CN112308315A - Multi-point intelligent path planning method and system - Google Patents
Multi-point intelligent path planning method and system Download PDFInfo
- Publication number
- CN112308315A CN112308315A CN202011185597.3A CN202011185597A CN112308315A CN 112308315 A CN112308315 A CN 112308315A CN 202011185597 A CN202011185597 A CN 202011185597A CN 112308315 A CN112308315 A CN 112308315A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- path planning
- point
- algorithms
- intelligent path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0835—Relationships between shipper or supplier and carriers
- G06Q10/08355—Routing methods
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a multi-point intelligent path planning method and a multi-point intelligent path planning system.A plurality of types of intelligent path planning algorithms are integrated in a cloud platform algorithm library, algorithm combination is carried out according to different application requirements, and different types of intelligent path algorithm subsets are generated; receiving a multipoint intelligent path planning request sent by an application terminal, wherein the request comprises a request parameter and a point location data set to be planned; and inputting the point location data set to be planned into the corresponding algorithm subset according to the algorithm combination corresponding to the request parameters to perform multipoint path planning calculation, and returning the optimal path planning result to the application terminal. The invention considers from the aspects of completeness, accuracy, calculation efficiency and the like, improves the algorithm performance through the combined operation of the algorithms, selects a relatively optimized multi-point path planning result through the mutual comparison of different algorithms, surpasses the optimal effect which can be achieved by a single algorithm, and obtains a better multi-point path planning scheme.
Description
Technical Field
The invention relates to the technical field of path planning, in particular to a multipoint intelligent path planning method and system.
Background
The multi-point path planning problem, which is also known as a Traveling Salesman Problem (TSP) in academia, is a classical combinatorial optimization problem, and belongs to a world problem. The application fields of the 'traveler question' include: how to plan the most reasonable and efficient road traffic to reduce congestion; how to better plan logistics distribution to reduce operating costs; how to better set up nodes in an internet environment to better let information flow, etc. Since the multi-point path planning problem is a worldwide problem, the full arrangement of all points will generate a combination explosion with a combination probability of N! (factorial of N); when N is large, N! The calculation complexity of the possibility is too high, the time consumption is too long, and the path planning result cannot be returned within the effective time, so the exhaustion method in the computer technology is not feasible, that is, the true optimal multi-point path planning scheme cannot be obtained.
At present, heuristic algorithms and approximation algorithms are commonly adopted in academic circles and scientific circles to solve, and among numerous proposed algorithms, the optimal algorithm is not really optimal but only superior, namely, each algorithm has advantages and disadvantages. Specifically, in the actual application process, the result obtained by the algorithm a is sometimes optimal, the result obtained by the algorithm B is sometimes optimal, and the result obtained by the algorithm C is sometimes optimal, so that a single algorithm cannot provide an optimal multipoint path planning scheme.
Disclosure of Invention
Therefore, the invention provides a multi-point intelligent path planning method and system, aiming at solving the problem of how to realize intelligent route planning among multiple points.
In order to achieve the purpose, the invention provides the following technical scheme:
in a first aspect, an embodiment of the present invention provides a multipoint intelligent path planning method, including the following steps:
integrating multiple types of intelligent path planning algorithms into a cloud platform algorithm library, and combining the algorithms according to different application requirements to generate different types of multi-point intelligent path algorithm subsets;
receiving a multi-point intelligent path planning request sent by an application terminal, wherein the multi-point intelligent path planning request comprises a request parameter and a point location data set to be planned;
and inputting the point location data set to be planned into the corresponding algorithm subset to perform multipoint path planning calculation according to the algorithm combination corresponding to the request parameters, and returning the optimal path planning result to the application terminal.
In one embodiment, the types of intelligent routing algorithms in the algorithm library include: heuristic algorithms, optimization algorithms, graph search algorithms, and sampling plan algorithms.
In one embodiment, the heuristic algorithm comprises: nearest neighbor algorithm, nearest neighbor insertion algorithm, minimum cost insertion algorithm, farthest insertion algorithm, convex hull insertion algorithm, Criser's Fisher algorithm, greedy algorithm, Floyd algorithm, LPA algorithm, D Lite algorithm, ant colony algorithm, neural network algorithm, particle swarm algorithm, simulated annealing algorithm, genetic algorithm;
the optimization algorithm comprises the following steps: and (3) a K point optimization algorithm: K-Opt algorithm, Or-Opt algorithm, synthesis heuristic, tabu search algorithm;
the graph search algorithm includes: dijkstra algorithm, a algorithm, Theta algorithm, Phi algorithm, Voronoi diagram, C space method, free space method, grid method, fallback algorithm;
the sampling planning algorithm comprises the following steps: RRT algorithm, PRM algorithm, artificial potential field method algorithm and DWA algorithm.
In an embodiment, the step of performing algorithm combination according to different application requirements to generate different types of multi-point intelligent path algorithm subsets includes:
testing all algorithms and algorithm combinations in the algorithm library, evaluating and sequencing the effects of all algorithms and algorithm combinations according to preset evaluation indexes, recording evaluation results and sequencing results, and generating different types of multi-point intelligent path algorithm subsets according to the evaluation results and the sequencing results.
In an embodiment, the step of evaluating and sorting the effects of all algorithms and algorithm combinations according to a preset evaluation index, and recording the evaluation result and the sorting result, and the step of generating the different types of multi-point intelligent path algorithm subsets according to the evaluation result and the sorting result includes:
taking the algorithm and algorithm combination of the route planning effect ranking N before the distance characteristic as the algorithm subset based on the shortest distance;
taking the algorithm and the algorithm combination of the route planning effect ranking N before the time-consuming characteristic as the algorithm subset based on the least time consumption;
taking the algorithm and the algorithm combination of the route planning effect ranking N before the expense characteristic as the algorithm subset based on the lowest expense;
taking the algorithm and algorithm combination of the path planning effect ranking N before the commercial value characteristic as the algorithm subset based on the lowest cost;
taking the algorithm and algorithm combination of the planning effect ranking N before the comprehensive evaluation characteristic as an algorithm subset based on the highest commercial value;
taking the algorithm and the algorithm combination based on the low computation time consumption ranking top N as an algorithm subset based on the low computation time consumption;
taking the algorithm and the algorithm combination based on the low resource consumption ranking top N as an algorithm subset based on the low resource consumption;
algorithms and algorithm combinations which can be applied to specific application scenarios are used as the algorithm subsets based on the specific application scenarios.
In one embodiment, the point location data set to be planned is input into the algorithm subset, the path planning result of each algorithm or algorithm combination in the algorithm subset is calculated respectively, comparison is performed according to the evaluation index, and the corresponding optimal result is selected and returned to the application terminal.
In one embodiment, an application terminal includes: computer terminal, cell-phone terminal, vehicle navigation equipment to and wearable electronic equipment.
In a second aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer instructions are stored, and the computer instructions are configured to cause a computer to execute the multipoint intelligent path planning method according to the first aspect of the present invention.
In a third aspect, an embodiment of the present invention provides a computer device, including: the multipoint intelligent path planning method comprises a memory and a processor, wherein the memory and the processor are mutually connected in a communication mode, the memory stores computer instructions, and the processor executes the computer instructions so as to execute the multipoint intelligent path planning method in the first aspect of the embodiment of the invention.
The technical scheme of the invention has the following advantages:
the invention provides a multi-point intelligent path planning method and a multi-point intelligent path planning system.A plurality of types of intelligent path planning algorithms are integrated in a cloud platform algorithm library, algorithm combination is carried out according to different application requirements, and different types of intelligent path algorithm subsets are generated; receiving a multipoint intelligent path planning request sent by an application terminal, wherein the request comprises a request parameter and a point location data set to be planned; and inputting the point location data set to be planned into the corresponding algorithm subset according to the algorithm combination corresponding to the request parameters to perform multipoint path planning calculation, and returning the optimal path planning result to the application terminal. The invention considers from the aspects of completeness, accuracy, computational efficiency and the like, adopts the algorithm cluster concept to improve the algorithm performance through the combined operation of the algorithms, selects the relatively optimized multi-point path planning result through the mutual comparison of different algorithms, surpasses the optimal effect which can be achieved by a single algorithm, and obtains a better multi-point path planning scheme.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a work flow diagram of a specific example of a multipoint intelligent path planning method provided in an embodiment of the present invention;
fig. 2 is an application schematic diagram of the multipoint intelligent path planning method provided in the embodiment of the present invention applied to a "cloud platform + application terminal";
fig. 3 is a module composition diagram of a specific example of the multi-point intelligent path planning system provided in the embodiment of the present invention;
fig. 4 is a block diagram of a specific example of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example 1
The embodiment of the invention provides a multipoint intelligent path planning method, which comprises the following specific application scenarios: commodity logistics distribution, customer visit, retail terminal maintenance, takeout distribution, express delivery, intelligent business analysis, tourist attraction sightseeing route formulation, tobacco monopoly inspection, safety inspection, unmanned route planning, robot round inspection, unmanned aerial vehicle flight route planning and the like, wherein the method is mainly applied to an intelligent path planning service cloud platform and comprises the following steps as shown in figure 1:
step S1: and integrating multiple types of intelligent path planning algorithms into a cloud platform algorithm library, and combining the algorithms according to different application requirements to generate different types of multi-point intelligent path algorithm subsets.
In an embodiment of the present invention, the types of intelligent routing algorithms in the algorithm library include: heuristic algorithms, optimization algorithms, graph search algorithms, and sampling plan algorithms. Wherein:
the heuristic algorithm comprises the following steps: nearest neighbor algorithm, nearest neighbor insertion algorithm, minimum cost insertion algorithm, farthest insertion algorithm, convex hull insertion algorithm, Criser's Fisher algorithm, greedy algorithm, Floyd algorithm, LPA algorithm, D Lite algorithm, ant colony algorithm, neural network algorithm, particle swarm algorithm, simulated annealing algorithm, genetic algorithm; the optimization algorithm comprises the following steps: and (3) a K point optimization algorithm: K-Opt algorithm, Or-Opt algorithm, synthesis heuristic, tabu search algorithm; the graph search algorithm includes: dijkstra algorithm, a algorithm, Theta algorithm, Phi algorithm, Voronoi diagram, C space method, free space method, grid method, fallback algorithm; the sampling planning algorithm comprises the following steps: RRT algorithm, PRM algorithm, artificial potential field method algorithm and DWA algorithm.
It should be noted that K in the K-point optimization algorithm is a natural number greater than 2, and specifically includes: a 2-point optimization algorithm, a 3-point optimization algorithm, a 4-point optimization algorithm, a 5-point optimization algorithm, and so on. The specific algorithms included in the above types are only used as examples, but not limited to these examples, and in practical applications, the algorithms in the algorithm library may be adaptively expanded according to actual requirements.
The embodiment of the invention combines algorithms according to different application requirements, and the process of generating the multi-point intelligent path algorithm subsets of different types is as follows: testing all algorithms and algorithm combinations in the algorithm library, evaluating and sequencing the effects of all algorithms and algorithm combinations according to preset evaluation indexes, recording evaluation results and sequencing results, and generating different types of multi-point intelligent path algorithm subsets according to the evaluation results and the sequencing results.
In consideration of the response time problem of the algorithms and the service, the calculation time consumption of the multiple algorithms is accumulated, and in order to improve the calculation efficiency of the whole method and reduce the calculation time consumption, the embodiment of the invention adopts a strategy of N (N can be any natural number) before the performance effect ranking. For example, when N is 5, the cloud platform may rank various algorithms and algorithm combinations through a previous random simulation test; in practical application, only the algorithm 5 before the ranking is selected for path planning calculation, and then the optimal scheme is selected from the 5 obtained path plans and returned to the application terminal. Therefore, the response time of the request service is ensured to be in a reasonable interval, and the defects and shortcomings of a single algorithm can be overcome through the advantages of the algorithm cluster.
Therefore, the embodiment of the present invention provides multiple feature-based evaluation indexes, forms different sets including algorithms and algorithm combinations to generate different types of multi-point intelligent path algorithm subsets, and enriches the application modes of path planning to apply terminal selection, specifically including:
(1) taking the algorithm and algorithm combination of the route planning effect ranking N before the distance characteristic as the algorithm subset based on the shortest distance;
(2) taking the algorithm and the algorithm combination of the route planning effect ranking N before the time-consuming characteristic as the algorithm subset based on the least time consumption;
(3) taking the algorithm and the algorithm combination of the route planning effect ranking N before the expense characteristic as the algorithm subset based on the lowest expense;
(4) taking the algorithm and algorithm combination of the path planning effect ranking N before the commercial value characteristic as the algorithm subset based on the lowest cost;
(5) taking the algorithm and algorithm combination of the planning effect ranking N before the comprehensive evaluation characteristic as an algorithm subset based on the highest commercial value;
(6) taking the algorithm and the algorithm combination based on the low computation time consumption ranking top N as an algorithm subset based on the low computation time consumption;
(7) taking the algorithm and the algorithm combination based on the low resource consumption ranking top N as an algorithm subset based on the low resource consumption;
(8) algorithms and algorithm combinations which can be applied to specific application scenarios are used as the algorithm subsets based on the specific application scenarios.
It should be noted that N of the top N in the path planning effect ranking obtained by the above-mentioned various feature-based evaluation indexes may be set according to actual needs, and is not limited herein.
Step S2: receiving a multi-point intelligent path planning request sent by an application terminal, wherein the multi-point intelligent path planning request comprises a request parameter and a point location data set to be planned.
In the practical application of multipoint intelligent path planning, the application range is wide, and the functions of mobile phone navigation, positioning and the like are generally needed due to the networking and moving requirements; meanwhile, the path planning application has diversity and variability, and many situations of sudden conditions and temporary changes, such as change of visiting places, user position movement and the like, can occur in the application process, so that the multipoint path planning algorithm, the application and the service need to have the characteristics of quick response, real-time response and dynamic response so as to be capable of timely dealing with the sudden conditions. Therefore, the embodiment of the invention adopts the combination of the cloud platform and the application terminal shown in fig. 2, so that the multipoint intelligent path planning cloud service can be promoted to reach every corner of the network coverage.
In the embodiment of the invention, the application terminal (such as a computer terminal, a mobile phone terminal, a vehicle-mounted navigation device, and wearable electronic devices: an electronic watch, an electronic bracelet, and the like) specifies a specific algorithm, an algorithm subset type, a request scene type, and the like adopted by the path planning application by sending the multi-point intelligent path planning request. The data interface can be used for program development through POST and GET methods based on an HTML protocol, and determining a specific algorithm, an algorithm subset type and a request scene type through parameter transmission so as to realize data interaction; a particular algorithm in the algorithm library may be specified, such as a nearest neighbor algorithm, etc.; the type of algorithm subset requested may also be specified, for example, based on shortest distance, based on least time consuming, based on least cost, based on highest business value, based on highest composite rating, based on low computing time consuming, based on low resource consumption, based on specific application scenarios; when the algorithm subset type based on a specific application scene is specified, the specific scene needs to be specified, such as commodity logistics distribution, customer visit, retail terminal maintenance, takeaway distribution, express delivery distribution, intelligent business analysis, tourist attraction sightseeing route planning, tobacco monopoly inspection, safety inspection, unmanned line planning, robot round inspection and unmanned plane flight route planning; different scenarios may correspond to different subsets of algorithms, for example, a goods logistics scenario, and there may be a subset of algorithms for the goods logistics scenario, i.e., the first N algorithms are different. The "application-specific scenario-based" can be regarded as a large class, and a specific scenario such as "commodity logistics" can be regarded as one of the sub-classes, and the calculation method of the top N algorithm sets in each sub-class is the same as that of the other "algorithm subset types". The point location data set to be planned is a geographical location information set of a plurality of point locations visited according to a user plan. N may also be set as a parameter in the user request so that the user can determine the value of N himself.
Step S3: and inputting the point location data set to be planned into the corresponding algorithm subset to perform multipoint path planning calculation according to the algorithm combination corresponding to the request parameters, and returning the optimal path planning result to the application terminal.
According to the embodiment of the invention, the point location data set to be planned is input into the algorithm subset, the path planning result of each algorithm or algorithm combination in the algorithm subset is respectively calculated, and the comparison is carried out according to the evaluation index, so that the corresponding optimal result is selected and returned to the application terminal.
The multi-point intelligent path planning method provided by the embodiment of the invention considers the aspects of completeness, accuracy, calculation efficiency and the like, because the optimal solution (typical NP problem) can not be obtained mathematically by the multi-point path planning algorithm, different path planning algorithms have advantages and disadvantages, in order to overcome the defect that a single algorithm can not avoid, an algorithm cluster concept is adopted, the algorithm performance is improved through the combined operation between the algorithms, and the relatively optimized multi-point path planning result is selected through the mutual comparison between the different algorithms. Each algorithm can solve a relatively optimal multipoint path planning scheme, and in order to find a more optimal solution among the algorithms, each algorithm can be calculated once and then a scheme is selected preferentially, so that the effect of being hundreds of families is achieved; furthermore, the combination optimization can be performed by combining the strong terms of the optimization algorithm, for example, a relatively better path planning scheme can be obtained by using a heuristic algorithm, and then secondary optimization is performed on the basis of the original scheme by using a K-point optimization algorithm, so that a better multi-point path planning result is obtained. Therefore, the heuristic algorithm, the optimization algorithm, the graph search algorithm and the sampling planning algorithm can cooperate with each other, so that the path planning effect of '1 +1> 2' is obtained. Therefore, the solution mode of any combination between different algorithms provided by the embodiment of the invention finally selects the optimal scheme from the plurality of path planning schemes according to the actual path planning effect, thereby exceeding the optimal effect which can be achieved by a single algorithm and obtaining a better multi-point path planning scheme. And the judgment of the effect is that different path planning results can be compared through indexes specified by a user, such as shortest distance, least time consumption, lowest cost, highest commercial value, highest comprehensive evaluation, low computation time consumption, low resource consumption and specific application scenes. The algorithm subset categories are diversified, so that the method provided by the embodiment of the invention can be better suitable for different application scenes, and a user can freely select the algorithm subset categories through the data interface design. Considering the problem of execution efficiency of an algorithm program, in order to achieve a certain balance between algorithm precision and execution efficiency in the multipoint path planning service, the method adopts a strategy of N before ranking, pre-selects a better candidate algorithm set through early-stage simulation calculation and algorithm evaluation, effectively avoids a large amount of invalid calculations, and can achieve a relatively better path planning effect. N can be used as a user-defined sliding window, namely when N is increased, the algorithm is more accurate, but the calculation efficiency is lower; otherwise, the algorithm precision is reduced, but the calculation efficiency is higher.
Based on the multipoint path planning method provided by the embodiment of the invention, the cloud platform provides functional support for the application terminal, such as electronic map analysis, data query, data analysis, path visualization, positioning, navigation, labeling and the like. For example, the planned path is visually displayed on an electronic map, and corresponding navigation service is provided; such as information queries for retail customers, including storefront information, addresses, pictures, etc., and related business data such as sales, order volume, etc.; for example, a data analysis chart and a report are calculated according to sales data of retail customers; the map analysis function comprises thermodynamic diagrams, grid diagrams, flight diagrams, bubble diagrams and the like, so that a user can conveniently and comprehensively display, analyze and evaluate the path planning scheme provided by the platform, the path planning scheme can be corrected through manual judgment if necessary, and adverse effects caused by algorithm defects are avoided through manual supervision.
Example 2
An embodiment of the present invention provides a multipoint intelligent path planning system, as shown in fig. 3, including:
the multi-point intelligent path algorithm subset module 1 is used for integrating various types of intelligent path planning algorithms into a cloud platform algorithm library, performing algorithm combination according to different application requirements and generating multi-point intelligent path algorithm subsets of different types; this module executes the method described in step S1 in embodiment 1, and is not described herein again.
The path planning request receiving module 2 is configured to receive a multipoint intelligent path planning request sent by an application terminal, where the multipoint intelligent path planning request includes a request parameter and a point location data set to be planned; this module executes the method described in step S2 in embodiment 1, and is not described herein again.
A path planning result generation module 3, configured to input the point location data set to be planned into a corresponding algorithm subset according to the algorithm combination corresponding to the request parameter to perform multipoint path planning calculation, and return an optimal path planning result to the application terminal; this module executes the method described in step S3 in embodiment 1, and is not described herein again.
According to the multi-point intelligent path planning system provided by the embodiment of the invention, various types of intelligent path planning algorithms are integrated in a cloud platform algorithm library, algorithm combination is carried out according to different application requirements, and different types of intelligent path algorithm subsets are generated; receiving a multipoint intelligent path planning request sent by an application terminal, wherein the request comprises a request parameter and a point location data set to be planned; and inputting the point location data set to be planned into the corresponding algorithm subset according to the algorithm combination corresponding to the request parameters to perform multipoint path planning calculation, and returning the optimal path planning result to the application terminal. The invention considers from the aspects of completeness, accuracy, computational efficiency and the like, adopts the algorithm cluster concept to improve the algorithm performance through the combined operation of the algorithms, selects the relatively optimized multi-point path planning result through the mutual comparison of different algorithms, surpasses the optimal effect which can be achieved by a single algorithm, and obtains a better multi-point path planning scheme.
Example 3
An embodiment of the present invention provides a computer device, as shown in fig. 4, the device may include a processor 51 and a memory 52, where the processor 51 and the memory 52 may be connected by a bus or in another manner, and fig. 4 takes the connection by the bus as an example.
The processor 51 may be a Central Processing Unit (CPU). The Processor 51 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof.
The memory 52, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as the corresponding program instructions/modules in the embodiments of the present invention. The processor 51 executes various functional applications and data processing of the processor by running non-transitory software programs, instructions and modules stored in the memory 52, that is, implements the multipoint intelligent path planning method in the above method embodiment 1.
The memory 52 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 51, and the like. Further, the memory 52 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 52 may optionally include memory located remotely from the processor 51, and these remote memories may be connected to the processor 51 via a network. Examples of such networks include, but are not limited to, the internet, intranets, mobile communication networks, and combinations thereof.
One or more modules are stored in the memory 52 and, when executed by the processor 51, perform the multipoint intelligent path planning method of embodiment 1. The details of the computer device can be understood by referring to the corresponding related descriptions and effects in embodiment 1, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program that can be stored in a computer-readable storage medium and that when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications of the invention may be made without departing from the spirit or scope of the invention.
Claims (10)
1. A multi-point intelligent path planning method is applied to an intelligent path planning service cloud platform and is characterized by comprising the following steps:
integrating multiple types of intelligent path planning algorithms into a cloud platform algorithm library, and combining the algorithms according to different application requirements to generate different types of multi-point intelligent path algorithm subsets;
receiving a multi-point intelligent path planning request sent by an application terminal, wherein the multi-point intelligent path planning request comprises a request parameter and a point location data set to be planned;
and inputting the point location data set to be planned into the corresponding algorithm subset to perform multipoint path planning calculation according to the algorithm combination corresponding to the request parameters, and returning the optimal path planning result to the application terminal.
2. The multi-point intelligent path planning method of claim 1, wherein the types of intelligent path planning algorithms in the algorithm library include: heuristic algorithms, optimization algorithms, graph search algorithms, and sampling plan algorithms.
3. The multi-point intelligent path planning method according to claim 2,
the heuristic algorithm comprises the following steps: nearest neighbor algorithm, nearest neighbor insertion algorithm, minimum cost insertion algorithm, farthest insertion algorithm, convex hull insertion algorithm, Criser's Fisher algorithm, greedy algorithm, Floyd algorithm, LPA algorithm, D Lite algorithm, ant colony algorithm, neural network algorithm, particle swarm algorithm, simulated annealing algorithm, genetic algorithm;
the optimization algorithm comprises the following steps: and (3) a K point optimization algorithm: K-Opt algorithm, Or-Opt algorithm, synthesis heuristic, tabu search algorithm;
the graph search algorithm includes: dijkstra algorithm, a algorithm, Theta algorithm, Phi algorithm, Voronoi diagram, C space method, free space method, grid method, fallback algorithm;
the sampling planning algorithm comprises the following steps: RRT algorithm, PRM algorithm, artificial potential field method algorithm and DWA algorithm.
4. The multipoint intelligent path planning method according to claim 1, wherein the step of combining algorithms according to different application requirements to generate different types of multipoint intelligent path algorithm subsets comprises:
testing all algorithms and algorithm combinations in the algorithm library, evaluating and sequencing the effects of all algorithms and algorithm combinations according to preset evaluation indexes, recording evaluation results and sequencing results, and generating different types of multi-point intelligent path algorithm subsets according to the evaluation results and the sequencing results.
5. The multipoint intelligent path planning method according to claim 4, wherein the step of evaluating and sorting the effects of all algorithms and algorithm combinations according to preset evaluation indexes, recording evaluation results and sorting results, and generating different types of multipoint intelligent path algorithm subsets according to the evaluation results and the sorting results comprises:
taking the algorithm and algorithm combination of the route planning effect ranking N before the distance characteristic as the algorithm subset based on the shortest distance;
taking the algorithm and the algorithm combination of the route planning effect ranking N before the time-consuming characteristic as the algorithm subset based on the least time consumption;
taking the algorithm and the algorithm combination of the route planning effect ranking N before the expense characteristic as the algorithm subset based on the lowest expense;
taking the algorithm and algorithm combination of the path planning effect ranking N before the commercial value characteristic as the algorithm subset based on the lowest cost;
taking the algorithm and algorithm combination of the planning effect ranking N before the comprehensive evaluation characteristic as an algorithm subset based on the highest commercial value;
taking the algorithm and the algorithm combination based on the low computation time consumption ranking top N as an algorithm subset based on the low computation time consumption;
taking the algorithm and the algorithm combination based on the low resource consumption ranking top N as an algorithm subset based on the low resource consumption;
algorithms and algorithm combinations which can be applied to specific application scenarios are used as the algorithm subsets based on the specific application scenarios.
6. The multipoint intelligent path planning method according to claim 4, wherein point location data sets to be planned are input into the algorithm subset, path planning results of each algorithm or algorithm combination in the algorithm subset are respectively calculated, comparison is performed according to evaluation indexes, and a corresponding optimal result is selected and returned to the application terminal.
7. The multipoint intelligent path planning method according to claim 6, wherein the application terminal comprises: computer terminal, cell-phone terminal, vehicle navigation equipment to and wearable electronic equipment.
8. A multi-point intelligent path planning system, comprising:
the multi-point intelligent path algorithm subset module is used for integrating various types of intelligent path planning algorithms into a cloud platform algorithm library, performing algorithm combination according to different application requirements and generating multi-point intelligent path algorithm subsets of different types;
the path planning request receiving module is used for receiving a multi-point intelligent path planning request sent by an application terminal, wherein the multi-point intelligent path planning request comprises a request parameter and a point location data set to be planned;
and the path planning result generation module is used for inputting the point location data set to be planned into the corresponding algorithm subset to perform multipoint path planning calculation according to the algorithm combination corresponding to the request parameters, and returning the optimal path planning result to the application terminal.
9. A computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the multipoint intelligent path planning method of any of claims 1-6.
10. A computer device, comprising: a memory and a processor, the memory and the processor being communicatively coupled to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the multipoint intelligent path planning method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011185597.3A CN112308315A (en) | 2020-10-29 | 2020-10-29 | Multi-point intelligent path planning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011185597.3A CN112308315A (en) | 2020-10-29 | 2020-10-29 | Multi-point intelligent path planning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112308315A true CN112308315A (en) | 2021-02-02 |
Family
ID=74331888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011185597.3A Pending CN112308315A (en) | 2020-10-29 | 2020-10-29 | Multi-point intelligent path planning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112308315A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113111110A (en) * | 2021-04-06 | 2021-07-13 | 王皓 | Intelligent monopoly data application platform |
| CN113467473A (en) * | 2021-07-28 | 2021-10-01 | 河南中烟工业有限责任公司 | Material storage method and device based on autonomous mobile robot |
| CN116703364A (en) * | 2023-08-02 | 2023-09-05 | 杭州宇谷科技股份有限公司 | Operation and maintenance work order generation method and system based on optimization algorithm |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389639A (en) * | 2015-12-15 | 2016-03-09 | 上海汽车集团股份有限公司 | Logistics transportation route planning method, device and system based on machine learning |
| CN108830403A (en) * | 2018-05-23 | 2018-11-16 | 广西中烟工业有限责任公司 | The tobacco retail customer calculated based on commercial value visits path visual analysis method |
| CN109029475A (en) * | 2018-05-23 | 2018-12-18 | 广西中烟工业有限责任公司 | Tobacco retail customer based on cloud computing visits path planning visual analysis system |
| CN109084794A (en) * | 2018-08-09 | 2018-12-25 | 北京智行者科技有限公司 | A kind of paths planning method |
| CN109724611A (en) * | 2019-01-08 | 2019-05-07 | 北京三快在线科技有限公司 | Paths planning method, device, electronic equipment and storage medium |
| CN109726868A (en) * | 2018-12-28 | 2019-05-07 | 腾讯科技（深圳）有限公司 | Paths planning method, device and storage medium |
| CN111442783A (en) * | 2020-04-30 | 2020-07-24 | 福州吉诺网络科技有限公司 | Method and terminal for optimizing path planning |
-
2020
- 2020-10-29 CN CN202011185597.3A patent/CN112308315A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389639A (en) * | 2015-12-15 | 2016-03-09 | 上海汽车集团股份有限公司 | Logistics transportation route planning method, device and system based on machine learning |
| CN108830403A (en) * | 2018-05-23 | 2018-11-16 | 广西中烟工业有限责任公司 | The tobacco retail customer calculated based on commercial value visits path visual analysis method |
| CN109029475A (en) * | 2018-05-23 | 2018-12-18 | 广西中烟工业有限责任公司 | Tobacco retail customer based on cloud computing visits path planning visual analysis system |
| CN109084794A (en) * | 2018-08-09 | 2018-12-25 | 北京智行者科技有限公司 | A kind of paths planning method |
| CN109726868A (en) * | 2018-12-28 | 2019-05-07 | 腾讯科技（深圳）有限公司 | Paths planning method, device and storage medium |
| CN109724611A (en) * | 2019-01-08 | 2019-05-07 | 北京三快在线科技有限公司 | Paths planning method, device, electronic equipment and storage medium |
| CN111442783A (en) * | 2020-04-30 | 2020-07-24 | 福州吉诺网络科技有限公司 | Method and terminal for optimizing path planning |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113111110A (en) * | 2021-04-06 | 2021-07-13 | 王皓 | Intelligent monopoly data application platform |
| CN113467473A (en) * | 2021-07-28 | 2021-10-01 | 河南中烟工业有限责任公司 | Material storage method and device based on autonomous mobile robot |
| CN113467473B (en) * | 2021-07-28 | 2023-09-15 | 河南中烟工业有限责任公司 | Material storage method and device based on autonomous mobile robot |
| CN116703364A (en) * | 2023-08-02 | 2023-09-05 | 杭州宇谷科技股份有限公司 | Operation and maintenance work order generation method and system based on optimization algorithm |
| CN116703364B (en) * | 2023-08-02 | 2024-01-16 | 杭州宇谷科技股份有限公司 | Operation and maintenance work order generation method and system based on optimization algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112308315A (en) | Multi-point intelligent path planning method and system | |
| WO2020176381A1 (en) | Joint order dispatching and fleet management for online ride-sharing platforms | |
| CN111612122B (en) | Real-time demand prediction method and device and electronic equipment | |
| CN110390415A (en) | A kind of method and system carrying out trip mode recommendation based on user's trip big data | |
| JP2023500883A (en) | Cold chain delivery route determination method, device, server and storage medium | |
| US20230075758A1 (en) | Travel route planning method and travel route recommendation method | |
| CN112712690A (en) | Vehicle electronic fence method and device and electronic equipment | |
| CN111473789B (en) | Navigation route planning method, device and equipment | |
| CN111295569A (en) | System and method for generating road map | |
| Marchetta et al. | A map-based platform for smart mobility services | |
| CN111859187A (en) | POI query method, device, equipment and medium based on distributed graph database | |
| CN115705593A (en) | Logistics transportation method and device, computer equipment and storage medium | |
| Bozdog et al. | RideMatcher: peer-to-peer matching of passengers for efficient ridesharing | |
| Ivaschenko et al. | Multi-layer data model for transportation logistics solutions | |
| Bakkal et al. | Modeling and querying trajectories using Neo4j spatial and TimeTree for carpool matching | |
| US10191928B2 (en) | Planar graph generation device and method | |
| Belcastro et al. | Evaluation of large scale roi mining applications in edge computing environments | |
| CN114594790A (en) | Power distribution network multi-unmanned-aerial-vehicle line patrol path planning method and system | |
| CN115409222A (en) | Graph database-based transportation route planning method, device, equipment and medium | |
| CN114330807A (en) | Route determination method and device and electronic equipment | |
| Chen et al. | Research on the shortest path Analysis method in Complex Traffic Environment Based on GIS | |
| Ghosh et al. | Computing Skyline Using Taxicab Geometry | |
| CN110674843A (en) | Method and system for generating parking lot entity | |
| Pei et al. | A novel traveling salesman problem solution by accelerated evolutionary computation with approximated cost matrix in an industrial application | |
| Ghosh et al. | Opportunistic package delivery as a service on road networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |