Path planning method and device, vehicle and storage medium

Abstract

The application relates to the technical field of path planning, in particular to a path planning method and device, a vehicle and a storage medium, wherein the method comprises the following steps: acquiring path planning information; generating an initial path population of first iteration optimization according to the path planning information; using multiple path optimization algorithms to iteratively optimize the initial path population to obtain multiple optimized path populations; generating an optimal path population of current iteration optimization according to paths meeting a first preset condition in the multiple optimized path populations, and taking the optimal path population of current iteration optimization as an initial path population of next iteration optimization until the iteration is stopped when a second preset condition is met; and determining an optimal planning path corresponding to the path planning information according to the optimal path population. Thus, the problems that, in the related art, a single algorithm is used to solve a path problem, the efficiency is low, the algorithm is prone to premature convergence into a local optimal solution, and an optimal path cannot be quickly and accurately determined are solved.

Description

Technical Field

[0001] This application relates to the field of path planning technology, and in particular to a path planning method, apparatus, vehicle and storage medium. Background Technology

[0002] During operation, autonomous vehicles need to acquire obstacle information through environmental perception modules and make planning decisions based on the information. They then calculate a local planning route that takes the shortest time and meets obstacle avoidance constraints based on the global navigation path.

[0003] Commonly used intelligent optimization algorithms include genetic algorithms, differential evolution algorithms, fuzzy control algorithms, ant colony algorithms, distribution estimation algorithms, and particle swarm optimization algorithms. However, these technologies generally obtain the optimal path through a single intelligent optimization algorithm. However, a single intelligent optimization algorithm is inefficient and is prone to premature convergence and getting trapped in local optima, thus failing to obtain a fast and accurate optimal path solution. Summary of the Invention

[0004] This application provides a path planning method, apparatus, vehicle, and storage medium to address the problems of low efficiency, premature convergence and local optima, and inability to quickly and accurately determine the optimal path when using a single algorithm to solve path problems in related technologies.

[0005] A first aspect of this application provides a path planning method, comprising the following steps: obtaining path planning information; generating an initial path population for the first iteration of optimization based on the path planning information; iteratively optimizing the initial path population using multiple path optimization algorithms to obtain multiple optimized path populations; generating an optimal path population for the current iteration of optimization based on the paths in the multiple optimized path populations that satisfy a first preset condition; using the optimal path population for the current iteration of optimization as the initial path population for the next iteration of optimization; stopping the iteration when a second preset condition is met; and determining the optimal planned path corresponding to the path planning information based on the optimal path population.

[0006] Optionally, in one embodiment of this application, generating the optimal path population for the current iteration of optimization based on the paths that satisfy the first preset condition from the plurality of optimized path populations includes: calculating the evaluation value of each path in the plurality of optimized path populations; sorting all paths according to the evaluation values; and selecting a preset number of paths as the optimal path population in a preset order.

[0007] Optionally, in one embodiment of this application, calculating the evaluation value of each path in the plurality of optimized path populations includes: determining the constraint violation level of each path using a constraint violation function, wherein the constraint conditions of the constraint violation function include moving body curvature constraints and / or obstacle constraints; calculating the evaluation value of each path based on the total path length and constraint violation level of each path, wherein the shorter the path and the smaller the constraint violation level, the better the corresponding evaluation value.

[0008] Optionally, in one embodiment of this application, the plurality of path optimization algorithms includes a first path optimization algorithm and a second path optimization algorithm. The step of iteratively optimizing the initial path population using the plurality of path optimization algorithms to obtain a plurality of optimized path populations includes using the first path optimization algorithm to perform random optimization on the initial path population to obtain a first optimized path population; and using the second path optimization algorithm to perform global optimization on the initial path population to obtain a second optimized path population.

[0009] Optionally, in one embodiment of this application, the step of randomly optimizing the initial path population using the first path optimization algorithm to obtain a first optimized path population includes: initializing the initial path population; selecting a feasible solution set from the initial path population; establishing a probability distribution model based on the feasible solution set; and sampling the probability distribution model to obtain a candidate solution set; and generating the first optimized path population based on the candidate solution set and the initial path population.

[0010] Optionally, in one embodiment of this application, the step of globally optimizing the initial path population using the second path optimization algorithm to obtain a second optimized path population includes: obtaining a mutation operator and a crossover operator; performing a mutation operation on the initial path population according to the mutation operator to obtain a mutation vector, and performing a crossover operation on the mutation vector according to the crossover operator to obtain a trial vector; and using the target vector corresponding to the initial path population and the vector with the smaller cost function value among the trial vectors as the second optimized path population.

[0011] Optionally, in one embodiment of this application, generating the initial path population for the first iteration of optimization based on the path planning information includes: randomly generating an initial path population of a preset size based on the path planning information.

[0012] A second aspect of this application provides a path planning apparatus, comprising: an acquisition module for acquiring path planning information; an iteration module for generating an initial path population for the first iteration optimization based on the path planning information, iteratively optimizing the initial path population using multiple path optimization algorithms to obtain multiple optimized path populations, generating an optimal path population for the current iteration optimization based on paths in the multiple optimized path populations that satisfy a first preset condition, and using the optimal path population for the current iteration optimization as the initial path population for the next iteration optimization, until the iteration stops when a second preset condition is met; and a determination module for determining the optimal planned path corresponding to the path planning information based on the optimal path population.

[0013] Optionally, in one embodiment of this application, the iteration module includes: a calculation unit for calculating the evaluation value of each path in the plurality of optimized path populations; and a selection unit for sorting all paths according to the evaluation values ​​and selecting a preset number of paths as the optimal path population in a preset order.

[0014] Optionally, in one embodiment of this application, the calculation unit is further configured to determine the constraint violation level of each path using a constraint violation function, wherein the constraint conditions of the constraint violation function include moving body curvature constraints and / or obstacle constraints; and to calculate the evaluation value of each path based on the total path length and constraint violation level of each path, wherein the shorter the path and the lower the violation constraint level, the better the corresponding evaluation value.

[0015] Optionally, in one embodiment of this application, the plurality of path optimization algorithms includes a first path optimization algorithm and a second path optimization algorithm, and the iterative module includes: a first optimization unit, used to perform random optimization on the initial path population using the first path optimization algorithm to obtain a first optimized path population; and a second optimization unit, used to perform global optimization on the initial path population using the second path optimization algorithm to obtain a second optimized path population.

[0016] Optionally, in one embodiment of this application, the first optimization unit is further configured to initialize the initial path population; select feasible solutions from the initial path population; establish a probability distribution model based on the feasible solutions; and sample the probability distribution model to obtain a candidate solution set; and generate the first optimized path population based on the candidate solution set and the initial path population.

[0017] Optionally, in one embodiment of this application, the second optimization unit is further configured to obtain a mutation operator and a crossover operator; perform a mutation operation on the initial path population according to the mutation operator to obtain a mutation vector, and perform a crossover operation on the mutation vector according to the crossover operator to obtain a trial vector; and use the target vector corresponding to the initial path population and the vector with the smaller cost function value among the trial vectors as the second optimized path population.

[0018] Optionally, in one embodiment of this application, the iteration module is further configured to randomly generate an initial path population of a preset size based on the path planning information.

[0019] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the path planning method as described in the above embodiments.

[0020] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the path planning method as described in the above embodiments.

[0021] Therefore, this application has at least the following beneficial effects:

[0022] This application's embodiments generate an initial path population based on path planning information, iteratively optimize the initial path population using multiple path optimization algorithms to obtain multiple optimized path populations, and select the path that meets a first preset condition to generate the current iteratively optimized optimal path population as the initial path population for the next iterative optimization, until a stopping condition is met to stop iterating and obtain the optimal path population, and select the optimal path as the path planning solution. Therefore, by fully combining the advantages of multiple path optimization algorithms, the diversity of the population is increased, the search efficiency is higher, the search accuracy is higher, and the globally optimal path can be obtained. This solves the problems of low efficiency, premature convergence and getting trapped in local optima, and inability to quickly and accurately determine the optimal path when using a single algorithm to solve path problems in related technologies.

[0023] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0024] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0025] Figure 1 This is a flowchart of a path planning method provided according to an embodiment of this application;

[0026] Figure 2 This is a block diagram of a path planning device according to an embodiment of this application;

[0027] Figure 3 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0028] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein 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 accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0029] The path planning method, apparatus, vehicle, and storage medium of this application are described below with reference to the accompanying drawings. Addressing the problems mentioned in the background section, this application provides a path planning method. In this method, an initial path population is generated based on path planning information. Multiple path optimization algorithms are used to iteratively optimize the initial path population to obtain multiple optimized path populations. Paths satisfying a first preset condition are selected to generate the optimal path population for the current iteration, which is then used as the initial path population for the next iteration. Iteration continues until a stopping condition is met, resulting in the optimal path population. The optimal path is then selected as the path planning solution. Therefore, by fully combining the advantages of multiple path optimization algorithms, the diversity of the population is increased, resulting in higher search efficiency and accuracy. This allows for the acquisition of globally optimal paths, solving the problems of low efficiency, premature convergence into local optima, and inability to quickly and accurately determine the optimal path when using a single algorithm to solve path problems in related technologies.

[0030] Specifically, Figure 1 This is a flowchart illustrating a path planning method provided in an embodiment of this application.

[0031] like Figure 1 As shown, this path planning method includes the following steps:

[0032] In step S101, path planning information is obtained.

[0033] In this embodiment, the path planning information may include: the starting and ending points of the motion, curvature constraints of the moving body, and obstacle constraints, wherein the curvature constraint of the moving body refers to the minimum turning radius r of the moving body. tc Waypoints are connected using Dubins paths with limited curvature; obstacle information refers to the coordinates and range of obstacles.

[0034] In step S102, an initial path population for the first iteration of optimization is generated based on the path planning information. Multiple path optimization algorithms are used to iteratively optimize the initial path population to obtain multiple optimized path populations. The optimal path population for the current iteration of optimization is generated based on the paths in the multiple optimized path populations that meet the first preset condition. The optimal path population for the current iteration of optimization is then used as the initial path population for the next iteration of optimization. The iteration continues until the second preset condition is met.

[0035] In this embodiment of the application, the path of the first preset condition is selected by calculating the evaluation value, and the second preset condition can be the maximum number of iterations.

[0036] Different algorithms have their own advantages and disadvantages. The embodiments of this application can complement the advantages of multiple algorithms to improve algorithm efficiency and obtain the optimal solution.

[0037] In one embodiment of this application, generating an initial path population for the first iteration of optimization based on path planning information includes: randomly generating an initial path population of a preset size based on path planning information.

[0038] The preset size can be set according to the actual situation without specific limitations.

[0039] It is understood that in the embodiments of this application, the coordinates and range of obstacles can be initialized as infeasible areas; the control variables and parameter population size N can be initialized, and multiple paths can be determined by the starting position, ending position, intermediate waypoint position and orientation in the path planning information, thereby obtaining an initial path population with a random size of N.

[0040] In one embodiment of this application, the multiple path optimization algorithms include a first path optimization algorithm and a second path optimization algorithm. The initial path population is iteratively optimized using the multiple path optimization algorithms to obtain multiple optimized path populations. This includes using the first path optimization algorithm to perform random optimization on the initial path population to obtain a first optimized path population; and using the second path optimization algorithm to perform global optimization on the initial path population to obtain a second optimized path population.

[0041] In one embodiment of this application, a first path optimization algorithm is used to randomly optimize an initial path population to obtain a first optimized path population, including: initializing the initial path population; selecting a feasible solution set from the initial path population; establishing a probability distribution model based on the feasible solution set; and sampling the probability distribution model to obtain a candidate solution set; and generating the first optimized path population based on the candidate solution set and the initial path population.

[0042] In this embodiment of the application, the first path optimization algorithm can be a distribution estimation algorithm, which can directly extract global statistical information from the initial path population, establish a probability model of candidate solutions, and sample new candidate solutions from the established model.

[0043] Specifically, the steps for generating a path population of a predetermined size using a distribution estimation algorithm are as follows:

[0044] (1) Initialize the initial path population P(0), G=0.

[0045] (2) Select a feasible solution set S(G) from P(G), and establish a probability model for the feasible solutions using a Gaussian distribution; establish the probability distribution model, which adopts a Gaussian mixture distribution model:

[0046]

[0047] Where p(x) k j ) is the edge density function in the j-th dimension, N(μ) i,j k ,σ i,j k ) represents the j-th dimension component of the i-th individual in the k-th generation, which is a normal distribution; α i k This represents the weighting coefficient of a Gaussian mixture distribution.

[0048] (3) Sample the probability model to obtain a new candidate solution O(G).

[0049] (4) By selecting, O(G) is combined with P(G), and G = G + 1.

[0050] In one embodiment of this application, a second path optimization algorithm is used to globally optimize the initial path population to obtain a second optimized path population, including: obtaining a mutation operator and a crossover operator; performing a mutation operation on the initial path population according to the mutation operator to obtain a mutation vector, and performing a crossover operation on the mutation vector according to the crossover operator to obtain a trial vector; and using the vector with the smaller cost function value among the target vector and the trial vector corresponding to the initial path population as the second optimized path population.

[0051] In this embodiment, the second path optimization algorithm can be a differential evolution algorithm, which can solve the optimization problem through competition and cooperation among populations, extract differential information from the current population to guide further search and development, including mutation, crossover and selection operations.

[0052] Specifically, the steps for generating a path population of a predetermined size using the differential evolution algorithm are as follows:

[0053] (1) Mutation operator

[0054] For each target vector xi, i = 1, 2, 3... NP, the mutation vector is generated by formula (1):

[0055] v i,G+1 =x r1,G +F(x r2,G -x r3,G )

[0056] The random exponents r1, r2, r3 ∈ {1, 2, ..., NP} are all integers and distinct, and the exponents i are also distinct. Therefore, NP must be greater than or equal to 4 to satisfy the condition. F controls the difference variation (x r2；G -x r3；G The magnification factor of ), where F is a real constant belonging to [0,2].

[0057] (2) Cross operator

[0058] To increase the diversity of the perturbation parameter vector, a crossover operation is introduced to form a trial vector u. i,G+1 =(u 1i,G+1 ,u 2i,G+1 ,...,u Di,G+1 ),in

[0059]

[0060] j = 1, 2, ..., D.

[0061] Where randb(j) is a random value belonging to [0,1] that follows a uniform random distribution. CR is a crossover constant belonging to [0,1], determined by the user. Rnbr(i) is an integer randomly selected from 1,2,…,D to ensure u i,G+1 From v i,G+1 Obtain at least one parameter.

[0062] (3) Selection Operator

[0063] The selection determines whether the trial vector should become a member of generation G+1, using a greedy criterion to select the trial vector u. i,G+1 With the target vector x i,G Compare. If u i,G+1 If a cost function value smaller than xi,G is produced, then x i,G+1 =u i,G+1 Otherwise, x i,G+1 =x i,G .

[0064] In one embodiment of this application, generating the optimal path population for the current iteration of optimization based on paths that satisfy a first preset condition from multiple optimized path populations includes: calculating the evaluation value of each path in the multiple optimized path populations; sorting all paths according to the evaluation values; and selecting a preset number of paths as the optimal path population in a preset order.

[0065] In this embodiment, each path in multiple optimized path populations can be sorted according to its evaluation value, and the top N populations can be selected as the optimal path population for the current iteration of optimization, thereby increasing population diversity, improving search efficiency, and increasing search accuracy.

[0066] In one embodiment of this application, the evaluation value of each path in a plurality of optimized path populations is calculated, including: determining the constraint violation level of each path using a constraint violation function, wherein the constraint conditions of the constraint violation function include moving body curvature constraints and / or obstacle constraints; calculating the evaluation value of each path based on the total path length and constraint violation level of each path, wherein the shorter the path and the smaller the constraint violation level, the better the corresponding evaluation value.

[0067] Specifically, in this embodiment, the generated initial path can be evaluated using the evaluation function F(n) = H(n) + G(n): the evaluation index H(n) is the total path length, and G(n) is the constraint violation function. The constraints include the curvature constraint of the moving body and the obstacle constraint. The shorter the path and the smaller the degree of constraint violation, the better the evaluation value. When the degree of path constraint violation is equal, the path with the shorter total path length ranks higher; when the degree of path constraint violation is unequal, the path with the smaller degree of constraint violation ranks higher.

[0068] In step S103, the optimal planning path corresponding to the path planning information is determined based on the optimal path population.

[0069] It is understood that the embodiments of this application can use multiple path optimization algorithms to iteratively optimize the initial path population multiple times until the stopping condition is met to obtain the optimal path population, and select the local planning path with the shortest time and the obstacle avoidance constraint from the optimal path population.

[0070] According to the path planning method proposed in this application, an initial path population is generated based on path planning information. Multiple path optimization algorithms are used to iteratively optimize the initial path population to obtain multiple optimized path populations. The path that satisfies a first preset condition is selected to generate the optimal path population for the current iteration, which is then used as the initial path population for the next iteration. Iteration continues until a stopping condition is met, at which point the optimal path population is obtained, and the optimal path is selected as the path planning solution. Therefore, by fully combining the advantages of multiple path optimization algorithms, the diversity of the population is increased, resulting in higher search efficiency and accuracy. This allows for the acquisition of globally optimal paths, solving the problems of low efficiency, premature convergence to local optima, and inability to quickly and accurately determine the optimal path when using a single algorithm to solve path problems in related technologies.

[0071] Next, the path planning apparatus proposed according to the embodiments of this application is described with reference to the accompanying drawings.

[0072] Figure 2 This is a block diagram of a path planning device according to an embodiment of this application.

[0073] like Figure 2 As shown, the path planning device 10 includes: an acquisition module 100, an iteration module 200, and a determination module 300.

[0074] The acquisition module 100 is used to acquire path planning information; the iteration module 200 is used to generate an initial path population for the first iteration optimization based on the path planning information, iterate and optimize the initial path population using multiple path optimization algorithms to obtain multiple optimized path populations, generate the optimal path population for the current iteration optimization based on the paths in the multiple optimized path populations that meet the first preset condition, and use the optimal path population for the current iteration optimization as the initial path population for the next iteration optimization, until the iteration stops when the second preset condition is met; the determination module 300 is used to determine the optimal planned path corresponding to the path planning information based on the optimal path population.

[0075] In one embodiment of this application, the iteration module 200 includes a calculation unit and a selection unit.

[0076] The calculation unit is used to calculate the evaluation value of each path in the multiple optimized path populations; the selection unit is used to sort all paths according to the evaluation values ​​and select a preset number of paths as the optimal path population according to a preset order.

[0077] In one embodiment of this application, the calculation unit is further configured to determine the constraint violation level of each path using a constraint violation function, wherein the constraint conditions of the constraint violation function include moving body curvature constraints and / or obstacle constraints; and to calculate the evaluation value of each path based on the total path length and constraint violation level of each path, wherein the shorter the path and the lower the violation constraint level, the better the corresponding evaluation value.

[0078] In one embodiment of this application, the plurality of path optimization algorithms include a first path optimization algorithm and a second path optimization algorithm, and the iteration module 200 further includes a first optimization unit and a second optimization unit.

[0079] The first optimization unit is used to randomly optimize the initial path population using the first path optimization algorithm to obtain the first optimized path population; the second optimization unit is used to globally optimize the initial path population using the second path optimization algorithm to obtain the second optimized path population.

[0080] In one embodiment of this application, the first optimization unit is further configured to initialize an initial path population; select a feasible solution set from the initial path population; establish a probability distribution model based on the feasible solution set; and sample the probability distribution model to obtain a candidate solution set; and generate a first optimized path population based on the candidate solution set and the initial path population.

[0081] In one embodiment of this application, the second optimization unit is further used to obtain a mutation operator and a crossover operator; to perform a mutation operation on the initial path population according to the mutation operator to obtain a mutation vector, and to perform a crossover operation on the mutation vector according to the crossover operator to obtain a trial vector; and to take the target vector corresponding to the initial path population and the vector with the smaller cost function value among the trial vectors as the second optimized path population.

[0082] In one embodiment of this application, the iteration module 200 is further configured to randomly generate an initial path population of a preset size based on path planning information.

[0083] It should be noted that the foregoing explanation of the path planning method embodiment also applies to the path planning device of this embodiment, and will not be repeated here.

[0084] The path planning apparatus proposed in this application generates an initial path population based on path planning information. Multiple path optimization algorithms are used to iteratively optimize the initial path population to obtain multiple optimized path populations. Paths satisfying a first preset condition are selected to generate the current optimal path population for iterative optimization, which is then used as the initial path population for the next iteration. Iteration continues until a stopping condition is met, at which point the optimal path population is obtained, and the optimal path is selected as the path planning solution. Therefore, by fully combining the advantages of multiple path optimization algorithms, the diversity of the population is increased, resulting in higher search efficiency and accuracy. This allows for the acquisition of globally optimal paths, solving the problems of low efficiency, premature convergence into local optima, and inability to quickly and accurately determine the optimal path when using a single algorithm to solve path problems in related technologies.

[0085] Figure 3 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0086] The memory 301, the processor 302, and the computer program stored on the memory 301 and capable of running on the processor 302.

[0087] When the processor 302 executes the program, it implements the path planning method provided in the above embodiments.

[0088] Furthermore, the vehicle also includes:

[0089] Communication interface 303 is used for communication between memory 301 and processor 302.

[0090] The memory 301 is used to store computer programs that can run on the processor 302.

[0091] The memory 301 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0092] If the memory 301, processor 302, and communication interface 303 are implemented independently, then the communication interface 303, memory 301, and processor 302 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0093] Optionally, in a specific implementation, if the memory 301, processor 302, and communication interface 303 are integrated on a single chip, then the memory 301, processor 302, and communication interface 303 can communicate with each other through an internal interface.

[0094] Processor 302 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.

[0095] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the path planning method described above.

[0096] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0097] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0098] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0099] It should be understood that the 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 memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0100] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

Claims

1. A path planning method, characterized in that, Includes the following steps: Obtain path planning information; The initial path population for the first iteration of optimization is generated based on the path planning information. Multiple path optimization algorithms are used to iteratively optimize the initial path population to obtain multiple optimized path populations. The optimal path population for the current iteration of optimization is generated based on the paths in the multiple optimized path populations that meet the first preset condition. The optimal path population for the current iteration of optimization is used as the initial path population for the next iteration of optimization. The iteration stops when the second preset condition is met. The optimal planning path corresponding to the path planning information is determined based on the optimal path population. The multiple path optimization algorithms include a first path optimization algorithm and a second path optimization algorithm. The step of iteratively optimizing the initial path population using these multiple path optimization algorithms to obtain multiple optimized path populations includes: The initial path population is randomly optimized using the first path optimization algorithm to obtain a first optimized path population. The initial path population is globally optimized using the second path optimization algorithm to obtain the second optimized path population. The step of generating the optimal path population for the current iteration of optimization based on the paths satisfying the first preset condition from the plurality of optimized path populations includes: Calculate the evaluation value of each path in the plurality of optimized path populations; All paths are sorted according to the evaluation value, and a preset number of paths are selected as the optimal path population in a preset order. When the degree of path constraint violation is equal, the path with the smaller total path length ranks higher; when the degree of path constraint violation is unequal, the path with the smaller degree of constraint violation ranks higher.

2. The method according to claim 1, characterized in that, The calculation of the evaluation value of each path in the plurality of optimized path populations includes: The constraint violation level of each path is determined using a constraint violation function, wherein the constraint conditions of the constraint violation function include the curvature constraint of the moving body and / or the obstacle constraint. The evaluation value of each path is calculated based on the total path length and the constraint violation level of each path. The shorter the path and the lower the violation constraint level, the better the corresponding evaluation value.

3. The method according to claim 1, characterized in that, The step of randomly optimizing the initial path population using the first path optimization algorithm to obtain a first optimized path population includes: Initialize the initial path population; A feasible solution set is selected from the initial path population, a probability distribution model is established based on the feasible solution set, and a candidate solution set is obtained by sampling the probability distribution model; The first optimized path population is generated based on the candidate solution set and the initial path population.

4. The method according to claim 1, characterized in that, The step of using the second path optimization algorithm to globally optimize the initial path population to obtain the second optimized path population includes: Obtain the mutation and crossover operators; The mutation vector is obtained by performing a mutation operation on the initial path population according to the mutation operator, and a trial vector is obtained by performing a crossover operation on the mutation vector according to the crossover operator. The target vector corresponding to the initial path population and the vector with the smaller cost function value among the trial vectors are used as the second optimized path population.

5. The method according to claim 1, characterized in that, The step of generating the initial path population for the first iteration of optimization based on the path planning information includes: An initial path population of a preset size is randomly generated based on the path planning information.

6. A path planning device, characterized in that, include: The acquisition module is used to obtain path planning information; The iteration module is used to generate an initial path population for the first iteration optimization based on the path planning information, iteratively optimize the initial path population using multiple path optimization algorithms to obtain multiple optimized path populations, generate the optimal path population for the current iteration optimization based on the paths in the multiple optimized path populations that meet the first preset condition, and use the optimal path population for the current iteration optimization as the initial path population for the next iteration optimization, until the iteration stops when the second preset condition is met. The determination module is used to determine the optimal planning path corresponding to the path planning information based on the optimal path population; The multiple path optimization algorithms include a first path optimization algorithm and a second path optimization algorithm. The step of iteratively optimizing the initial path population using these multiple path optimization algorithms to obtain multiple optimized path populations includes: The initial path population is randomly optimized using the first path optimization algorithm to obtain a first optimized path population. The initial path population is globally optimized using the second path optimization algorithm to obtain the second optimized path population. The step of generating the optimal path population for the current iteration of optimization based on the paths satisfying the first preset condition from the plurality of optimized path populations includes: Calculate the evaluation value of each path in the plurality of optimized path populations; All paths are sorted according to the evaluation value, and a preset number of paths are selected as the optimal path population in a preset order. When the degree of path constraint violation is equal, the path with the smaller total path length ranks higher; when the degree of path constraint violation is unequal, the path with the smaller degree of constraint violation ranks higher.

7. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the path planning method as described in any one of claims 1-5.

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

Images