Path Planning Method, Apparatus, Device, and Storage Medium

Abstract

The present application relates to the field of driverless technologies, and provides a path planning method, apparatus, device, and storage medium. The method includes: randomly generating a plurality of ancestor individuals in the first round of iteration, any one of the individuals representing a driving path of a plurality of stations in a tandem park, and the starting point and the ending point of the driving path being the planning starting point and the planning ending point in the path planning task respectively; repeatedly executing the following iterative operations: introducing a population energy index reflecting the current search progress of the algorithm, adopting different dynamic competition mechanisms for a plurality of candidate individuals in this iteration to ensure the balance between local development and global search of the algorithm, and using the candidate individuals retained after screening and the new candidate individuals generated based on at least some of the retained candidate individuals as the candidate individuals for the next iteration; until the maximum number of iterations is satisfied, taking the driving path decoded from the optimal candidate individual with the highest fitness in the last iteration as the optimal path between the planning starting point and the planning ending point.

Description

Background Art

[0002] With the continuous development of driverless technology, driverless shuttle buses based on this technology also have broad application prospects in the fields of logistics transportation, disaster relief, environmental monitoring, etc.

[0003] Among them, path planning is an important component of the application of driverless shuttle buses. As a commonly used path planning algorithm, the Harris Hawk Optimization Algorithm plans the driving route of the driverless shuttle bus according to the information of the park.

[0004] Due to the lack of global search ability in the later stage of the algorithm, it is easy to fall into local optimal solutions, resulting in obvious limitations in the driving routes planned for driverless shuttle buses. The driving routes may not cover all the stations in the park. Even if the planned routes can pass through all the stations, they may not be the most time-efficient choice. Summary of the Invention

[0005] The embodiments of the present application provide a path planning method, device, equipment and storage medium to solve the problem of path planning limitations caused by the lack of global search ability in the later stage of the algorithm.

[0006] In a first aspect, the embodiments of the present application provide a path planning method, including:

[0007] In response to a path planning task, a plurality of ancestor individuals for the first round of iteration are randomly generated, where any individual is used to represent a driving route connecting multiple stations in the park, and the starting point and the ending point of the driving route are the planned starting point and the planned ending point in the path planning task respectively;

[0008] The following iterative operation is repeatedly executed: based on the population energy index of the current iteration, a plurality of candidate individuals of the current iteration are screened, and the candidate individuals retained after screening and the new candidate individuals generated based on at least part of the retained candidate individuals are used as the candidate individuals for the next iteration;

[0009] Until the maximum number of iterations is reached, the optimal candidate individual with the highest fitness in the last iteration is obtained, and the driving route decoded from the optimal candidate individual is used as the optimal path between the planned starting point and the planned ending point.

[0010] Optionally, based on the population energy index of the current iteration, screening a plurality of candidate individuals of the current iteration, and using the candidate individuals retained after screening and the new candidate individuals generated based on at least part of the retained candidate individuals as the candidate individuals for the next iteration, includes:

[0011] When the population energy index in this iteration is within the first value range, eliminate the candidate individuals whose fitness ranks lower than the first preset rank in this iteration. Use the other individuals retained in this iteration and the new candidate individuals generated based on the candidate individuals whose fitness ranks are not lower than the second preset rank in this iteration as the candidate individuals for the next iteration;

[0012] When the population energy index in this iteration is within the second value range, eliminate the candidate individuals whose fitness ranks lower than the third preset rank in this iteration. Use the other individuals retained in this iteration and the new candidate individuals generated based on the candidate individual with the highest fitness in this iteration as the candidate individuals for the next iteration;

[0013] When the population energy index in this iteration is within the third value range, eliminate all other individuals except the candidate individual with the highest fitness in this iteration. Use the candidate individual with the highest fitness in this iteration and the new candidate individuals generated based on the candidate individual with the highest fitness in this iteration as the candidate individuals for the next iteration.

[0014] Optionally, the new candidate individuals are generated by performing the following operations:

[0015] Iteratively update a candidate individual based on the fitness of one candidate individual in this iteration, the fitness of all candidate individuals, and the update radius of this iteration to obtain a candidate individual for the next iteration.

[0016] Optionally, the fitness of any individual is obtained by performing the following operations:

[0017] Obtain the actual site distances between the sites corresponding to the adjacent vector values in the any individual from the abstract map of the park;

[0018] Take the sum of the site distances between the sites corresponding to all adjacent vector values as the fitness of the any individual.

[0019] Optionally, the population energy index of this iteration is obtained by performing the following operations:

[0020] Based on the number of individuals in this iteration and the current individual energy of each candidate individual in this iteration, obtain the population energy index of this iteration.

[0021] Optionally, the current individual energy of each candidate individual in this iteration is obtained by performing the following operations:

[0022] Based on the initial individual energy of the ancestor individuals associated with each candidate individual in this iteration, the number of this iteration, and the total number of iterations, obtain the respective current individual energy of each candidate individual in this iteration.

[0023] Optionally, the optimal path is obtained by decoding the optimal candidate individual through the following operations:

[0024] Replace each vector value in the optimal candidate individual with the associated site label value respectively, and construct the path order between the site label values based on the arrangement order of the vector values, so as to form the optimal path between the planned starting point and the planned ending point.

[0025] In a second aspect, an embodiment of the present application further provides a path planning device, including:

[0026] An initialization unit, configured to randomly generate a plurality of ancestor individuals for the first round of iteration in response to a path planning task, where any individual is used to represent a driving path of a plurality of sites in a series-connected park, and the starting point and the ending point of the driving path are the planned starting point and the planned ending point in the path planning task respectively;

[0027] An iterative update unit, configured to repeatedly perform the following iterative operations: screen the plurality of candidate individuals for the current iteration based on the population energy index of the current iteration, and use the candidate individuals retained after screening and the new candidate individuals generated based on at least some of the retained candidate individuals as the candidate individuals for the next iteration;

[0028] A decoding processing unit, configured to obtain the optimal candidate individual with the highest fitness in the last iteration until the maximum number of iterations is reached, and use the driving path obtained by decoding the optimal candidate individual as the optimal path between the planned starting point and the planned ending point.

[0029] Optionally, the iterative update unit is configured to:

[0030] When the population energy index of the current iteration is within the first value range, eliminate the candidate individuals whose fitness ranking in the current iteration is lower than the first preset ranking, and use the other individuals retained in the current iteration and the new candidate individuals generated based on the candidate individuals whose fitness ranking in the current iteration is not lower than the second preset ranking as the candidate individuals for the next iteration;

[0031] When the population energy index of the current iteration is within the second value range, eliminate the candidate individuals whose fitness ranking in the current iteration is lower than the third preset ranking, and use the other individuals retained in the current iteration and the new candidate individuals generated based on the candidate individual with the highest fitness in the current iteration as the candidate individuals for the next iteration;

[0032] When the population energy index of the current iteration is within the third value range, eliminate all the individuals in the current iteration except the candidate individual with the highest fitness, and use the candidate individual with the highest fitness in the current iteration and the new candidate individuals generated based on the candidate individual with the highest fitness in the current iteration as the candidate individuals for the next iteration.

[0033] Optionally, the iterative update unit generates a new candidate individual by performing the following operations:

[0034] Based on the fitness of a candidate individual in this iteration, the fitness of all candidate individuals, and the update radius of this iteration, perform iterative update on a candidate individual to obtain a candidate individual for the next iteration.

[0035] Optionally, the iterative update unit obtains the fitness of any individual by performing the following operations:

[0036] From the abstract map of the park, obtain the actual site distances between the sites corresponding to the adjacent vector values in any individual;

[0037] Take the sum of the site distances between the sites corresponding to all adjacent vector values as the fitness of any individual.

[0038] Optionally, the iterative update unit obtains the population energy index of this iteration by performing the following operations:

[0039] Based on the number of individuals in this iteration and the current individual energy of each candidate individual in this iteration, obtain the population energy index of this iteration.

[0040] Optionally, the iterative update unit obtains the current individual energy of each candidate individual in this iteration by performing the following operations:

[0041] Based on the initial individual energy of the ancestor individuals associated with each candidate individual in this iteration, the number of this iteration and the total number of iterations, respectively obtain the current individual energy of each candidate individual in this iteration.

[0042] Optionally, the decoding processing unit decodes the optimal candidate individual by performing the following operations to obtain the optimal path:

[0043] Replace each vector value in the optimal candidate individual with the associated site label value respectively, and construct the path order between the site label values based on the arrangement order of the vector values to form the optimal path between the planned starting point and the planned ending point.

[0044] In a third aspect, an embodiment of the present application further provides a computer device, including a processor and a memory, wherein the memory stores program code, and when the program code is executed by the processor, the processor is caused to execute the steps of any of the above path planning methods.

[0045] Fourthly, an embodiment of the present application further provides a computer-readable storage medium, which includes program codes. When the program product runs on a computer device, the program codes are used to cause the computer device to execute the steps of any of the above path planning methods.

[0046] The beneficial effects of the present application are as follows:

[0047] An embodiment of the present application provides a path planning method, device, equipment and storage medium. The method includes: in response to a path planning task, randomly generating a plurality of ancestor individuals in the first round of iteration, where any individual is used to represent a driving path of multiple stations in a tandem park, and the starting point and the ending point of the driving path are respectively the planned starting point and the planned ending point in the path planning task; repeatedly executing the following iterative operations: based on the population energy index of the current iteration, screening the plurality of candidate individuals in the current iteration, and using the candidate individuals retained after screening and the new candidate individuals generated based on at least some of the retained candidate individuals as the candidate individuals for the next iteration; until the maximum number of iterations is reached, obtaining the optimal candidate individual with the highest fitness in the last iteration, and using the driving path decoded from the optimal candidate individual as the optimal path between the planned starting point and the planned ending point.

[0048] Aiming at the path planning limitation problem caused by the insufficient global search ability of the Harris hawk optimization algorithm in the later stage, the present application introduces a population energy index that reflects the current search progress of the algorithm, and adopts different dynamic competition mechanisms for different stages of the algorithm to ensure the balance between local development and global search of the algorithm, and then more accurately and effectively execute different mechanisms, improve the convergence speed and accuracy of the algorithm, and improve the path planning limitation problem caused by falling into local optimal solutions.

[0049] Other features and advantages of the present application will be described in the subsequent description, and part of them will become obvious from the description, or will be understood by implementing the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures specifically pointed out in the written description, claims and drawings. Description of the Drawings

[0050] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0051] Figure 1 It is a logical schematic diagram of the existing Harris hawk optimization algorithm;

[0052] Figure 2A It is a schematic flowchart of planning a driving route for a driverless shuttle bus in a park provided by an embodiment of the present application;

[0053] Figure 2B It is a logical schematic diagram for planning the driving route of driverless shuttles in the park provided by the embodiments of the present application;

[0054] Figure 3 It is a structural schematic diagram of a path planning device provided by the embodiments of the present application;

[0055] Figure 4 It is a schematic diagram of the composition structure of a computer device provided in the embodiments of the present application;

[0056] Figure 5 It is a structural schematic diagram of a computing device in the embodiments of the present application. Detailed implementation manners

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the technical solutions of the present application. Based on the embodiments described in this application document, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope protected by the technical solutions of the present application.

[0058] The design concept of the embodiments of the present application will be briefly introduced below:

[0059] With the continuous development of driverless technology, driverless shuttles based on this technology also have broad application prospects in fields such as logistics transportation, disaster rescue, and environmental monitoring.

[0060] Among them, path planning is an important component part of the application of driverless shuttles. As a commonly used path planning algorithm, the Harris hawk optimization algorithm plans the driving route of driverless shuttles according to the information of the park.

[0061] As Figure 1 shown, the Harris hawk optimization algorithm includes an exploration stage and a development stage, and different position update strategies are executed in each stage. Due to the lack of global search ability in the later stage of the algorithm, it is easy to fall into local optimal solutions, resulting in obvious limitations in the driving routes planned for driverless shuttles. The driving routes may not cover all stations in the park. Even if the planned routes can pass through all stations, they may not be the most time-efficient choice.

[0062] In view of this, the embodiments of the present application provide a path planning method, apparatus, device, and storage medium. The method includes: in response to a path planning task, randomly generating a plurality of ancestor individuals in the first round of iteration, where any individual is used to represent a driving path of a plurality of stations in a series-connected park, and the starting point and the ending point of the driving path are respectively the planned starting point and the planned ending point in the path planning task; repeatedly performing the following iterative operations: based on the population energy index of the current iteration, screening the plurality of candidate individuals in the current iteration, and using the candidate individuals retained after screening and the new candidate individuals generated based on at least some of the retained candidate individuals as the candidate individuals for the next iteration; until the maximum number of iterations is reached, obtaining the optimal candidate individual with the highest fitness in the last iteration, and using the driving path decoded from the optimal candidate individual as the optimal path between the planned starting point and the planned ending point.

[0063] In view of the problem of path planning limitations caused by the insufficient global search ability of the Harris hawk optimization algorithm in the later stage, the present application introduces a population energy index that reflects the current search progress of the algorithm, and adopts different dynamic competition mechanisms for different stages of the algorithm to ensure the balance between local development and global search of the algorithm, thereby more accurately and effectively executing different mechanisms, improving the convergence speed and accuracy of the algorithm, and improving the problem of path planning limitations caused by falling into local optimal solutions.

[0064] The following describes the preferred embodiments of the present application with reference to the accompanying drawings of the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. And without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0065] Combined with Figures 2A - 2B the schematic diagram shown, specifically introduce the planned driving route of the driverless shuttle bus traveling in the park, so that the driverless shuttle bus passes through all stations in the park in the shortest time.

[0066] S201: In response to a path planning task, randomly generate a plurality of ancestor individuals in the first round of iteration, where any individual is used to represent a driving path of a plurality of stations in a series-connected park, and the starting point and the ending point of the driving path are respectively the planned starting point and the planned ending point in the path planning task.

[0067] Using Formula 1, randomly generate a plurality of ancestor individuals in the first round of iteration. Each individual contains a plurality of vector values, which are used to represent a driving path of a plurality of stations in a series-connected park, and different individuals contain the same planned starting point and planned ending point. Among them, is a random function, is the initial individual energy of the ancestor individual corresponding to the i-th individual. The ancestor individual of any individual is the initialized individual that directly or indirectly generates the said individual, or when the said individual itself is an initialized individual, its ancestor individual is itself.

[0068] Formula 1;

[0069] S202: Repeatedly perform the following iterative operation: Based on the population energy index of the current iteration, screen the multiple candidate individuals of the current iteration, and use the candidate individuals retained after screening and the new candidate individuals generated based on at least some of the retained candidate individuals as the candidate individuals for the next iteration.

[0070] (1) When the population energy index of the current iteration is within the first value range, eliminate the candidate individuals whose fitness rankings in the current iteration are lower than the first preset ranking, and use the other individuals retained in the current iteration and the new candidate individuals generated based on the candidate individuals whose fitness rankings in the current iteration are not lower than the second preset ranking as the candidate individuals for the next iteration.

[0071] When the population energy index of the current iteration it indicates that the Harris hawk optimization algorithm is still in the early search stage at this time. Eliminate the candidate individuals whose fitness rankings in the current iteration are lower than the first preset ranking, retain the remaining individuals, select the candidate individuals whose fitness rankings are not lower than the second preset ranking from the remaining retained individuals to generate new candidate individuals, and use the other individuals retained in the current iteration and the newly generated candidate individuals in the current iteration as the candidate individuals for the next iteration.

[0072] (2) When the population energy index of the current iteration is within the second value range, eliminate the candidate individuals whose fitness rankings in the current iteration are lower than the third preset ranking, and use the other individuals retained in the current iteration and the new candidate individuals generated based on the candidate individual with the highest fitness in the current iteration as the candidate individuals for the next iteration.

[0073] When the population energy index of the current iteration it indicates that the Harris hawk optimization algorithm has just entered the exploitation stage. To achieve a balance between global exploration and local exploitation, eliminate the candidate individuals whose fitness rankings in the current iteration are lower than the third preset ranking, retain the remaining individuals, select the candidate individual with the highest fitness from the remaining retained individuals to generate new candidate individuals, and use the other individuals retained in the current iteration and the newly generated candidate individuals in the current iteration as the candidate individuals for the next iteration.

[0074] (3) When the population energy index in this iteration is within the third value range, all individuals in this iteration except the candidate individual with the highest fitness are eliminated. The candidate individual with the highest fitness in this iteration and the new candidate individuals generated based on the candidate individual with the highest fitness in this iteration are used as candidate individuals for the next iteration.

[0075] When the population energy index in this iteration indicates that the Harris hawk optimization algorithm has entered the final stage of iteration at this time. To improve the convergence accuracy and convergence speed in the later stage of the algorithm, a more intense competition mechanism will be adopted at this stage. All individuals in this iteration except the candidate individual with the highest fitness are eliminated. Based on the candidate individual with the highest fitness, new candidate individuals are generated, and the individuals retained in this iteration and the newly generated candidate individuals in this iteration are used as candidate individuals for the next iteration.

[0076] As shown in Formula 2, based on the initial individual energy of the ancestor individuals associated with each candidate individual in this iteration , the iteration number t of this iteration, and the total number of iterations T, the current individual energy of each candidate individual in this iteration is obtained respectively .

[0077] Formula 2;

[0078] As shown in Formula 3, based on the number of individuals N in this iteration and the current individual energy of each candidate individual in this iteration , the population energy index of this iteration is obtained .

[0079] Formula 3;

[0080] As shown in Formula 4, by performing the following operations, new candidate individuals for the next iteration are generated : Based on the fitness of a candidate individual in this iteration , the fitness of all candidate individuals, and the update radius of this iteration , a candidate individual is iteratively updated to obtain a candidate individual for the next iteration. Among them, is a random constant, is the fitness of the optimal individual calculated so far up to this iteration (i.e., the distance of the shortest path), is the fitness of the worst individual calculated so far up to this iteration (i.e., the distance of the longest path).

[0081] Formula 4;

[0082] As shown in Formula 5, the fitness of any individual is obtained by performing the following operations : From the abstract map of the park, obtain the actual site distance between the sites corresponding to each adjacent vector value in any individual , and then take the sum of the site distances between the sites corresponding to all adjacent vector values as the fitness of any individual

[0083] Formula 5;

[0084] Formula 6 is the calculation formula for the update radius of this iteration, K, is a constant, t is the number of this iteration, and T is the total number of iterations

[0085] Formula 6;

[0086] The macroscopic map of the park is constructed based on an overall overview of a large geographical area. It usually ignores the specific obstacles between sites, such as buildings, terrain changes, or other physical obstacles. Although this simplification helps to provide a clear overall view, it may cause problems in practical applications

[0087] For example, the driving route planned based on the macroscopic map will also ignore the existence of these obstacles, resulting in it being difficult for the driverless shuttle bus to reach the designated site according to the pre-planned route during actual driving. Due to these unconsidered obstacles, the travel time and complexity are increased, affecting the overall transportation efficiency and service quality

[0088] Therefore, in the embodiments of the present application, according to the terrain type of the road passing between sites, terrain weighting is performed on the initial site distance between sites to obtain the actual distance between sites, and the actual site distance between each site and other sites in the park is marked on the abstract map

[0089] For example, convert the shortest actual distance between Site 1 and Site 2 into Euclidean distance, and the initial site distance between the two points is 1250m. There are three paths between the two points. Path 1 is a sloping road. Therefore, the actual site distance of Path 1 is 1250 (1 + 0.2)=1500m. Path 2 is a straight and flat road. Therefore, the actual site distance of Path 2 is 1250m. Path 3 is a winding road. Therefore, the actual site distance of Path 3 is 1250 (1 + 0.1)=1375m. Select the shortest Path 2 as the legal path. Therefore, the actual site distance between the two ends is 1375m

[0090] Although the abstract map does not conform to the actual terrain in terms of appearance, each station in the map corresponds one-to-one with the stations in the actual scenario, and the distances between the stations are the same. Then, using the decimal numbers from 1 to M, integer real number encoding is performed on each station in the abstract map. Each integer represents the index of a station. By applying the path planning method provided in this application, the obtained path is the optimal path in the current scenario.

[0091] S203: Until the maximum number of iterations is satisfied, obtain the optimal candidate individual with the highest fitness in the last iteration, and use the driving path obtained by decoding the optimal candidate individual as the optimal path between the planning start point and the planning end point.

[0092] Since the solutions in the continuous space generated by the Harris hawk optimization algorithm may not be applicable to the discrete behavior of the Traveling Salesman Problem (TSP), the embodiments of this application adopt a random key encoding scheme. Each vector value composed of uniformly distributed random real numbers in the optimal candidate individual is respectively replaced with the associated station label value, and the path order between the station label values is constructed based on the arrangement order of each vector value to form the optimal path between the planning start point and the planning end point. Among them, the first-dimensional vector value of the optimal candidate individual is used to associate with the station label value of the planning start point, and the last-dimensional vector value is used to associate with the station label value of the planning end point. For example, the vector [0.5, 0.1, 3.4] composed of uniformly distributed random real numbers is converted into an integer sequence [2, 1, 3], and each integer represents the index of a station.

[0093] The iteration stop condition of this application is that when the current number of iterations meets the maximum number of iterations, the loop step is stopped, and the driving path formed by the planning in the last iteration is used as the optimal path of the unmanned shuttle vehicle, ensuring that the vehicle passes through all stations in the park in the shortest time, and improving the situation that the planned driving route may not cover all stations in the park due to falling into a local optimal solution, and even if the planned route can pass through all stations, it may not be the most time-efficient choice.

[0094] Based on the same inventive concept as the above method embodiments, the embodiments of this application also provide a path planning device. As Figure 3 shown, the path planning device 300 may include:

[0095] An initialization unit 301, configured to randomly generate a plurality of ancestor individuals in the first round of iteration in response to a path planning task, where any individual is used to represent a driving path connecting multiple stations in the park, and the start point and the end point of the driving path are respectively the planning start point and the planning end point in the path planning task;

[0096] The iterative update unit 302 is configured to repeatedly perform the following iterative operations: based on the population energy metric of the current iteration, screen the multiple candidate individuals of the current iteration, and use the candidate individuals retained after screening and the new candidate individuals generated based on at least some of the retained candidate individuals as the candidate individuals for the next iteration;

[0097] The decoding processing unit 303 is configured to, until the maximum number of iterations is reached, obtain the optimal candidate individual with the highest fitness in the last iteration, and use the driving path obtained by decoding the optimal candidate individual as the optimal path between the planned starting point and the planned ending point.

[0098] Optionally, the iterative update unit 302 is configured to:

[0099] When the population energy metric of the current iteration is within the first value range, eliminate the candidate individuals whose fitness rankings in the current iteration are lower than the first preset ranking, and use the other individuals retained in the current iteration and the new candidate individuals generated based on the candidate individuals whose fitness rankings in the current iteration are not lower than the second preset ranking as the candidate individuals for the next iteration;

[0100] When the population energy metric of the current iteration is within the second value range, eliminate the candidate individuals whose fitness rankings in the current iteration are lower than the third preset ranking, and use the other individuals retained in the current iteration and the new candidate individuals generated based on the candidate individual with the highest fitness in the current iteration as the candidate individuals for the next iteration;

[0101] When the population energy metric of the current iteration is within the third value range, eliminate all individuals in the current iteration except the candidate individual with the highest fitness, and use the candidate individual with the highest fitness in the current iteration and the new candidate individuals generated based on the candidate individual with the highest fitness in the current iteration as the candidate individuals for the next iteration.

[0102] Optionally, the iterative update unit 302 generates new candidate individuals by performing the following operations:

[0103] Based on the fitness of one candidate individual in the current iteration, the fitness of all candidate individuals, and the update radius of the current iteration, perform iterative update on one candidate individual to obtain one candidate individual for the next iteration.

[0104] Optionally, the iterative update unit 302 obtains the fitness of any individual by performing the following operations:

[0105] From the abstract map of the park, obtain the actual site distances between the sites corresponding to the adjacent vector values in any individual;

[0106] The sum of the site distances between the sites corresponding to all adjacent vector values is used as the fitness of any one of the individuals.

[0107] Optionally, the iterative update unit 302 obtains the population energy index of this iteration by performing the following operations:

[0108] Based on the number of individuals in this iteration and the current individual energies of each candidate individual in this iteration, the population energy index of this iteration is obtained.

[0109] Optionally, the iterative update unit 302 obtains the current individual energy of each candidate individual in this iteration by performing the following operations:

[0110] Based on the initial individual energies of the ancestor individuals associated with each candidate individual in this iteration, the number of this iteration and the total number of iterations, the current individual energies of each candidate individual in this iteration are respectively obtained.

[0111] Optionally, the decoding processing unit 303 decodes the optimal candidate individual by performing the following operations to obtain the optimal path:

[0112] Each vector value in the optimal candidate individual is respectively replaced with the associated site label value, and based on the arrangement order of the vector values, the path order between the site label values is constructed to form the optimal path between the planned starting point and the planned ending point.

[0113] For the convenience of description, the above parts are divided into each module (or unit) according to functions and described separately. Of course, when implementing this application, the functions of each module (or unit) can be implemented in the same or multiple software or hardware.

[0114] After introducing the path planning method and device of the exemplary embodiment of the present application, next, a computer device according to another exemplary embodiment of the present application is introduced.

[0115] Those skilled in the art of the relevant technical field can understand that various aspects of the present application can be implemented as a system, a method or a program product. Therefore, various aspects of the present application can be specifically implemented in the following forms, that is: a complete hardware implementation manner, a complete software implementation manner (including firmware, microcode, etc.), or an implementation manner combining hardware and software aspects, which can be collectively referred to as "circuit", "module" or "system" here.

[0116] Based on the same inventive concept as the above method embodiment, an embodiment of the present application also provides a computer device. Refer to Figure 4As shown, the computer device 400 may at least include a processor 401 and a memory 402. Among them, the memory 402 stores program code, which, when executed by the processor 401, causes the processor 401 to execute the steps of any of the above path planning methods.

[0117] In some possible implementation manners, the computing device according to the present application may at least include at least one processor and at least one memory. Among them, the memory stores program code, which, when executed by the processor, causes the processor to execute the steps in the path planning methods according to various exemplary implementation manners of the present application described above in this specification. For example, the processor may execute steps such as Figure 2A shown in.

[0118] Next, refer to Figure 5 to describe the computing device 500 according to this implementation manner of the present application. Figure 5 The computing device 500 is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0119] As Figure 5 shown, the computing device 500 is presented in the form of a general-purpose computing device. The components of the computing device 500 may include but are not limited to: the above at least one processing unit 501, the above at least one storage unit 502, and a bus 503 connecting different system components (including the storage unit 502 and the processing unit 501).

[0120] The bus 503 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a processor, or a local bus using any bus structure in a variety of bus structures.

[0121] The storage unit 502 may include a readable medium in the form of volatile memory, such as a random access memory (RAM) 5021 and / or a cache storage unit 5022, and may further include a read-only memory (ROM) 5023.

[0122] The storage unit 502 may further include a program / utility 5025 having a set (at least one) of program modules 5024. Such program modules 5024 include but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0123] The computing device 500 may also communicate with one or more external devices 504 (such as a keyboard, a pointing device, etc.), and may also communicate with one or more devices that enable a user to interact with the computing device 500, and / or communicate with any device that enables the computing device 500 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be carried out through the input / output (I / O) interface 505. Moreover, the computing device 500 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 506. As shown in the figure, the network adapter 506 communicates with other modules for the computing device 500 through the bus 503. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the computing device 500, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0124] Based on the same inventive concept as the above method embodiments, various aspects of the path planning method provided in this application can also be implemented in the form of a program product, which includes program code. When the program product runs on a computer device, the program code is used to cause the computer device to execute the steps in the path planning method according to various exemplary embodiments described above in this specification. For example, the computer device can execute the steps as shown in Figure 2A .

[0125] The program product may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0126] Although the preferred embodiments of this application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of this application.

[0127] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to cover these changes and modifications.

Claims

1. A path planning method, characterized in that, Including: In response to a path planning task, a plurality of ancestor individuals for the first round of iteration are randomly generated, wherein any one individual is used to represent a driving path of a plurality of stations in a tandem park, and the starting point and the ending point of the driving path are respectively the planned starting point and the planned ending point in the path planning task; The following iterative operations are repeatedly executed: Based on the population energy index of the current iteration, a plurality of candidate individuals in the current iteration are screened, and the candidate individuals retained after screening and the new candidate individuals generated based on at least some of the retained candidate individuals are used as the candidate individuals for the next iteration, wherein the new candidate individuals are obtained by iteratively updating a candidate individual based on the fitness of a candidate individual in the current iteration, the fitness of all candidate individuals, and the update radius of the current iteration; The population energy index of the current iteration is based on the number of individuals in the current iteration and the current individual energy of each candidate individual in the current iteration, and the current individual energy of a candidate individual in the current iteration is related to the initial individual energy of the ancestor individual associated with the candidate individual; The fitness of any one individual is obtained by performing the following operations: From the abstract map of the park, obtain the actual station distances between the stations corresponding to the adjacent vector values in the any one individual, and use the sum of the station distances between the stations corresponding to all adjacent vector values as the fitness of the any one individual; Until the maximum number of iterations is reached, obtain the optimal candidate individual with the highest fitness in the last iteration, and decode to obtain the optimal path by performing the following operations on the optimal candidate individual: Replace each vector value in the optimal candidate individual with the associated station label value, and construct the path order between the station label values based on the arrangement order of the vector values to form the optimal path between the planned starting point and the planned ending point.

2. The method according to claim 1, wherein Based on the population energy index of the current iteration, screening a plurality of candidate individuals in the current iteration, and using the candidate individuals retained after screening and the new candidate individuals generated based on at least some of the retained candidate individuals as the candidate individuals for the next iteration, including: When the population energy index of the current iteration is within the first value range, eliminate the candidate individuals whose fitness rankings in the current iteration are lower than the first preset ranking, and use the other individuals retained in the current iteration and the new candidate individuals generated based on the candidate individuals whose fitness rankings in the current iteration are not lower than the second preset ranking as the candidate individuals for the next iteration; When the population energy index of the current iteration is within the second value range, eliminate the candidate individuals whose fitness rankings in the current iteration are lower than the third preset ranking, and use the other individuals retained in the current iteration and the new candidate individuals generated based on the candidate individual with the highest fitness in the current iteration as the candidate individuals for the next iteration; When the population energy index of the current iteration is within the third value range, eliminate the other individuals in the current iteration except the candidate individual with the highest fitness, and use the candidate individual with the highest fitness in the current iteration and the new candidate individuals generated based on the candidate individual with the highest fitness in the current iteration as the candidate individuals for the next iteration; Among them, the lower limit value of the first value range is greater than the upper limit value of the second value range, and the lower limit value of the second value range is greater than the upper limit value of the third value range.

3. The method according to claim 1, wherein The current individual energy of each candidate individual in this iteration is obtained by performing the following operations: Based on the initial individual energy of the ancestor individuals associated with each candidate individual in this iteration, the number of this iteration, and the total number of iterations, the current individual energy of each candidate individual in this iteration is obtained respectively.

4. A path planning device, characterized in that, It includes: An initialization unit, configured to randomly generate multiple ancestor individuals for the first iteration in response to a path planning task. Among them, any individual is used to represent a driving path of multiple stations in a series-connected park, and the starting point and the ending point of the driving path are the planned starting point and the planned ending point in the path planning task respectively; An iterative update unit, configured to repeatedly perform the following iterative operations: based on the population energy index of this iteration, screen multiple candidate individuals of this iteration, and use the candidate individuals retained after screening and the new candidate individuals generated based on at least some of the retained candidate individuals as the candidate individuals for the next iteration. Among them, the new candidate individual is obtained by iteratively updating a candidate individual based on the fitness of a candidate individual in this iteration, the fitness of all candidate individuals, and the update radius of this iteration; the population energy index of this iteration is obtained based on the number of individuals in this iteration and the current individual energy of each candidate individual in this iteration, and the current individual energy of a candidate individual in this iteration is related to the initial individual energy of the ancestor individual associated with the candidate individual; the fitness of any individual is obtained by performing the following operations: from the abstract map of the park, obtain the actual station distance between the stations corresponding to the adjacent vector values in the any individual, and use the sum of the station distances between the stations corresponding to all adjacent vector values as the fitness of the any individual; A decoding processing unit, configured to obtain the optimal candidate individual with the highest fitness in the last iteration until the maximum number of iterations is reached, and decode to obtain the optimal path by performing the following operations on the optimal candidate individual: replace each vector value in the optimal candidate individual with the associated station label value respectively, and construct the path order between the station label values based on the arrangement order of the vector values to form the optimal path between the planned starting point and the planned ending point.

5. A computer device, characterized in that, It includes a processor and a memory. Among them, the memory stores program codes, and when the program codes are executed by the processor, the processor is caused to execute the steps of the method according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, It includes program codes, and when the program product runs on a computer device, the program codes are used to cause the computer device to execute the steps of the method according to any one of claims 1-3.

Images