Local Path Planning Method, Device, Vehicle and Medium for Autonomous Driving Vehicle

Abstract

The present application relates to the technical field of vehicles, and particularly relates to a local path planning method, device, vehicle and medium for an autonomous vehicle. The method includes: extracting at least one sampling trajectory from the full-path planned trajectory according to the current position of the vehicle and the maximum planning distance, and calculating the priority cost, collision cost, transition cost and maximum lateral acceleration cost of each sampling trajectory, and taking the sampling trajectory with the minimum total trajectory cost among the obtained sampling trajectories of each sampling trajectory as the optimal local path. Thus, problems such as the need to select different cost weights to implement path planning when traditional local path planning methods are applied to different scenarios are solved. The problem of weight selection is solved by adding a planning method with speed and curvature constraints and an adaptive formula for the cost function, improving the system's adaptability and the smoothness and stability of the trajectory, and tracking the planned trajectory through an algorithm, and comparing the corresponding total trajectory costs to select the optimal local path.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a local path planning method, device, vehicle and medium for an autonomous driving vehicle. Background Art

[0002] Path planning is the basis of intelligent vehicle navigation and control. Path planning can be divided into local path planning and global path planning. Among them, global path planning is to plan a collision-free and passable path from the starting point to the target point based on the information of the global map database. At the same time, during the driving process of the vehicle, as the road becomes more complicated, it is more important to plan a collision-free ideal local path based on local environmental information and its own state information, and different local path planning methods have emerged.

[0003] In the related art, the local path planning method mainly obtains the optimal trajectory by calculating the cost of each trajectory with different cost functions through fixed time and interval distance sampling.

[0004] However, this method needs to select different cost weights to ensure the implementation of path planning when dealing with different scenarios. In particular, in some complex scenarios, it is difficult to meet the requirements with fixed cost weights. In addition, separate planning for the horizontal and vertical directions of the road is not conducive to the planning effect of the vehicle when driving on roads with large curvature and high speed, which needs to be solved urgently. Summary of the invention

[0005] The present application provides a local path planning method, device, vehicle and medium for an autonomous vehicle to solve the problem that traditional local path planning methods need to select different cost weights to implement path planning when dealing with different scenarios. The weight selection problem is solved by adding a planning method with speed and curvature constraints and a cost function adaptive formula, thereby improving the system's adaptability and the smoothness and stability of the trajectory. The planned trajectory is tracked and simulated through an algorithm, and the corresponding total trajectory cost is compared to select the optimal local path.

[0006] The first aspect of the present application provides a local path planning method for an autonomous driving vehicle, comprising the following steps:

[0007] Extract at least one sample trajectory from the entire road planning path according to the current position of the autonomous driving vehicle and the maximum planning distance;

[0008] Calculating the priority cost, collision cost, transition cost and maximum lateral acceleration cost of each sampled trajectory to obtain the total trajectory cost of each sampled trajectory; and

[0009] Based on the total trajectory cost of each sampling trajectory, the sampling trajectory with the minimum total trajectory cost is taken as the optimal local path.

[0010] According to an embodiment of the present application, taking the sampling trajectory with the minimum total trajectory cost as the optimal local path includes:

[0011] Calculating the total trajectory cost according to the priority cost, the transition cost, the maximum lateral acceleration cost and the corresponding weight coefficients by using a preset cost formula.

[0012] According to an embodiment of the present application, the local path planning method for an autonomous vehicle, wherein

[0013] The calculation formula for the priority cost is:

[0014] r1 = f((x t , y t ), (x o , y o )) = (y t - y0)d,

[0015] The calculation formula for the collision cost is:

[0016]

[0017] The calculation formula for the transition cost is:

[0018] r3 = f((x t , y t ), (x t-1 , y t-1 )) = (y t - y t-1 )d,

[0019] The calculation formula for the maximum lateral acceleration cost is:

[0020] r4 = f(κ) = v 2 / r,

[0021] where r1 is the priority cost, r2 is the collision cost, r3 is the transition cost, r4 is the maximum lateral acceleration cost; x t , y t are the coordinates of the position point on the locally planned trajectory corresponding to time t; x o , y0 are the coordinates of the corresponding position point on the global path; x c , y c are the obstacle positions; d c is the lateral distance between the planned trajectory and the obstacle; l c is the longitudinal distance between the planned trajectory and the obstacle; x t-1 , y t-1is the coordinate of the position point on the planned trajectory corresponding to time t-1; r is the radius of curvature, v is the speed, and d is the trajectory density. According to an embodiment of the present application, the preset cost formula is:

[0022] Total trajectory cost = t1*r1 + t2*r2 + t3*r3 + t4*r4,

[0023] where t1 is the weight coefficient of the priority cost, t2 is the weight coefficient of the collision cost, t3 is the weight coefficient of the transition cost, and t4 is the weight coefficient of the maximum lateral acceleration cost.

[0024] According to an embodiment of the present application, the extracting at least one sampling trajectory from the full-road planned path according to the current position of the autonomous vehicle and the maximum planned distance includes:

[0025] Horizontally sampling to obtain a set of target points based on a preset trajectory density and a preset number of trajectories;

[0026] Performing trajectory point scattering based on the set of target points to generate at least one initial sampling trajectory;

[0027] Smoothing each initial sampling trajectory and screening out the initial sampling trajectories that do not meet the preset conditions to obtain the at least one sampling trajectory.

[0028] According to the local path planning method of the autonomous vehicle according to the embodiment of the present application, at least one sampling trajectory is extracted from the full-road planned path according to the current position of the vehicle and the maximum planned distance, and the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampling trajectory are calculated. The sampling trajectory with the minimum total trajectory cost among the obtained sampling trajectories of each sampling trajectory is used as the optimal local path. Thus, the problems such as the need to select different cost weights to implement path planning when the traditional local path planning method deals with different scenarios are solved. The problem of weight selection is solved by adding a planning method with speed and curvature constraints and an adaptive formula for the cost function, improving the system's adaptability and the smoothness and stability of the trajectory. And the planned trajectory is tracked and simulated by an algorithm, and the corresponding total trajectory costs are compared to select the optimal local path.

[0029] An embodiment of the second aspect of the present application provides a local path planning device for an autonomous vehicle, including:

[0030] An extraction module, configured to extract at least one sampling trajectory from the full-road planned path according to the current position of the autonomous vehicle and the maximum planned distance;

[0031] A calculation module, configured to calculate the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampling trajectory to obtain the total trajectory cost of each sampling trajectory; and

[0032] A selection module, configured to use the total trajectory cost of each sampling trajectory to select the sampling trajectory with the minimum total trajectory cost as the optimal local path.

[0033] According to an embodiment of the present application, the selection module is specifically configured to:

[0034] Calculate the total trajectory cost according to the priority cost, the transition cost, the maximum lateral acceleration cost and the corresponding weight coefficients by using a preset cost formula.

[0035] According to an embodiment of the present application, wherein,

[0036] The calculation formula of the priority cost is:

[0037] r1 = f((x t , y t ), (x o , y o )) = (y t - y0)d,

[0038] The calculation formula of the collision cost is:

[0039]

[0040] The calculation formula of the transition cost is:

[0041] r3 = f((x t , y t ), (x t-1 , y t-1 )) = (y t - y t-1 )d,

[0042] The calculation formula of the maximum lateral acceleration cost is:

[0043] r4 = f(κ) = v 2 / r,

[0044] Wherein, r1 is the priority cost, r2 is the collision cost, r3 is the transition cost, r4 is the maximum lateral acceleration cost; x t , y t are the coordinates of the position point on the local planned trajectory at time t; x o , y0 are the coordinates of the corresponding position point on the global path; x c , y c are the obstacle positions; d c is the lateral distance between the planned trajectory and the obstacle; l c is the longitudinal distance between the planned trajectory and the obstacle; x t-1 , yt-1 is the coordinate of the position point on the corresponding planned trajectory at time t-1; r is the radius of curvature, v is the speed, and d is the trajectory density.

[0045] According to an embodiment of the present application, the preset cost formula is:

[0046] Total trajectory cost = t1*r1 + t2*r2 + t3*r3 + t4*r4,

[0047] wherein, t1 is the weight coefficient of the priority cost, t2 is the weight coefficient of the collision cost, t3 is the weight coefficient of the transition cost, and t4 is the weight coefficient of the maximum lateral acceleration cost.

[0048] According to an embodiment of the present application, the extraction module is specifically configured to:

[0049] Horizontally sample to obtain a target point set based on a preset trajectory density and a preset number of trajectories;

[0050] Generate at least one initial sampled trajectory by scattering points based on the target point set;

[0051] Perform smoothing processing on each initial sampled trajectory, and screen out the initial sampled trajectories that do not meet the preset conditions to obtain the at least one sampled trajectory.

[0052] The local path planning device of the autonomous vehicle according to the embodiment of the present application extracts at least one sampled trajectory from the full-path planned path according to the current position of the vehicle and the maximum planning distance, and calculates the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampled trajectory, and uses the sampled trajectory with the minimum total trajectory cost among the obtained sampled trajectories as the optimal local path. Thus, it solves the problems that traditional local path planning methods need to select different cost weights to achieve path planning when dealing with different scenarios, and solves the problem of weight selection through a planning method with speed and curvature constraints and a cost function adaptive formula, improves the system's adaptability and the smoothness and stability of the trajectory, and performs tracking simulation on the planned trajectory through an algorithm, compares the corresponding total trajectory costs, and thus selects the optimal local path.

[0053] An embodiment of the third aspect of the present application provides a vehicle, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the local path planning method of the autonomous vehicle as described in the above embodiment.

[0054] The fourth aspect of the present application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the local path planning method for an autonomous vehicle as described in the above embodiments.

[0055] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, in which:

[0057] Figure 1 FIG. [FIG. number not provided] is a flowchart of a local path planning method for an autonomous vehicle according to an embodiment of the present application;

[0058] Figure 2 FIG. [FIG. number not provided] is a schematic diagram of a trajectory cluster of a local path planning method for an autonomous vehicle according to an embodiment of the present application;

[0059] Figure 3 FIG. [FIG. number not provided] is a flowchart of program execution of a local path planning method for an autonomous vehicle according to an embodiment of the present application;

[0060] Figure 4 FIG. [FIG. number not provided] is an exemplary diagram of a local path planning device for an autonomous vehicle according to an embodiment of the present application;

[0061] Figure 5 FIG. [FIG. number not provided] is a schematic structural diagram of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0063] The following describes a local path planning method, apparatus, vehicle, and medium for an autonomous vehicle according to an embodiment of the present application. In view of the problems mentioned in the above background art, such as the need to select different cost weights to achieve path planning in traditional local path planning methods when dealing with different scenarios, the present application provides a local path planning method for an autonomous vehicle. In this method, at least one sampling trajectory is extracted from the full-path planning trajectory according to the current position of the vehicle and the maximum planning distance, and the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampling trajectory are calculated. The sampling trajectory with the minimum total trajectory cost among the obtained sampling trajectories of each sampling trajectory is used as the optimal local path. Thus, the problems in traditional local path planning methods, such as the need to select different cost weights to achieve path planning when dealing with different scenarios, are solved. The problem of weight selection is solved by adding a planning method with speed and curvature constraints and a cost function adaptive formula, improving the system's adaptability and the smoothness and stability of the trajectory. The planned trajectory is tracked and simulated by an algorithm, and the corresponding total trajectory costs are compared to select the optimal local path.

[0064] Specifically, Figure 1 FIG. is a schematic flowchart of a local path planning method for an autonomous vehicle provided by an embodiment of the present application.

[0065] As Figure 1 shown, the local path planning method for the autonomous vehicle includes the following steps:

[0066] In step S101, at least one sampling trajectory is extracted from the full-path planning trajectory according to the current position of the autonomous vehicle and the maximum planning distance.

[0067] Further, in some embodiments, extracting at least one sampling trajectory from the full-path planning trajectory according to the current position of the autonomous vehicle and the maximum planning distance includes: horizontally sampling to obtain a target point set based on a preset trajectory density and a preset number of trajectories; generating at least one initial sampling trajectory by spreading points based on the target point set; smoothing each initial sampling trajectory and screening out the initial sampling trajectories that do not meet the preset conditions to obtain at least one sampling trajectory.

[0068] Among them, the preset trajectory density can be represented by d, the preset number of trajectories can be represented by m, the current position of the vehicle can be represented by p0, the maximum planning distance can be represented by s, and the position of the lateral sampling point can be represented by pi. It should be noted that the preset trajectory density and the preset number of trajectories can be thresholds preset by the user, thresholds obtained through a finite number of experiments, or thresholds obtained through a finite number of computer simulations, and no specific limitation is made here; the maximum planning distance can be the maximum planning distance from the vehicle center to the parallel lateral sampling point; the sampling trajectory can be the local target trajectory that the vehicle needs to collect according to the current position and the maximum planning distance.

[0069] Specifically, as Figure 2 shown, first, the embodiment of the present application can extract the required part from the full-road planned path according to the current position p0 and the maximum planning distance s of the vehicle as the local target trajectory, and calculate the distance ld = k * v from the vehicle center to the lateral sampling point according to the trajectory density d and the maximum planning distance s, and obtain the target point set according to the current position p0 and ld of the vehicle. Secondly, the embodiment of the present application can perform trajectory point scattering based on the target point set. Among them, the point scattering can be sampled in two segments. The first segment of sampling can be from the current position p0 of the vehicle to the position pi of the lateral sampling point; the second segment of sampling can be translated and extended from the position pi of the lateral sampling point according to the heading angle to the maximum planning distance s, so as to generate at least one initial sampling trajectory. Finally, the embodiment of the present application can perform uniform sampling through the point spacing, smooth each initial sampling trajectory, and screen out irregular points and initial sampling trajectories that do not meet the preset conditions, and then generate candidate trajectories, that is, obtain at least one sampling trajectory. By smoothing each initial sampling trajectory, the rolling discontinuity caused in the sampling step can be eliminated, and at the same time, the curvature is also improved, and the stability of the vehicle is improved.

[0070] In step S102, calculate the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampling trajectory to obtain the total trajectory cost of each sampling trajectory.

[0071] Specifically, the priority cost is to grade each sampling trajectory path. Among them, it can be preset that the priority level of the central path is the highest, and then it decreases from the central path to both sides in turn. The purpose is to enable the vehicle to stay on the central path when there are no obstacles; the collision cost can calculate the sampling trajectory path in two parts, namely the lateral horizontal distance from the sampling trajectory path to the obstacle and the longitudinal horizontal distance from the sampling trajectory path to the obstacle; the transition cost can limit the vehicle from frequently switching between different sampling trajectory paths, and the purpose is to ensure the smoothness of the vehicle's progress; the maximum lateral acceleration cost can be obtained through the curvature radius and vehicle speed of the sampling trajectory, and the purpose is to ensure the traceability of the sampling trajectory.

[0072] Further, in some embodiments, for the above-mentioned local path planning method of an autonomous vehicle, the calculation formula for the priority cost is as follows:

[0073] r1 = f((x t , y t ), (x o , y o )) = (y t - y0)d, (1)

[0074] The calculation formula for the collision cost is as follows:

[0075]

[0076] The calculation formula for the transition cost is as follows:

[0077] r3 = f((x t , y t ), (x t-1 , y t-1 )) = (y t - y t-1 )d, (3)

[0078] The calculation formula for the maximum lateral acceleration cost is as follows:

[0079] r4 = f(κ) = v 2 / r, (4)

[0080] Among them, r1 is the priority cost, r2 is the collision cost, r3 is the transition cost, and r4 is the maximum lateral acceleration cost; x t , y t are the coordinates of the position point on the local planned trajectory corresponding to time t; x o , y0 are the coordinates of the corresponding position point on the global path; x c , y c are the positions of the obstacles; d c is the lateral distance between the planned trajectory and the obstacle; l c is the longitudinal distance between the planned trajectory and the obstacle; x t-1 , y t-1 are the coordinates of the position point on the planned trajectory corresponding to time t - 1; r is the radius of curvature, v is the speed, and d is the trajectory density.

[0081] Specifically, in the embodiments of the present application, the total trajectory cost of each sampled trajectory can be generated by respectively performing weighted calculations on the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampled trajectory.

[0082] In step S103, based on the total trajectory cost of each sampled trajectory, the sampled trajectory with the minimum total trajectory cost is used as the optimal local path.

[0083] Further, in some embodiments, using the sampled trajectory with the minimum total trajectory cost as the optimal local path includes: calculating the total trajectory cost according to the priority cost, collision cost, transition cost, maximum lateral acceleration cost, and corresponding weight coefficients using a preset cost formula.

[0084] Among them, the calculation formula of the total trajectory cost is shown as the following formula:

[0085] Total trajectory cost = t1 * r1 + t2 * r2 + t3 * r3 + t4 * r4; (5)

[0086] Among them, t1 is the weight coefficient of the priority cost, t2 is the weight coefficient of the collision cost, t3 is the weight coefficient of the transition cost, and t4 is the weight coefficient of the maximum lateral acceleration cost.

[0087] It should be noted that the calculation of t1 to t4 can be obtained through a finite number of experiments or an adaptive formula for the weight of the cost function obtained through multi-scenario simulation tests, and t1 to t4 can all be set as constants.

[0088] For example, first set t1 as a constant, t3 = k * v * t1, where k is the speed factor of the above-mentioned sampled trajectory generation, the transition cost of t3 is related to the speed and has a relatively small impact on the total weight; t2 = t1 + 0.5t1, the weight of t2 has the greatest impact and is usually used to determine whether the sampled trajectory is blocked; t4 = t2, the weight of t4 can be set as the boundary weight and constrained longitudinally. In order to ensure the traceability of the sampled trajectory, the set weight should not be too large. It should be noted that the calculation of the above four weights only needs to sample different speeds during the vehicle driving process, so as to obtain the relevant data of the four weights at different speeds, and look up the table according to the obtained data to obtain the speed factor k. This method is applicable to most scenarios.

[0089] Thus, through the calculation of the above four weight coefficients, the corresponding total trajectory cost of each sampled trajectory is calculated using the preset cost formula (5). Through algorithm tracking simulation and data comparison, the sampled trajectory with the minimum total trajectory cost is used as the optimal local path, and then this optimal local path is sent to the vehicle control system for target tracking. Among them, the algorithm can be selected as the PID (Proportion Integral Differential, PID algorithm) algorithm for calculation, or other algorithms with related functions can be selected, which is not specifically limited here.

[0090] Furthermore, in the embodiments of the present application, by optimizing the planning method with speed and curvature constraints and the cost function adaptive formula, the path planning for different scenarios is selected. The performance comparison before and after optimization is shown in Table 1 as follows:

[0091] Table 1

[0092]

[0093] In summary, as Figure 3 shown, Figure 3 The program execution flow chart of the local path planning method for an autonomous vehicle according to an embodiment of the present application includes the following steps:

[0094] S301, Program initialization.

[0095] S302, Read the current task status and local target.

[0096] S303, Calculate the set of sub-goal points.

[0097] S304, Generate a candidate trajectory cluster.

[0098] S305, Calculate the trajectory cost.

[0099] S306, Determine whether there is an executable trajectory. If so, execute step S307; otherwise, execute step S308.

[0100] S307, Select the optimal trajectory and jump to execute step S309.

[0101] S308, Generate an abnormal trajectory.

[0102] S309, Send it to the control system and jump to execute step S302.

[0103] According to the local path planning method for an autonomous vehicle in the embodiments of the present application, at least one sampling trajectory is extracted from the full-path planning path according to the current position of the vehicle and the maximum planning distance, and the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampling trajectory are calculated. The sampling trajectory with the minimum total trajectory cost among each obtained sampling trajectory is used as the optimal local path. Thus, the problems that traditional local path planning methods need to select different cost weights to achieve path planning when dealing with different scenarios are solved. The weight selection problem is solved by adding a planning method with speed and curvature constraints and a cost function adaptive formula, improving the system's adaptive ability and the smoothness and stability of the trajectory. And the planned trajectory is tracked and simulated through an algorithm, and the corresponding total trajectory costs are compared to select the optimal local path.

[0104] Next, a partial path planning device for an autonomous vehicle according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0105] Figure 4 It is a block diagram of a partial path planning device for an autonomous vehicle according to an embodiment of the present application.

[0106] As Figure 4 shown, the partial path planning device 10 of the autonomous vehicle includes: an extraction module 100, a calculation module 200, and a selection module 300.

[0107] Among them, the extraction module 100 is used to extract at least one sampling trajectory from the full-path planning trajectory according to the current position and the maximum planning distance of the autonomous vehicle;

[0108] The calculation module 200 is used to calculate the priority cost, transition cost, and maximum lateral acceleration cost of each sampling trajectory to obtain the total trajectory cost of each sampling trajectory; and

[0109] The selection module 300 is used to select the sampling trajectory with the minimum total trajectory cost as the optimal local path based on the total trajectory cost of each sampling trajectory.

[0110] Furthermore, in some embodiments, the selection module 300 is specifically used for:

[0111] Calculating the total trajectory cost according to the priority cost, transition cost, maximum lateral acceleration cost, and corresponding weight coefficients using a preset cost formula.

[0112] Furthermore, in some embodiments, for the above-mentioned partial path planning device 10 of the autonomous vehicle, where

[0113] The calculation formula for the priority cost is:

[0114] r1 = f((x t , y t ), (x o , y o )) = (y t - y0)d,

[0115] The calculation formula for the collision cost is:

[0116]

[0117] The calculation formula for the transition cost is:

[0118] r3 = f((x t , y t ), (x t-1 , y t-1 )) = (y t - yt-1 )d,

[0119] The calculation formula for the maximum lateral acceleration cost is as follows:

[0120] r4 = f(κ) = v 2 / r,

[0121] where r1 is the priority cost, r2 is the collision cost, r3 is the transition cost, and r4 is the maximum lateral acceleration cost; x t , y t are the coordinates of the position point on the local planned trajectory corresponding to time t; x o , y0 are the coordinates of the corresponding position point on the global path; x c , y c are the positions of the obstacles; d c is the lateral distance between the planned trajectory and the obstacle; l c is the longitudinal distance between the planned trajectory and the obstacle; x t-1 , y t-1 are the coordinates of the position point on the planned trajectory corresponding to time t - 1; r is the radius of curvature, v is the speed, and d is the trajectory density.

[0122] Furthermore, in some embodiments, the preset cost formula is:

[0123] Total trajectory cost = t1 * r1 + t2 * r2 + t3 * r3 + t4 * r4,

[0124] where t1 is the weight coefficient of the priority cost, t2 is the weight coefficient of the collision cost, t3 is the weight coefficient of the transition cost, and t4 is the weight coefficient of the maximum lateral acceleration cost.

[0125] Furthermore, in some embodiments, the extraction module 100 is specifically configured to:

[0126] Based on the preset trajectory density and the preset number of trajectories, perform lateral sampling to obtain a set of target points;

[0127] Perform trajectory scattering based on the set of target points to generate at least one initial sampling trajectory;

[0128] Perform smoothing processing on each initial sampling trajectory, and screen out the initial sampling trajectories that do not meet the preset conditions to obtain at least one sampling trajectory.

[0129] The local path planning device of an autonomous vehicle according to an embodiment of the present application extracts at least one sampling trajectory from the full-path planned trajectory according to the current position of the vehicle and the maximum planning distance, and calculates the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampling trajectory. The sampling trajectory with the minimum total trajectory cost among each obtained sampling trajectory is used as the optimal local path. Thus, problems such as the need to select different cost weights to implement path planning when traditional local path planning methods are applied to different scenarios are solved. The problem of weight selection is solved by a planning method with speed and curvature constraints and an adaptive formula for the cost function, improving the system's adaptability and the smoothness and stability of the trajectory. The algorithm is used to perform tracking simulation on the planned trajectory, compare the corresponding total trajectory costs, and thus select the optimal local path.

[0130] Figure 5 The structure diagram of the vehicle provided by the embodiment of the present application. The vehicle may include:

[0131] A memory 501, a processor 502, and a computer program stored on the memory 501 and executable on the processor 502.

[0132] When the processor 502 executes the program, it implements the local path planning method of the autonomous vehicle provided in the above embodiment.

[0133] Further, the electronic device further includes:

[0134] A communication interface 503 for communication between the memory 501 and the processor 502.

[0135] The memory 501 is used to store a computer program executable on the processor 502.

[0136] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0137] If the memory 501, the processor 502, and the communication interface 503 are independently implemented, the communication interface 503, the memory 501, and the processor 502 can be interconnected through a bus and complete communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation,Figure 5 It is only represented by a thick line, but it does not mean that there is only one bus or one type of bus.

[0138] Optionally, in a specific implementation, if the memory 501, the processor 502, and the communication interface 503 are integrated on a single chip, the memory 501, the processor 502, and the communication interface 503 can communicate with each other through an internal interface.

[0139] The processor 502 may be a central processing unit (CPU for short), or an application specific integrated circuit (ASIC for short), or one or more integrated circuits configured to implement the embodiments of the present application.

[0140] This embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the local path planning method of the autonomous vehicle as described above is implemented.

[0141] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0142] In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0143] Any process or method description represented in a flowchart or otherwise described herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a customized logical function or process. The scope of the preferred embodiments of this application includes additional implementations, where functions may be executed in a substantially simultaneous manner or in the reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of this application pertain.

[0144] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with such instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection portion (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, a computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0145] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0146] Those of ordinary skill in the art can understand that all or part of the steps carried out in implementing the above-described embodiment method can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0147] In addition, in each of the embodiments of the present application, each functional unit can be integrated in a processing module, or each unit can exist physically alone, or two or more units can be integrated in a module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0148] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A local path planning method for an autonomous vehicle, characterized in that, Including the following steps: Extract at least one sampled trajectory from the full-road planned path according to the current position of the autonomous vehicle and the maximum planned distance; Calculate the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampled trajectory to obtain the total trajectory cost of each sampled trajectory; And Based on the total trajectory cost of each sampled trajectory, take the sampled trajectory with the minimum total trajectory cost as the optimal local path; Wherein, taking the sampled trajectory with the minimum total trajectory cost as the optimal local path includes: calculating the total trajectory cost according to the priority cost, the collision cost, the transition cost, the maximum lateral acceleration cost, and the corresponding weight coefficients using a preset cost formula, where The calculation formula for the priority cost is: r1 = f((x t , y t ), (x o , y o )) = (y t - y0)d, The calculation formula for the collision cost is: The calculation formula for the transition cost is: r3 = f((x t , y t ), (x t-1 , y t-1 )) = (y t - y t-1 )d, The calculation formula for the maximum lateral acceleration cost is: r4 = f(κ) = v 2 / r, Among them, r1 is the priority cost, r2 is the collision cost, r3 is the transition cost, and r4 is the maximum lateral acceleration cost; x t , y t are the coordinates of the position point on the local planned trajectory at time t; x o , y0 are the coordinates of the corresponding position point on the global path; x c , y c are the obstacle positions; d c is the lateral distance between the planned trajectory and the obstacle; l c is the longitudinal distance between the planned trajectory and the obstacle; x t-1 , y t-1 are the coordinates of the position point on the planned trajectory at time t - 1; r is the radius of curvature, v is the speed, and d is the trajectory density; The preset cost formula is: Total trajectory cost = t1*r1 + t2*r2 + t3*r3 + t4*r4, Wherein, t1 is the weight coefficient of the priority cost, t2 is the weight coefficient of the collision cost, t3 is the weight coefficient of the transition cost, and t4 is the weight coefficient of the maximum lateral acceleration cost.

2. The method according to claim 1, wherein The extracting at least one sampled trajectory from the full-road planned path according to the current position of the autonomous vehicle and the maximum planned distance includes: Based on a preset trajectory density and a preset number of trajectories, perform lateral sampling to obtain a set of target points; Based on the set of target points, scatter points for trajectories to generate at least one initial sampled trajectory; Perform smoothing processing on each initial sampled trajectory, and screen out the initial sampled trajectories that do not meet the preset conditions to obtain the at least one sampled trajectory.

3. A local path planning device for an autonomous vehicle, characterized in that, Including: An extraction module for extracting at least one sampled trajectory from the full-road planned path according to the current position of the autonomous vehicle and the maximum planned distance; A calculation module for calculating the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampled trajectory to obtain the total trajectory cost of each sampled trajectory; And A selection module for taking the sampled trajectory with the minimum total trajectory cost as the optimal local path based on the total trajectory cost of each sampled trajectory; Wherein, the selection module is specifically used for: calculating the total trajectory cost according to the priority cost, the transition cost, the maximum lateral acceleration cost, and the corresponding weight coefficients using a preset cost formula, where The calculation formula for the priority cost is: r1 = f((x t , y t ), (x o , y o )) = (y t - y0)d, The calculation formula for the collision cost is: The calculation formula for the transition cost is: r3 = f((x t , y t ), (x t-1 , y t-1 )) = (y t - y t-1 )d, The calculation formula for the maximum lateral acceleration cost is: r4 = f(κ) = v 2 / r, Among them, r1 is the priority cost, r2 is the collision cost, r3 is the transition cost, and r4 is the maximum lateral acceleration cost; x t , y t are the coordinates of the position point on the local planned trajectory at time t; x o , y0 are the coordinates of the corresponding position point on the global path; x c , y c is the obstacle position; d c is the lateral distance between the planned trajectory and the obstacle; l c is the longitudinal distance between the planned trajectory and the obstacle; x t-1 , y t-1 are the coordinates of the position point on the planned trajectory at time t - 1; r is the radius of curvature, v is the speed, and d is the trajectory density; The preset cost formula is: Total trajectory cost = t1*r1 + t2*r2 + t3*r3 + t4*r4, Wherein, t1 is the weight coefficient of the priority cost, t2 is the weight coefficient of the collision cost, t3 is the weight coefficient of the transition cost, and t4 is the weight coefficient of the maximum lateral acceleration cost.

4. A vehicle, characterized in that, Including: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the local path planning method of the autonomous vehicle according to any one of claims 1-2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the local path planning method of the autonomous vehicle according to any one of claims 1-2.

Images