Path planning method, system, storage medium and device based on fusion algorithm

Abstract

The present invention proposes a path planning method, system, storage medium and device based on a fusion algorithm, the method comprising: initializing a grid map, determining a starting point and an end point; setting CPO algorithm parameters, establishing an improved adaptive weight coefficient objective function, and initializing a population, covering a search space, for global path planning using an improved CPO algorithm; obtaining vehicle information, taking the next key point in the global path as a target point, and using a DWA algorithm for local path regularization based on an improved trajectory scoring function according to a preset rule; updating vehicle position information, and obtaining a comparison result between the vehicle position information and the end point position information, and completing path planning based on the comparison result. The present invention can prevent premature convergence during global path planning, realize multi-objective optimization of global path planning, and avoid falling into a local optimal solution during local planning by extracting key points in the global path as the target points of the algorithm, while realizing dynamic obstacle avoidance.

Description

Technical Field

[0001] The present invention relates to the field of path planning, and in particular to a path planning method, system, storage medium and device based on a fusion algorithm. Background Art

[0002] With the rapid development of modern intelligent transportation and autonomous driving technologies, vehicle path planning has become one of the core technologies to ensure safe, efficient and intelligent driving. Path planning aims to provide the best driving route for the vehicle, which needs to comprehensively consider complex factors such as road topology, dynamic obstacles, traffic rules and vehicle physical limitations.

[0003] At present, in the field of path planning, global path algorithms include Dijkstra algorithm, PSO algorithm and GA algorithm. Dijkstra algorithm is suitable for finding the shortest path in static environment, PSO algorithm is suitable for path planning in dynamic environment, and GA algorithm is suitable for path planning in complex environment and multi-objective optimization problems. Local path planning algorithms include DWA algorithm and TEB algorithm. DWA and TEB algorithms each have their own advantages and applicable scenarios. The DWA algorithm is suitable for resource-constrained systems due to its simplicity and efficiency, while the TEB algorithm is suitable for application scenarios that require more sophisticated path planning and posture management due to its ability to provide smooth trajectory and optimized posture control.

[0004] However, the above-mentioned global path algorithm has the problem of premature convergence and insufficient path exploration, and is prone to falling into local optimality. It often needs to be combined with other algorithms to prevent falling into local optimal solutions. It also takes a long time to solve and cannot adapt well to dynamic environments and multi-objective optimization. The local path planning algorithm relies on the global information of the map. If the global information is insufficient, the local path planning is prone to falling into local optimality. Summary of the invention

[0005] Based on this, the purpose of the present invention is to provide a path planning method, system, storage medium and device based on a fusion algorithm, aiming to solve the problem that the current global path algorithm is prone to fall into local optimality, has a long solution time, and cannot adapt well to dynamic environments and multi-objective optimization; the local path planning algorithm relies on the global information of the map. If the global information is insufficient, the local path planning is prone to fall into the local optimal problem.

[0006] To achieve the above object, the present invention proposes a path planning method based on a fusion algorithm, and the path planning method based on a fusion algorithm includes:

[0007] Initialize the grid map and determine the starting and ending points;

[0008] Set the CPO algorithm parameters, establish the improved adaptive weight coefficient objective function, and initialize the population to cover the search space for global path planning using the improved CPO algorithm;

[0009] Obtain vehicle information, take the next key point in the global path as the target point, and use the DWA algorithm to perform local path regularization based on the improved trajectory scoring function based on preset rules;

[0010] The vehicle position information is updated, and a comparison result between the vehicle position information and the destination position information is obtained, and the path planning is completed based on the comparison result.

[0011] In summary, according to a path planning method based on a fusion algorithm proposed in the present invention, the grid map is initialized, and the starting point and end point of the path planning are determined; the CPO algorithm parameters are set, and an improved adaptive weight coefficient objective function is established based on the path length, obstacle avoidance penalty, and the distance from the path end point to the target, and the search space is covered for global path planning; vehicle information is obtained, and a trajectory scoring function is obtained based on the vehicle information; the vehicle information is updated to determine whether the current position is the end point position, if not, the third step is repeated.

[0012] The present invention can avoid falling into local optimum in global path planning, prevent premature convergence and insufficient exploration of search space in global path planning, realize multi-objective optimization of global path planning, and provide optimal global information for the DWA algorithm by extracting key points in the global path as target points of the DWA algorithm, avoid falling into local optimum solution in local planning, and realize dynamic obstacle avoidance at the same time.

[0013] According to one aspect of the above technical solution, the steps of setting CPO algorithm parameters, establishing an improved adaptive weight coefficient objective function, and initializing a population to cover a search space for global path planning using an improved CPO algorithm specifically include:

[0014] Set the CPO algorithm parameters, including at least the number of proxy requests , maximum number of iterations , search space upper boundary and the lower boundary , number of path points, number of loops , convergence rate The trade-off percentage between the third and fourth defense mechanisms ;

[0015] And establish an improved adaptive weight coefficient objective function that takes into account the path length, obstacle avoidance penalty and the distance from the path end point to the target. The improved adaptive weight coefficient objective function is:

[0016]

[0017] in, , , are weight coefficients, is the total length of the normalized path, To avoid obstacle penalties, is the distance from the regularized path to the end point;

[0018] The global path planning dynamically adjusts the weight coefficient according to the contribution rate of the objective function of the improved adaptive weight coefficient. The dynamic adjustment formula is as follows:

[0019]

[0020] in , , is the contribution rate, , , is the basic weight coefficient, To adjust the weight factor coefficient.

[0021] According to one aspect of the above technical solution, the initialization population covers the search space, and the covering formula includes:

[0022]

[0023] in, represents the first Candidate solution, and are the upper and lower limits of the search space range, respectively. represents a random number of [0 1], ;

[0024] Based on the coverage, a first defense mechanism, a second defense mechanism, a third defense mechanism, and a fourth defense mechanism are established, and a corresponding defense mechanism is selected to search the search space, and a random number is generated at the initial stage of exploration. and ,when , then enter the global search phase and generate a random number and ,like , then the first defense mechanism is selected. , then choose the second defense mechanism;

[0025] when , then enter the local exploration phase and generate random numbers ,like , choose the third defense mechanism, when , select the fourth defense mechanism.

[0026] According to one aspect of the above technical solution, the initialization of the population and the covering of the search space step include:

[0027] Establish an adaptive perturbation mechanism to enhance population diversity and Search Agent Make a perturbation:

[0028]

[0029]

[0030] in, represents the generated disturbance, Indicates the number of path points, each component , , …, The value range is [-4, 4]. is the position of the i-th individual in the t-th iteration, represents the position of the i-th individual in the t+1 iteration.

[0031] According to one aspect of the above technical solution, after establishing the adaptive disturbance mechanism, an improved cyclic population reduction mechanism is established:

[0032]

[0033] in, is the current population size, represents the initial population size, represents the minimum population size, represents the number of iterations, represents the maximum number of iterations, Indicates the number of cycles, Represents the remainder operation;

[0034] Dynamic adjustment of minimum population size:

[0035] (- )

[0036] in, Indicates the increase, Represents the decay rate.

[0037] According to one aspect of the above technical solution, the step of obtaining vehicle information, taking the next key point in the global path as the target point, and using the DWA algorithm to perform local path regularization based on an improved trajectory scoring function according to preset rules specifically includes:

[0038] Obtain the current vehicle status information, based on the kinematic model and driving space constraints on the vehicle's driving status, and the vehicle's driving speed limit for:

[0039]

[0040] in, is the minimum speed of the vehicle, is the maximum speed of the vehicle, is the minimum yaw rate of the vehicle, is the maximum yaw rate of the vehicle;

[0041] Vehicle acceleration limits :

[0042]

[0043] in, is the current linear velocity, is the current angular velocity, and are the maximum acceleration limits, and = , and are the maximum angular acceleration allowed, and = ;

[0044] Obstacle restrictions :

[0045] .

[0046] According to one aspect of the above technical solution, in the step of improving the trajectory scoring function based on the preset rule, the trajectory scoring function is:

[0047]

[0048] in, is the heading angle evaluation function, Indicates the distance to the nearest obstacle. represents the vehicle linear speed, , , is the weight coefficient;

[0049] Dynamically adjust weight coefficients using fuzzy control rules

[0050]

[0051] in, , , as well as , , is the initial value, Take 0.2, is the minimum value, Take 0.2, and normalize the heading angle evaluation function, the distance to the nearest obstacle, and the vehicle linear speed respectively.

[0052] The present invention further proposes a path planning system based on a fusion algorithm, wherein the path planning system based on a fusion algorithm is used to implement the above-mentioned path planning method based on a fusion algorithm, and the system comprises:

[0053] Map initialization module, used to initialize the grid map and determine the starting and ending points;

[0054] The global planning module is used to set the CPO algorithm parameters, establish the improved adaptive weight coefficient objective function, and initialize the population to cover the search space for global path planning using the improved CPO algorithm;

[0055] The local planning module is used to obtain vehicle information, take the next key point in the global path as the target point, and use the DWA algorithm to perform local path regularization based on the improved trajectory scoring function based on preset rules;

[0056] The update comparison module is used to update the vehicle position information and obtain the comparison result between the vehicle position information and the destination position information, and complete the path planning based on the comparison result.

[0057] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned path planning method based on the fusion algorithm is implemented.

[0058] The present invention also proposes a device, wherein the vehicle comprises a memory and a processor, wherein:

[0059] The memory is used to store computer programs;

[0060] When the processor is used to execute the computer program stored in the memory, the above-mentioned path planning method based on the fusion algorithm is implemented.

[0061] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0063] Figure 1 is a flow chart of a path planning method based on a fusion algorithm in a first embodiment of the present invention;

[0064] Figure 2 This is a flow chart of an improved CPO algorithm in the first embodiment of the present invention;

[0065] Figure 3 This is a flow chart of an improved DWA algorithm in the first embodiment of the present invention;

[0066] Figure 4 This is a diagram of an adaptive weight structure based on fuzzy control in the first embodiment of the present invention;

[0067] Figure 5 is a schematic structural diagram of a path planning system based on a fusion algorithm in a second embodiment of the present invention;

[0068] Figure 6 It is a structural diagram of a path planning method and device based on a fusion algorithm in the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0069] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0070] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0071] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0072] Embodiment 1

[0073] like Figure 1 The figure shows a flow chart of a path planning method based on a fusion algorithm in the present invention. The path planning method based on a fusion algorithm includes the following steps S01 to S04, wherein:

[0074] S01. Initialize the grid map and determine the starting point and the end point.

[0075] S02. Set CPO algorithm parameters, establish an improved adaptive weight coefficient objective function, and initialize the population to cover the search space for global path planning using the improved CPO algorithm.

[0076] like Figure 2 As shown, set the CPO algorithm parameters, including at least the number of proxy requests , maximum number of iterations , search space upper boundary and the lower boundary , number of path points, number of loops , convergence rate The trade-off percentage between the third and fourth defense mechanisms .

[0077] An improved adaptive weight coefficient objective function is established that takes into account the path length, obstacle avoidance penalty, and the distance from the path end point to the target. The improved adaptive weight coefficient objective function is:

[0078]

[0079] in, , , are weight coefficients, is the total length of the normalized path, To avoid obstacle penalties, is the distance from the normalized path to the end point.

[0080] The global path planning dynamically adjusts the weight coefficient according to the contribution rate of the objective function of the improved adaptive weight coefficient. The dynamic adjustment formula is as follows:

[0081]

[0082] in , , is the contribution rate, , , is the basic weight coefficient, To adjust the weight factor coefficient.

[0083] In this embodiment, the improved adaptive weight coefficient objective function is used to evaluate the quality of the planned path and drive the improved CPO algorithm to search for the direction. When the planned path is the shortest and collision-free, the improved adaptive weight coefficient objective function is maximized to obtain the optimal path. The obstacle avoidance penalty value is determined by looping through each point in the path to see if it is on an obstacle. If it is on an obstacle, =100; otherwise it is 0, and the weight coefficient is dynamically adjusted by improving the contribution rate of the adaptive weight coefficient objective function. , , The value is 1.

[0084] Initialize the population and cover the search space. The covering formula includes:

[0085]

[0086] in, represents the first Candidate solution, and are the upper and lower limits of the search space range, respectively. represents a random number of [0 1], ;

[0087] Based on the coverage, a first defense mechanism, a second defense mechanism, a third defense mechanism, and a fourth defense mechanism are established, and a corresponding defense mechanism is selected to search the search space, and a random number is generated at the initial stage of exploration. and ,when , then enter the global search phase and generate a random number and ,like , then the first defense mechanism is selected. , then choose the second defense mechanism; when , then enter the local exploration phase and generate random numbers ,like , choose the third defense mechanism, when , select the fourth defense mechanism.

[0088] The first defense mechanism is:

[0089]

[0090] in, represents the position of the i-th individual in the t-th iteration, represents the position of the i-th individual in the t+1 iteration, represents random numbers based on normal distribution, represents a random number of [0 1], represents the best individual position in the tth iteration, represents the position of the ith agent, is the position of a randomly selected individual.

[0091] Second defense mechanism:

[0092]

[0093] in, is a randomly generated binary vector in the interval [0,1], is the average position between the current agent and other randomly selected agents, is the position of another randomly selected agent, , The positions of the agents are randomly selected.

[0094] The third defense mechanism:

[0095]

[0096]

[0097]

[0098]

[0099] in, represents the diffusion factor, represents a random number in the interval [0,1], Indicates the direction of controlling the search. represents the search intensity, and Represent the number of iterations and the maximum number of iterations respectively, is a random value in the range [0,1], represents the objective function value of the i-th individual in the t-th iteration, N is the total number of individuals in the population, represents the sum of all individual objective function values, is a minimum value.

[0100] Fourth defense mechanism:

[0101]

[0102] in, represents the convergence speed, , and are all random values ​​in the interval [0, 1]. represents the attenuation factor, represents the average strength of the ith search agent, represents the quality of the i-th search agent, and They represent the search speed of the i-th search agent at the t-th and t+1-th time, respectively. represents the iteration step length, represents the fitness value of the k-th search agent at the t-th time, is an exponential function, represents the sum of the fitness values ​​of the k-th search agent in each population at the t-th time.

[0103] Initialize the population, cover the search space step, and then establish an adaptive perturbation mechanism to enhance population diversity. Search Agent Make a perturbation:

[0104]

[0105]

[0106] in, represents the generated disturbance, Indicates the number of path points, each component , , …, The value range is [-4, 4]. is the position of the i-th individual in the t-th iteration, represents the position of the i-th individual in the t+1 iteration.

[0107] After establishing the adaptive perturbation mechanism, an improved cyclic population reduction mechanism is established:

[0108]

[0109] in, is the current population size, represents the initial population size, represents the minimum population size, represents the number of iterations, represents the maximum number of iterations, Indicates the number of cycles, Represents the remainder operation;

[0110] Dynamic adjustment of minimum population size:

[0111] (- )

[0112] in, Indicates the increase, Represents the decay rate.

[0113] In this embodiment, the minimum population size is dynamically adjusted. A larger one is set in the early stage of exploration to promote the search agent to explore a wider area, and a smaller one is used in the local search stage to concentrate on the local optimal area.

[0114] The key points in the global path planning are extracted as the target points of the local path planning of the DAW algorithm. On the basis of the improved CPO planning of the optimal global path, the closest point to the obstacle, the turning point and the inflection point are selected as the key points according to a certain index interval as the target points in the DWA algorithm.

[0115] S03, obtaining vehicle information, taking the next key point in the global path as the target point, and using the DWA algorithm to perform local path regularization based on an improved trajectory scoring function according to preset rules.

[0116] like Figure 3 and Figure 4 As shown, the DWA algorithm is used for local path regularization, and the process includes the following sub-steps:

[0117] Obtain the current vehicle status information, based on the kinematic model and driving space constraints on the vehicle's driving status, and the vehicle's driving speed limit for:

[0118]

[0119] in, is the minimum speed of the vehicle, is the maximum speed of the vehicle, is the minimum yaw rate of the vehicle, is the maximum yaw rate of the vehicle.

[0120] Vehicle acceleration limits :

[0121]

[0122] in, is the current linear velocity, is the current angular velocity, and are the maximum acceleration limits, and = , and are the maximum angular acceleration allowed, and = .

[0123] Obstacle restrictions :

[0124] .

[0125] In the step of improving the trajectory scoring function based on the preset rules, the trajectory scoring function is:

[0126]

[0127] in, is the heading angle evaluation function, Indicates the distance to the nearest obstacle. represents the vehicle linear speed, , , is the weight coefficient;

[0128] Since the traditional DWA algorithm uses a fixed weight coefficient, when in different environments, the fixed weight coefficient is likely to cause problems such as poor obstacle avoidance effect, increased path length, and target point loss. Therefore, this application uses fuzzy control rules to dynamically adjust the weight coefficient, and normalizes the heading angle evaluation function, the distance to the nearest obstacle, and the vehicle linear speed.

[0129] Use fuzzy rules to dynamically adjust weight coefficients:

[0130]

[0131] in, , , as well as , , is the initial value, Take 0.2, Take 0.2.

[0132] When the vehicle is far away from the obstacle and the heading angle is large, the smaller , give priority to the principle of directionality. When the vehicle is close to an obstacle and the heading angle is small, the vehicle's own safety should be considered and a larger heading angle should be chosen. , when the importance of directionality and safety is close, Take the appropriate value.

[0133] In order to prevent the heading angle evaluation function, the distance to the nearest obstacle, and the vehicle linear speed score base from being too different, the heading angle evaluation function, the distance to the nearest obstacle, and the vehicle linear speed are normalized respectively:

[0134]

[0135] in, is a variable. In this embodiment, for .

[0136] S04: updating the vehicle position information, and obtaining a comparison result between the vehicle position information and the destination position information, and completing the path planning based on the comparison result.

[0137] Update the current position and determine whether the current position is the end point. If so, complete the path planning. If not, repeat step S03 until the vehicle position coincides with the end point.

[0138] In summary, according to a path planning method based on a fusion algorithm proposed in the present invention, the grid map is initialized, and the starting point and end point of the path planning are determined; the CPO algorithm parameters are set, and an improved adaptive weight coefficient objective function is established based on the path length, obstacle avoidance penalty, and the distance from the path end point to the target, and the search space is covered for global path planning; vehicle information is obtained, and a trajectory scoring function is obtained based on the vehicle information; the vehicle information is updated to determine whether the current position is the end point position, if not, the third step is repeated.

[0139] The present invention can avoid falling into local optimum in global path planning, prevent premature convergence and insufficient exploration of search space in global path planning, realize multi-objective optimization of global path planning, and provide optimal global information for the DWA algorithm by extracting key points in the global path as target points of the DWA algorithm, avoid falling into local optimum solution in local planning, and realize dynamic obstacle avoidance at the same time.

[0140] Embodiment 2

[0141] Another aspect of the present invention is to provide a path planning system based on a fusion algorithm. Figure 5 , which is a schematic diagram of the structure of a path planning system based on a fusion algorithm in a second embodiment of the present invention, wherein the path planning system based on a fusion algorithm includes:

[0142] The map initialization module 11 is used to initialize the grid map and determine the starting point and the end point;

[0143] The global planning module 12 is used to set the CPO algorithm parameters, establish the improved adaptive weight coefficient objective function, and initialize the population to cover the search space for global path planning using the improved CPO algorithm;

[0144] A local planning module 13 is used to obtain vehicle information, take the next key point in the global path as the target point, and use the DWA algorithm to perform local path regularization based on the improved trajectory scoring function of the preset rules;

[0145] The updating and comparing module 14 is used to update the vehicle position information and obtain the comparison result between the vehicle position information and the destination position information, and complete the path planning based on the comparison result.

[0146] Furthermore, in some optional embodiments, the global planning module 12 further includes:

[0147] Global planning unit, used to set CPO algorithm parameters, including at least the number of proxy requests , maximum number of iterations , search space upper boundary and the lower boundary , number of path points, number of loops , convergence rate The trade-off percentage between the third and fourth defense mechanisms ;

[0148] And establish an improved adaptive weight coefficient objective function that takes into account the path length, obstacle avoidance penalty and the distance from the path end point to the target. The improved adaptive weight coefficient objective function is:

[0149]

[0150] in, , , are weight coefficients, is the total length of the normalized path, To avoid obstacle penalties, is the distance from the regularized path to the end point;

[0151] The global path planning dynamically adjusts the weight coefficient according to the contribution rate of the objective function of the improved adaptive weight coefficient. The dynamic adjustment formula is as follows:

[0152]

[0153] in , , is the contribution rate, , , is the basic weight coefficient, To adjust the weight factor coefficient.

[0154] The initialization population covers the search space, and the covering formula includes:

[0155]

[0156] in, represents the first Candidate solution, and are the upper and lower limits of the search space range, respectively. represents a random number of [0 1], ;

[0157] Based on the coverage, a first defense mechanism, a second defense mechanism, a third defense mechanism, and a fourth defense mechanism are established, and a corresponding defense mechanism is selected to search the search space, and a random number is generated at the initial stage of exploration. and ,when , then enter the global search phase and generate a random number and ,like , then the first defense mechanism is selected. , then choose the second defense mechanism;

[0158] when , then enter the local exploration phase and generate random numbers ,like , choose the third defense mechanism, when , select the fourth defense mechanism.

[0159] The initialization population and the covering search space step include:

[0160] Establish an adaptive perturbation mechanism to enhance population diversity and Search Agent Make a perturbation:

[0161]

[0162]

[0163] in, represents the generated disturbance, Indicates the number of path points, each component , , …, The value range is [-4, 4]. is the position of the i-th individual in the t-th iteration, represents the position of the i-th individual in the t+1 iteration.

[0164] After establishing the adaptive perturbation mechanism, an improved cyclic population reduction mechanism is established:

[0165]

[0166] in, is the current population size, represents the initial population size, represents the minimum population size, represents the number of iterations, represents the maximum number of iterations, Indicates the number of cycles, Represents the remainder operation;

[0167] Dynamic adjustment of minimum population size:

[0168] (- )

[0169] in, Indicates the increase, Represents the decay rate.

[0170] Furthermore, in some optional embodiments, the local planning module 13 further includes:

[0171] The local planning unit is used to obtain the current vehicle status information, based on the kinematic model and the driving space constraints on the vehicle driving state, the vehicle speed limit for:

[0172]

[0173] in, is the minimum speed of the vehicle, is the maximum speed of the vehicle, is the minimum yaw rate of the vehicle, is the maximum yaw rate of the vehicle;

[0174] Vehicle acceleration limits :

[0175]

[0176] in, is the current linear velocity, is the current angular velocity, and are the maximum acceleration limits, and = , and are the maximum angular acceleration allowed, and = .

[0177] Obstacle restrictions :

[0178] .

[0179] In the step of improving the trajectory scoring function based on the preset rules, the trajectory scoring function is:

[0180]

[0181] in, is the heading angle evaluation function, Indicates the distance to the nearest obstacle. represents the vehicle linear speed, , , is the weight coefficient;

[0182] The weight coefficient is dynamically adjusted by using fuzzy control rules, and the heading angle evaluation function, the distance to the nearest obstacle, and the vehicle linear speed are normalized respectively.

[0183] In summary, according to a path planning system based on a fusion algorithm proposed in the present invention, the grid map is initialized, and the starting point and end point of the path planning are determined; the CPO algorithm parameters are set, and an improved adaptive weight coefficient objective function is established based on the path length, obstacle avoidance penalty, and the distance from the path end point to the target, and the search space is covered for global path planning; vehicle information is obtained, and a trajectory scoring function is obtained based on the vehicle information; the vehicle information is updated to determine whether the current position is the end point position, if not, the third step is repeated.

[0184] The present invention can avoid falling into local optimum in global path planning, prevent premature convergence and insufficient exploration of search space in global path planning, realize multi-objective optimization of global path planning, and provide optimal global information for the DWA algorithm by extracting key points in the global path as target points of the DWA algorithm, avoid falling into local optimum solution in local planning, and realize dynamic obstacle avoidance at the same time.

[0185] Embodiment 3

[0186] Another aspect of the present invention further provides a computer-readable storage medium on which one or more computer programs are stored, and when the program is executed by a processor, the above-mentioned path planning method based on the fusion algorithm is implemented.

[0187] Those skilled in the art will appreciate that the logic or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable storage medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable storage medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0188] More specific examples (a non-exhaustive list) of computer-readable storage media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0189] Embodiment 4

[0190] Another aspect of the present invention also provides a device, see Figure 6 , shown is a schematic diagram of the structure of the device in the fourth embodiment of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor, and when the processor 10 executes the computer program 30, the path planning method based on the fusion algorithm as described above is implemented.

[0191] Specifically, the device may be a computer, a vehicle testing device, etc. The processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip in some embodiments, and is used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0192] The memory 20 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 20 may be an internal storage unit of the device, such as a hard disk of the device. In other embodiments, the memory 20 may also be an external storage device of the device, such as a plug-in hard disk equipped on the device, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Further, the memory 20 may also include both an internal storage unit of the device and an external storage device. The memory 20 may be used not only to store application software and various types of data installed on the device, but also to temporarily store data that has been output or is to be output.

[0193] It should be pointed out that Figure 6The structure shown does not constitute a limitation on the device. In other embodiments, the device may include Figure 6 Fewer or more components may be shown, or certain components may be combined, or arranged differently.

[0194] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0195] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does 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 more embodiments or examples in a suitable manner.

[0196] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A path planning method based on a fusion algorithm, characterized in that: The path planning method based on the fusion algorithm includes: Initialize the grid map and determine the starting and ending points; Set the CPO algorithm parameters, including at least the number of proxy requests , maximum number of iterations , search space upper boundary and the lower boundary , number of path points, number of loops , convergence rate The trade-off percentage between the third and fourth defense mechanisms , and establish an improved adaptive weight coefficient objective function that takes into account the path length, obstacle avoidance penalty, and the distance from the path end point to the target. The improved adaptive weight coefficient objective function is: in, , , are weight coefficients, is the total length of the normalized path, To avoid obstacle penalties, In order to regulate the distance between the path and the end point, the global path planning dynamically adjusts the weight coefficient according to the contribution rate of the objective function of the improved adaptive weight coefficient. The dynamic adjustment formula is as follows: in , , is the contribution rate, , , is the basic weight coefficient, To adjust the weight factor coefficient and initialize the population, cover the search space for global path planning using the improved CPO algorithm; Obtain vehicle information, take the next key point in the global path as the target point, and use the DWA algorithm to perform local path regularization based on the improved trajectory scoring function based on preset rules; The vehicle position information is updated, and a comparison result between the vehicle position information and the destination position information is obtained, and the path planning is completed based on the comparison result.

2. The path planning method based on the fusion algorithm according to claim 1, characterized in that: The initialization population covers the search space, and the covering formula includes: in, represents the first Candidate solution, and are the upper and lower limits of the search space range, respectively. represents a random number of [0 1], ; Based on the coverage, a first defense mechanism, a second defense mechanism, a third defense mechanism, and a fourth defense mechanism are established, and a corresponding defense mechanism is selected to search the search space, and a random number is generated at the initial stage of exploration. and ,when , then enter the global search phase and generate a random number and ,like , then the first defense mechanism is selected. , then choose the second defense mechanism; when , then enter the local exploration phase and generate random numbers ,like , choose the third defense mechanism, when , select the fourth defense mechanism.

3. The path planning method based on fusion algorithm according to claim 1, characterized in that: The initialization population and the covering search space step include: Establish an adaptive perturbation mechanism to enhance population diversity and Search Agent Make a perturbation: in, represents the generated disturbance, Indicates the number of path points, each component , , …, The value range is [-4, 4]. is the position of the i-th individual in the t-th iteration, represents the position of the i-th individual in the t+1 iteration.

4. The path planning method based on fusion algorithm according to claim 3 is characterized in that: After establishing the adaptive perturbation mechanism, an improved cyclic population reduction mechanism is established: in, is the current population size, represents the initial population size, represents the minimum population size, represents the number of iterations, represents the maximum number of iterations, Indicates the number of cycles, Represents the remainder operation; Dynamic adjustment of minimum population size: （- ） in, Indicates the increase, represents the attenuation rate, Represents the minimum population size.

5. The path planning method based on fusion algorithm according to claim 1, characterized in that: The step of obtaining vehicle information, taking the next key point in the global path as the target point, and using the DWA algorithm to perform local path regularization based on an improved trajectory scoring function according to a preset rule specifically includes: Obtain the current vehicle status information, based on the kinematic model and driving space constraints on the vehicle's driving status, and the vehicle's driving speed limit for: in, is the minimum speed of the vehicle, is the maximum speed of the vehicle, is the minimum yaw rate of the vehicle, is the maximum yaw rate of the vehicle; Vehicle acceleration limits : in, is the current linear velocity, is the current angular velocity, and are the maximum acceleration limits, and = , and are the maximum angular acceleration allowed, and = ; Obstacle restrictions : 。 6. The path planning method based on fusion algorithm according to claim 5, characterized in that: In the step of improving the trajectory scoring function based on the preset rules, the trajectory scoring function is: in, is the heading angle evaluation function, Indicates the distance to the nearest obstacle. represents the vehicle linear speed, , , is the weight coefficient; Dynamically adjust weight coefficients using fuzzy control rules in, , , as well as , , is the initial value, Take 0.2, is the minimum value, Take 0.2, and normalize the heading angle evaluation function, the distance to the nearest obstacle, and the vehicle linear speed respectively.

7. A path planning system based on a fusion algorithm, wherein the path planning system based on a fusion algorithm is used to implement the path planning method based on a fusion algorithm according to any one of claims 1 to 6, and the system comprises: Map initialization module, used to initialize the grid map and determine the starting and ending points; The global planning module is used to set the CPO algorithm parameters, including at least the number of search agents. , maximum number of iterations , search space upper boundary and the lower boundary , number of path points, number of loops , convergence rate The trade-off percentage between the third and fourth defense mechanisms , and establish an improved adaptive weight coefficient objective function that takes into account the path length, obstacle avoidance penalty, and the distance from the path end point to the target. The improved adaptive weight coefficient objective function is: in, , , are weight coefficients, is the total length of the normalized path, To avoid obstacle penalties, In order to regulate the distance between the path and the end point, the global path planning dynamically adjusts the weight coefficient according to the contribution rate of the objective function of the improved adaptive weight coefficient. The dynamic adjustment formula is as follows: in , , is the contribution rate, , , is the basic weight coefficient, To adjust the weight factor coefficient and initialize the population, cover the search space for global path planning using the improved CPO algorithm; The local planning module is used to obtain vehicle information, take the next key point in the global path as the target point, and use the DWA algorithm to perform local path regularization based on the improved trajectory scoring function based on preset rules; The update comparison module is used to update the vehicle position information and obtain the comparison result between the vehicle position information and the destination position information, and complete the path planning based on the comparison result.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the path planning method based on the fusion algorithm as described in any one of claims 1 to 6 is implemented.

9. A device, characterized in that: The vehicle comprises a memory and a processor, wherein: The memory is used to store computer programs; When the processor is used to execute the computer program stored in the memory, it implements the path planning method based on the fusion algorithm described in any one of claims 1-6.

Images