solution result includes: taking some of the constraints in the first constraint as the third constraint; taking some of the terms in the first objective function as the second objective function; using a nonlinear programming solver to solve the path represented by the relationship between the variable x(t) and the variable y(t) when the second objective function is minimized while the third constraint is satisfied, and obtaining a second solution result; using the second solution result as the initial solution, and using a nonlinear programming solver to solve the path represented by the relationship between the variable x(t) and the variable y(t) when the first objective function is minimized while the second constraint is satisfied, and obtaining the first solution result.

[0014] In some embodiments, taking part of the constraints in the first constraint as the third constraint includes: taking the vehicle's starting state, the vehicle's ending state, and the minimum distance between the smooth path and each track reference point not greater than a preset value as the third constraint; taking part of the items in the first objective function as the second objective function includes: taking the cumulative minimum distance between the smooth path and each given track reference point as the second objective function.

[0015] According to another aspect of an embodiment of the present disclosure, a path planning device is provided, including: an objective function construction module, configured to take the time required for a vehicle to move along a planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point as optimization targets to construct a first objective function; the smooth path passes through each given track reference point; a constraint condition construction module, configured to take the vehicle's kinematic equation, the vehicle's starting state, the vehicle's ending state, and the minimum distance between the smooth path and each track reference point not greater than a preset value as a first constraint condition; and an optimization problem solving module, configured to use an optimization method to solve the smooth path that minimizes the value of the first objective function while satisfying the first constraint condition.

[0016] According to another aspect of an embodiment of the present disclosure, a path planning device is provided, including: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the aforementioned path planning method based on instructions stored in the memory.

[0017] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the aforementioned path planning method is implemented.

[0018] The present disclosure can plan a smooth path that meets the vehicle's motion characteristics based on given track reference points, thereby more accurately, directly and objectively guiding the vehicle to quickly pass through each track reference point.

[0019] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0021] Figure 1 A schematic diagram showing track reference points and navigation path.

[0022] Figure 2 A schematic flow chart of a path planning method according to some embodiments of the present disclosure is shown.

[0023] Figure 3 A schematic diagram showing the minimum distance between the planned smooth path and each given track reference point.

[0024] Figure 4 A schematic structural diagram of a path planning device according to some embodiments of the present disclosure is shown.

[0025] Figure 5 A schematic structural diagram of a path planning device according to some other embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present disclosure and its application or use. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0027] Figure 1 A schematic diagram of the track reference points and navigation path is shown. Figure 1As shown in the figure, several circles represent discrete track reference points, which are known conditions. The smooth curve with arrows represents the navigation path to be planned, which is the solution target. In order to accurately and objectively plan a smooth path for the vehicle, it is necessary to establish an optimization control problem.

[0028] The optimization control problem takes the vehicle to drive as close to each track reference point as possible as the optimization goal, and takes the vehicle's motion characteristics as the main constraint when driving on the planned smooth path. For this main constraint, it is assumed that there are N given track reference points in the inertial coordinate system OXY, recorded in the point set {(x i ,y i ), i=1,…,N}. Then, a kinematic model of the vehicle (such as a bicycle model) can be established in the inertial coordinate system OXY. The model is usually a set of equations consisting of a series of differential equations, which represent the inherent mechanical or physical indicators of the vehicle to constrain the solution of the optimization control problem to conform to the motion characteristics of the vehicle. In addition, the optimization control problem also requires other constraints, such as limiting the vehicle to travel from a certain starting point to a certain end point during the movement process, and the offset distance between the vehicle and each track reference point during the driving process cannot be too large.

[0029] In order to solve this optimization control problem, the optimization control problem can be discretized and converted into a nonlinear programming problem, and then optimized.

[0030] Combine the following Figure 2 The path planning method of some embodiments of the present disclosure is described.

[0031] Figure 2 FIG. 1 is a flow chart showing a path planning method according to some embodiments of the present disclosure. Figure 2 As shown, this embodiment includes steps S202 to S206.

[0032] In step S202, the time required for the vehicle to move along the planned smooth path and the cumulative minimum distance between the planned smooth path and each given track reference point are used as optimization targets to construct a first objective function, wherein the planned smooth path passes through each given track reference point.

[0033] Below through Figure 3 Explain the cumulative minimum distance between the planned smooth path and the given track reference points. Figure 3 A schematic diagram showing the minimum distance between the planned smooth path and each given track reference point is shown. Figure 3As shown in the figure, the solid triangle represents the track reference point, the solid line passing through each track reference point represents the planned smooth path, the solid circle represents the point on the curve closest to each track reference point, and the dotted line represents the minimum distance between the planned smooth path and each given track reference point. For a specific track reference point, there is a corresponding driving point on the planned smooth path with the minimum distance from the specific track reference point. By adding up these minimum distances, the cumulative minimum distance between the planned smooth path and each given track reference point can be obtained. Taking the time required for the vehicle to move along the planned smooth path as the optimization target, the vehicle can pass through each track reference point as quickly as possible along the smooth path, that is, the task completion time is the shortest; taking the cumulative minimum distance between the planned smooth path and each given track reference point as the optimization target, the generated smooth path can be as close to the given track reference point as possible, that is, the cumulative degree of deviation from each track reference point during driving is as small as possible.

[0034] When constructing the first objective function, the time required for the vehicle to move along the planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point can be weighted summed to obtain the first objective function. The specific form of the first objective function will be described in detail later.

[0035] In step S204, the kinematic equation of the vehicle, the initial state of the vehicle, the final state of the vehicle, and the minimum distance between the smooth path and each track reference point being no greater than a preset value are used as the first constraint conditions.

[0036] The kinematic equation of the vehicle can specifically adopt the kinematic equation of the vehicle in the bicycle model to simplify the calculation process. The specific kinematic equation is introduced later.

[0037] In step S206, when the first constraint condition is satisfied, an optimization method is used to find a smooth path that minimizes the value of the first objective function.

[0038] Under the premise of a limited number of track reference points, this embodiment can plan a smooth path that meets the vehicle's motion characteristics according to the given track reference points, thereby generating a smooth path that is easy for the vehicle to track and drive in real time, and then more accurately, directly and objectively guide the vehicle to quickly pass through each track reference point. At the same time, since the vehicle's motion characteristics are taken into account when planning the path, this embodiment can plan differentiated and customized smooth paths for various models, thereby playing a good guiding role in the driving process of different models.

[0039] The preferred embodiment of the first objective function is introduced below.

[0040] The first objective function can be Among them, tf represents the time when the unknown vehicle passes the last track reference point, t0 represents the time when the known vehicle passes the first track reference point, λ is a known preset constant greater than zero, i is the identifier of the track reference point, N is the total number of known track reference points, x(τ) is the horizontal coordinate of the vehicle on the smooth path at the unknown time τ, y(τ) is the vertical coordinate of the vehicle on the smooth path at the unknown time τ, and x i is the horizontal coordinate of the known track reference point i, y i is the ordinate of the known track reference point i. In the above formula, λ>0 represents the compromise between the motion completion time and trajectory deviation in the objective function.

[0041] Accordingly, a preferred embodiment of the first constraint condition is introduced below.

[0042] The first constraint condition that the minimum distance between the smooth path and each track reference point is not greater than the preset value is: m is a preset value greater than zero, which is used to characterize the upper limit of the allowable deviation of the minimum distance between the smooth path and each given track reference point. This constraint condition limits the distance between the vehicle and the corresponding track point at N equally spaced sampling moments during the entire movement process. Adding this constraint condition can prevent the planned path from deviating significantly from the solution result of the track reference point.

[0043] The first constraint on the initial state of the vehicle is [a(t0),ω(t0),v(t0),φ(t0),x(t0),y(t0),θ(t0)] = [0,0,v st ,0,x(t0),y(t0),θ(t0)]. Wherein, a represents the acceleration of the vehicle along the longitudinal axis of the vehicle body at time t0, ω(t0) represents the front wheel deflection angular velocity of the vehicle at time t0, v(t0) represents the speed of the vehicle along the longitudinal axis of the vehicle body at time t0, φ(t0) represents the front wheel deflection angle of the vehicle at time t0, x(t0) represents the horizontal coordinate of the midpoint of the rear wheel axle of the vehicle at time t0, y(t0) represents the vertical coordinate of the midpoint of the rear wheel axle of the vehicle at time t0, θ(t0) represents the attitude angle of the vehicle at time t0, and v st The speed value that indicates the vehicle's uniform motion along the planned smooth path.

[0044] The first constraint on the vehicle's terminal state is [a(t f ),ω(t f ),v(t f ),φ(t f ),x(t f ),y(t f ),θ(t f )]=[0,0,vst ,0,x(t f ),y(t f ),θ(t f )]. Among them, a(t f ) indicates that the vehicle is at t f The acceleration along the longitudinal axis of the vehicle body at the moment, ω(t f ) represents the front wheel yaw angular velocity of the vehicle at time t0, v(t f ) indicates that the vehicle is at t f The speed along the longitudinal axis of the vehicle body at the moment, φ(t f ) indicates that the vehicle is at t f The front wheel deflection angle at time, x(t f ) indicates that the midpoint of the rear axle of the vehicle is at t f The horizontal axis of the time, y(t f ) indicates that the midpoint of the rear axle of the vehicle is at t f The vertical coordinate of the time, θ(t f ) indicates that the vehicle is at t f The attitude angle of the moment.

[0045] The first constraint on the vehicle's kinematic equations is: Among them, x(t) represents the horizontal coordinate of the midpoint of the rear axle of the vehicle at time t, y(t) represents the vertical coordinate of the midpoint of the rear axle of the vehicle at time t, θ(t) represents the attitude angle of the vehicle at time t, v(t) represents the speed of the vehicle along the longitudinal axis of the vehicle body at time t, φ(t) represents the front wheel deflection angle of the vehicle at time t, a(t) represents the acceleration of the vehicle along the longitudinal axis of the vehicle body at time t, ω(t) represents the front wheel deflection angular velocity of the vehicle at time t, and L represents the wheelbase between the front and rear wheels of the vehicle.

[0046] When the optimization method is used to solve the smooth path that minimizes the value of the first objective function while satisfying the first constraint, a nonlinear programming solver can be used to solve the path represented by the relationship between the variable x(t) and the variable y(t) when the value of the first objective function is minimized while satisfying the first constraint. The following describes the process of solving the above smooth path using the optimization method.

[0047] The above-mentioned optimization control problem should be solved by numerical optimization method. When solving, the above-mentioned optimization control problem is first discretized to be converted into a nonlinear programming problem, and then the nonlinear programming solver is used to solve the nonlinear programming problem. The inventor has published a paper disclosing the process of discretizing similar optimization problems by using the fully simultaneous orthogonal configuration finite element method and numerically solving them by using the interior point algorithm. For details, see Li, Bai, et al. "Time-optimal maneuver planning in automatic parallel parking using a simultaneous dynamic optimization approach." IEEE Transactions on Intelligent Transportation Systems 17.11(2016):3263-3274 and Li, Bai, et al. "Centralized and optimal motion planning for large-scale AGV systems:A generic approach." Advances in Engineering Software 106(2017):33-46, which will not be elaborated here.

[0048] However, simply calling the nonlinear programming solver cannot satisfactorily complete the above-mentioned solution task. This is because it takes a long time to directly call the nonlinear programming solver to solve the nonlinear programming problem, and the convergence speed of the result is often low, which leads to poor timeliness of the planning path. In order to improve the solution efficiency, the present disclosure further proposes a hot start solution method, which is introduced step by step below.

[0049] (a) Label the nonlinear programming problem A.

[0050] Mark "finding a smooth path that minimizes the value of the first objective function while satisfying the first constraint" as nonlinear programming problem A.

[0051] (ii) Construct nonlinear programming problem B.

[0052] Take some of the constraints in the first constraint as the second constraint. For example, the kinematic equation of the vehicle, the starting state of the vehicle, and the ending state of the vehicle can be used as the second constraint. Then, "solving the smooth path that minimizes the value of the first objective function while satisfying the second constraint" is marked as nonlinear programming problem B.

[0053] Comparing nonlinear programming problem B with nonlinear programming problem A, it can be found that nonlinear programming problem B has simplified the constraints, which will reduce the difficulty and time of solving nonlinear programming problem B.

[0054] (iii) Construct nonlinear programming problem C.

[0055] Take some of the constraints in the first constraint as the third constraint, and take some of the terms in the first objective function as the second objective function. For example, the vehicle's starting state, the vehicle's ending state, and the minimum distance between the smooth path and each track reference point is not greater than the preset value as the third constraint; the cumulative minimum distance between the smooth path and each given track reference point is taken as the second objective function. Then, "solving the smooth path that minimizes the value of the second objective function while satisfying the third constraint" is marked as nonlinear programming problem C.

[0056] Comparing the nonlinear programming problem C with the nonlinear programming problem A, it can be found that the nonlinear programming problem C is simplified in terms of constraints and objective functions, which greatly reduces the difficulty and time of solving the nonlinear programming problem C. Those skilled in the art should understand that the nonlinear programming problem C is easier to solve than the nonlinear programming problem B.

[0057] (iv) Solve the nonlinear programming problem C.

[0058] The nonlinear programming problem C is solved using a nonlinear programming solver. That is, the path represented by the relationship between the variable x(t) and the variable y(t) is solved to minimize the value of the second objective function while satisfying the third constraint, and the solution of the nonlinear programming problem C is obtained.

[0059] (V) Solve the nonlinear programming problem B.

[0060] The solution of the nonlinear programming problem C is used as the initial solution, and the nonlinear programming solver is used to solve the nonlinear programming problem B. That is, the path represented by the relationship between the variable x(t) and the variable y(t) is solved to minimize the value of the first objective function while satisfying the second constraint, and the solution of the nonlinear programming problem B is obtained.

[0061] (vi) Solve the nonlinear programming problem A.

[0062] The solution of nonlinear programming problem B is used as the initial solution, and the nonlinear programming solver is used to solve the nonlinear programming problem A. That is, the path represented by the relationship between the variable x(t) and the variable y(t) is solved to minimize the value of the first objective function while satisfying the first constraint condition, and the solution of nonlinear programming problem A is obtained.

[0063] In this embodiment, when the original nonlinear programming problem is difficult to solve quickly, the nonlinear programming problem is simplified into a simple nonlinear programming problem that is easy to solve. Then, the solution of the simple nonlinear programming problem is used as the initial solution of the original nonlinear programming problem. By implementing this solution method multiple times and sequentially, the real-time solution of the navigation path planning problem can be achieved, thereby improving the effectiveness of path planning and achieving real-time planning of a smooth path.

[0064] Combine the following Figure 4 Some embodiments of the path planning device disclosed herein are described.

[0065] Figure 4 FIG. 1 is a schematic diagram showing the structure of a path planning device in some embodiments of the present disclosure. Figure 4 As shown, the path planning device 40 of this embodiment includes:

[0066] The objective function construction module 402 is configured to construct a first objective function by taking the time required for the vehicle to move along the planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point as optimization targets; the smooth path passes through each given track reference point;

[0067] The constraint condition building module 404 is configured to use the kinematic equation of the vehicle, the starting state of the vehicle, the ending state of the vehicle, and the minimum distance between the smooth path and each track reference point being no greater than a preset value as a first constraint condition;

[0068] The optimization problem solving module 406 is configured to use an optimization method to solve a smooth path that minimizes the value of the first objective function when the first constraint condition is satisfied.

[0069] Combine the following Figure 5 Some other embodiments of the path planning device disclosed in the present invention are described.

[0070] Figure 5 FIG. 2 is a schematic diagram showing the structure of a path planning device in some other embodiments of the present disclosure. Figure 5 As shown, the path planning device 50 of this embodiment includes: a memory 510 and a processor 520 coupled to the memory 510 , and the processor 520 is configured to execute the path planning method in any of the aforementioned embodiments based on instructions stored in the memory 510 .

[0071] The memory 510 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0072] The path planning device 50 may also include an input / output interface 530, a network interface 540, a storage interface 550, etc. These interfaces 530, 540, 550, the memory 510, and the processor 520 may be connected, for example, via a bus 560. The input / output interface 530 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 540 provides a connection interface for various networked devices. The storage interface 550 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0073] The present disclosure also includes a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the path planning method in any of the aforementioned embodiments.

[0074] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0078] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A path planning method, comprising: The time required for the vehicle to move along the planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point are used as optimization targets to construct a first objective function; the smooth path passes through each given track reference point; The kinematic equation of the vehicle, the starting state of the vehicle, the ending state of the vehicle, and the minimum distance between the smooth path and each track reference point being no greater than a preset value are used as first constraint conditions; Under the condition of satisfying the first constraint condition, using an optimization method to solve the smooth path that minimizes the value of the first objective function; The time required for the vehicle to move along the planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point are taken as optimization targets, and the first objective function is constructed including: The first objective function is obtained by weighted summing the time required for the vehicle to move along the planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point; The cumulative minimum distance is determined as follows: On the planned smooth path, determining the driving point with the shortest distance from each track reference point, and determining the distance between each track reference point and each driving point with the shortest distance as the minimum distance of each track reference point; The minimum distances of the various track reference points are cumulatively added to determine the cumulative minimum distance between the various track reference points.

2. The path planning method according to claim 1, wherein: The first objective function is ;in, Indicates the time when the unknown vehicle passes the last track reference point. Indicates the time when the known vehicle passes the first track reference point, is a known preset constant greater than zero, i is the identifier of the track reference point, N is the total number of known track reference points, , For unknown The horizontal coordinate of the midpoint of the rear axle of the vehicle on the smooth path at the moment, For unknown The ordinate of the midpoint of the rear axle of the vehicle on the smooth path at the moment, is the horizontal coordinate of the known track reference point i, is the ordinate of the known track reference point i.

3. The path planning method according to claim 2, wherein: The first constraint condition that the minimum distance between the smooth path and each track reference point is not greater than a preset value is: , is a preset value greater than zero; The first constraint on the vehicle's initial state is ,in, Indicates that the vehicle is The acceleration along the longitudinal axis of the vehicle at any moment, Indicates that the vehicle is The front wheel angular velocity at time , Indicates that the vehicle is The speed along the longitudinal axis of the vehicle at any moment, Indicates that the vehicle is The front wheel deflection angle at time Indicates that the midpoint of the vehicle's rear axle is The horizontal axis of time, Indicates that the midpoint of the vehicle's rear axle is The vertical coordinate of time, Indicates that the vehicle is The posture angle of the moment, Indicates the speed value of the vehicle moving uniformly along the planned smooth path; The first constraint on the vehicle's terminal state is ,in, Indicates that the vehicle is The acceleration along the longitudinal axis of the vehicle at any moment, Indicates that the vehicle is The front wheel angular velocity at time , Indicates that the vehicle is The speed along the longitudinal axis of the vehicle at any moment, Indicates that the vehicle is The front wheel deflection angle at time Indicates that the midpoint of the vehicle's rear axle is The horizontal axis of time, Indicates that the midpoint of the vehicle's rear axle is The vertical coordinate of time, Indicates that the vehicle is The attitude angle at the moment; The first constraint on the vehicle's kinematic equations is: , Indicates the wheelbase between the front and rear wheels of the vehicle.

4. The path planning method according to claim 2, wherein: In the case of satisfying the first constraint condition, the smooth path that minimizes the value of the first objective function is solved by an optimization method as follows: Using the nonlinear programming solver, find the variable that minimizes the first objective function while satisfying the first constraint. With variables The path represented by the relationship between .

5. The path planning method according to claim 3, wherein: Using the nonlinear programming solver, find the variable that minimizes the first objective function while satisfying the first constraint. With variables The paths represented by the relationship between include: Taking part of the constraints in the first constraint as the second constraint; Using the nonlinear programming solver, find the variable that minimizes the first objective function while satisfying the second constraint. With variables The path represented by the relationship between and is used to obtain the first solution; The first solution is used as the initial solution, and a nonlinear programming solver is used to solve the variable that minimizes the first objective function while satisfying the first constraint condition. With variables The path represented by the relationship between them is used to obtain the final solution.

6. The path planning method according to claim 5, wherein: The taking part of the constraints in the first constraint as the second constraint includes: The kinematic equation of the vehicle, the initial state of the vehicle, and the final state of the vehicle are used as the second constraint condition.

7. The path planning method according to claim 5, wherein: The nonlinear programming solver is used to solve the variable that minimizes the value of the first objective function while satisfying the second constraint condition. With variables The path represented by the relationship between , the first solution result includes: Taking part of the constraints in the first constraint as the third constraint; Taking some items in the first objective function as the second objective function; Using the nonlinear programming solver, find the variable that minimizes the second objective function while satisfying the third constraint. With variables The path represented by the relationship between and is used to obtain the second solution result; The second solution is used as the initial solution, and a nonlinear programming solver is used to solve the variable that minimizes the first objective function while satisfying the second constraint condition. With variables The path represented by the relationship between is used to obtain the first solution.

8. The path planning method according to claim 7, wherein: The taking of some of the constraints in the first constraint as the third constraint includes: taking the starting state of the vehicle, the ending state of the vehicle, and the minimum distance between the smooth path and each track reference point not greater than a preset value as the third constraint; The taking of some items in the first objective function as the second objective function includes: taking the accumulated minimum distance between the smooth path and each given track reference point as the second objective function.

9. A path planning device, comprising: The objective function construction module is configured to construct a first objective function by taking the time required for the vehicle to move along the planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point as optimization targets; the smooth path passes through each given track reference point; A constraint condition building module is configured to use the kinematic equation of the vehicle, the starting state of the vehicle, the ending state of the vehicle, and the minimum distance between the smooth path and each track reference point being no greater than a preset value as a first constraint condition; An optimization problem solving module is configured to use an optimization method to solve the smooth path that minimizes the value of the first objective function under the condition that the first constraint condition is satisfied; The time required for the vehicle to move along the planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point are taken as optimization targets, and the first objective function is constructed including: The first objective function is obtained by weighted summing the time required for the vehicle to move along the planned smooth path and the cumulative minimum distance between the smooth path and each given track reference point; The cumulative minimum distance is determined as follows: On the planned smooth path, determining the driving point with the shortest distance from each track reference point, and determining the distance between each track reference point and each driving point with the shortest distance as the minimum distance of each track reference point; The minimum distances of the various track reference points are cumulatively added to determine the cumulative minimum distance between the various track reference points.

10. A path planning device, comprising: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the path planning method according to any one of claims 1 to 8 based on instructions stored in the memory.

11. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the path planning method according to any one of claims 1 to 8 is implemented.

Images