CN109631923B - Scenic driving route planning method based on modular factorial algorithm - Google Patents
Scenic driving route planning method based on modular factorial algorithm Download PDFInfo
- Publication number
- CN109631923B CN109631923B CN201811454385.3A CN201811454385A CN109631923B CN 109631923 B CN109631923 B CN 109631923B CN 201811454385 A CN201811454385 A CN 201811454385A CN 109631923 B CN109631923 B CN 109631923B
- Authority
- CN
- China
- Prior art keywords
- scenic
- road section
- chromosome
- population
- driving route
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3476—Special cost functions, i.e. other than distance or default speed limit of road segments using point of interest [POI] information, e.g. a route passing visible POIs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Automation & Control Theory (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Theoretical Computer Science (AREA)
- Physiology (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Genetics & Genomics (AREA)
- Navigation (AREA)
Abstract
The invention provides a scenic driving route planning method based on a modular factorial algorithm, which recommends a scenic optimal driving route between two given points for a user on the premise of starting at a specified time and not exceeding a time budget. More specifically, in a time budget range given by a user, encoding scenic road sections from a starting point to an end point into a chromosome through a chromosome encoding process to obtain an initial scenic road section population; secondly, carrying out adaptability evaluation on chromosomes in the population; then generating a new scenic road section population through chromosome selection and variation and cross operation based on local improvement; and finally, iterating the population repeatedly until the specified iteration times are reached, and obtaining a scenic driving route meeting the user requirements.
Description
Technical Field
The invention relates to the field of route planning, in particular to a scenic route planning method.
Background
With the continuous progress and development of society, the self-driving travel becomes a life fashion, and the planning of driving routes is more and more emphasized by people. Finding driving routes between two points on a spatial road network has become one of the most common route planning activities today. Although many mobile terminal GPS navigation and online travel routing websites are now used for routing. The most common is to find the shortest or fastest path between two points. However, in real life, people tend to pay more attention to the driving process rather than reaching the destination quickly. Such as enjoying scenery along the way during driving, or finding a quiet driving route, or finding a safest route during night driving. With the increasing popularity of location-based social networks and sensors, various traffic-related data has accumulated on an unprecedented scale, providing tremendous convenience to route planners. However, in the conventional route planning method, the scenic values and the travel time on the road sections are changed along with time, so that complicated and various user requirements cannot be met.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a scenic driving route planning method based on a modular factorial algorithm, which recommends a scenic optimal driving route between two given points for a user on the premise of starting at a specified time and not exceeding a time budget. More specifically, in a time budget range given by a user, encoding scenic road sections from a starting point to an end point into a chromosome through a chromosome encoding process to obtain an initial scenic road section population; secondly, carrying out adaptability evaluation on chromosomes in the population; generating a new scenic road section population through chromosome selection and variation and cross operation based on local improvement; and finally, repeatedly iterating the population until the specified iteration times are reached, and obtaining a landscape driving route meeting the user requirements.
Specifically, the scenic driving route planning method based on the modular factorial algorithm adopts the technical scheme that: obtaining an optimal scenic driving route meeting the requirements of a user by using a modular factor algorithm; the system comprises a scenic road section initial population generation module, a fitness evaluation module and a scenic road section new population generation module; the scenic road section initial population generation module screens out the range of effective scenic sections within a time budget range given by a user, and codes the scenic road sections from a starting point to an end point into a chromosome through a chromosome coding process to obtain an initial scenic road section population; the population fitness evaluation module is used for evaluating the fitness of chromosomes in a population and eliminating chromosomes which do not meet requirements; the scenic road section new population generation module improves each chromosome through chromosome selection and variation and cross operation based on local improvement to generate a scenic road section new population.
Further, a scenic driving route planning method based on a modular factorization algorithm, the scenic section initial population generation module comprises the following steps:
the method comprises the following steps: determining a search range;
step two: and (4) encoding the landscape road section.
Furthermore, the method for planning the scenic driving route based on the modular factorial algorithm determines that the search range takes the starting point as the center of a circle, and takes the average speed from the starting point to the end point multiplied by the time budget as the radius to draw a circle, namely the search range of the scenic road section.
Further, a scenic driving route planning method based on a modulo factor algorithm, the scenic section code includes the following steps:
the method comprises the following steps: drawing a circle by taking the starting point as the center of a circle and taking the average speed from the starting point to the end point multiplied by the time budget as a radius, and drawing a circle by taking the end point as the center of a circle and the same radius in the same way, wherein the intersection area of the two circles is an effective scenic road section selection area;
step two: sequencing the road sections of the effective scenic road section selection area according to the geographic distance from the starting point to obtain an effective scenic road section sequencing set; randomly selecting a scenic road section from the effective scenic road section sequencing set, and updating the starting point to the node and the time budget in the scenic road section; repeating the first step;
step three: if the effective scenic road section sequencing set is empty, outputting the scenic route at the moment as a coded scenic route, and ending the coding; otherwise, circulating the step two; and finally outputting the encoded initial population of the scenic road sections.
Furthermore, a scenic driving route planning method based on a modular cause algorithm is characterized in that a fitness evaluation module is used for calculating the fitness of each chromosome according to a scenic value depending on the driving time and the time after decoding the initial population of a scenic road section into a specific driving route; the greater the route fitness value, the more excellent the chromosome, and the greater the chance of being retained in subsequent chromosome selection processes.
Further, a scenic driving route planning method based on a modular cause algorithm, wherein the scenic road section new population generation module comprises the following steps:
the method comprises the following steps: selecting a chromosome;
step two: (ii) variation based on local improvement;
step three: the chromosomes are crossed.
Further, a scenic driving route planning method based on a modular factorial algorithm is characterized in that chromosome selection is selected by adopting a roulette wheel algorithm, the sum of adaptive values of all chromosomes in a population is calculated firstly, then the ratio of the adaptive value of each chromosome to the total adaptive value is calculated, finally, one chromosome is selected from the population by adopting the roulette wheel algorithm and added into a new population, a new population with the same size as the population is obtained through multiple iterative selections, and the new population contains repeated chromosomes with higher adaptive values.
Furthermore, a scenic driving route planning method based on a modular factorial algorithm is characterized in that on the premise of not violating time budget, one scenic road section randomly selected is replaced by another scenic road section within an effective scenic road section selection range based on locally improved mutation operation; mutation operation mutation probability P specified by user m And in [0,1 ]]Random value ρ within a range m Two parameter control, P m ＞ρ m When performing mutation.
Further, a landscape driving route planning method based on a modular factorial algorithm, wherein the chromosome crossing operation is to select two chromosomes by using a gambling mechanism, divide the two chromosomes into two parts at the same position, and generate two new chromosomes by exchanging the second parts of the two chromosomes; crossover operation crossover probability P specified by user c And in [0,1 ]]Random value ρ in the range c Two parameter control, P c ＞ρ c And performing interleaving.
Further, a scenic driving route planning method based on a modular factor algorithm comprises the following steps:
the method comprises the following steps: obtaining an initial population of the scenic road section by determining a search range and a scenic road section code;
step two: decoding the initial population to obtain a plurality of specific driving routes, and performing adaptability evaluation on each driving route;
step three: improving each chromosome through chromosome selection and variation and cross operation based on local improvement to obtain a new scenic road section population;
step four: and step two and step three are circulated until the iteration times specified by the user are reached, and the landscape driving route at the moment is output as the optimal landscape driving route.
The invention has the beneficial effects that: a scenic driving route planning method based on a modular factorial algorithm recommends a scenic optimal driving route between two given points for a user on the premise of starting at a specified time and not exceeding a time budget. More specifically, in a time budget range given by a user, encoding scenic road sections from a starting point to an end point into a chromosome through a chromosome encoding process to obtain an initial scenic road section population; secondly, carrying out adaptability evaluation on chromosomes in the population; generating a new scenic road section population through chromosome selection and variation and cross operation based on local improvement; and finally, iterating the population repeatedly until the specified iteration times are reached, and obtaining a scenic driving route meeting the user requirements.
Drawings
FIG. 1 is a process flow framework of the method of the present invention;
FIG. 2 is a schematic view of a search range of a scenic road section;
FIG. 3 is a selection range of effective scenic road segments;
FIG. 4 is a schematic diagram of a chromosome coding process;
FIG. 5 is a diagram showing a process of chromosomal variation;
FIG. 6 is a schematic chromosome crossover;
FIG. 7 is a schematic view of embodiment 1 of the present invention: the starting point is a grocery store and the ending point is a starbucks cafe, wherein the three routes respectively represent different driving routes.
Detailed Description
The technical solution of the present invention is further described below with reference to the accompanying drawings:
the method flow framework herein has three main modules: the system comprises a scenic road section initial population generation module, a fitness evaluation module and a scenic road section new population generation module, which are shown in figure 1.
The initial population generation module of the scenic road section comprises: and screening the range of the effective scenic sections within the time budget range given by the user, and encoding the scenic sections from the starting point to the end point into a chromosome through a chromosome encoding process to obtain an initial scenic section population.
A fitness evaluation module: and evaluating the adaptability degree of the chromosomes in the population, and eliminating the chromosomes which do not meet the requirements.
The scenic road section new population generation module: each chromosome is improved through chromosome selection, variation based on local improvement and crossover operation, and a new population of landscape road sections is generated.
1. Scenic road segment initial population generation
The initial population generation of the scenic road sections comprises two steps.
Step 1: determining a search range; a search range is determined.
And drawing a circle by taking the starting point as the center of the circle and the average speed from the starting point to the end point multiplied by the time budget as the radius, wherein the circle is the search range of the landscape road section. As shown in fig. 2.
And 2, step: and (4) encoding the landscape road section. The scenic road section code includes the following steps:
step 2.1, drawing a circle by taking the starting point as the circle center and taking the average speed from the starting point to the end point multiplied by the time budget as a radius, and similarly, drawing a circle by taking the end point as the circle center and taking the same radius, wherein the intersection area of the two circles is the effective scenic road section selection area, as shown in fig. 3; step 2.2, the road sections of the effective landscape road section selection area are sorted according to the geographical distance from the starting point to obtain an effective landscape road section sorting set; randomly selecting a scenic road section from the effective scenic road section sequencing set, and updating the starting point to the node and the time budget in the scenic road section; repeating 1; step 2.3, if the effective scenic road section sequencing set is empty, outputting the scenic route at the moment as a coded scenic route, and ending the coding; otherwise, the step 1 and the step 2 are circulated. And finally outputting the encoded initial population of the scenic road sections. FIG. 4 shows the encoding process for a single chromosome.
2. Fitness evaluation
Before fitness evaluation, chromosomes in the initial population of the scenic road section need to be decoded into a specific driving route, and then fitness of each chromosome needs to be calculated. Because each landscape road section in the chromosome has a forward direction and a reverse direction, in order to reduce the time spent on driving the route as much as possible on the premise of ensuring the landscape value of the decoded feasible landscape route, the direction problem of all the landscape road sections needs to be considered when decoding one chromosome. In order to obtain the optimal road section direction combination in the chromosome, a dynamic planning algorithm is designed. Inputting a starting point O, an end point D, a chromosome to be decoded and a distance between any two nodes in a pre-stored shortest path of the algorithm; the output of the algorithm is the shortest driving route through all scenic road segments.
After the chromosomes are decoded into a specific driving route, the time-dependent landscape value and the travel time of the route can be calculated according to the departure time, then some chromosomes which do not meet the actual conditions are eliminated, and the chromosomes with the time-dependent travel time exceeding the time budget are eliminated. And calculating the fitness of the chromosome according to the time-dependent landscape value and the travel time. The larger the decoded route fitness function value, the higher landscape value and less travel time of the generated route, the more excellent the chromosome, and the higher the probability of being retained in the subsequent chromosome selection process.
And calculating the fitness of the chromosome. Where p represents the given decoded travel route, f (p) represents the fitness of the route p, u (p) represents the landscape value of the route p, and c (p) represents the travel time of the route p.
3. Landscape road section new population generation module
The generation of new population for scenic road section comprises three steps.
Step 1: and (4) selecting chromosomes.
The purpose of chromosome selection is to increase the proportion of good chromosomes in the population; the selection of chromosomes is actually a process that mimics the survival of the biological evolving fitter. The higher the fitness value of an individual, the greater the chance of survival. A new chromosome population is generated by an iterative process of chromosome selection. A roulette wheel algorithm is adopted to select chromosomes, the sum of the fitness values of all chromosomes in a population is calculated firstly, then the ratio of the fitness value of each chromosome to the total fitness value is calculated, finally, the roulette wheel algorithm is adopted to select one chromosome from the population and add the chromosome into a new population, a new population with the same size as the population is obtained through multiple iterative selection, and the new population contains repeated chromosomes with higher fitness values.
And 2, step: based on locally improved variation.
The mutation based on local improvement acts on a single chromosome, and the crossover operation is based on a pair of chromosomes. Based on locally improved variation. The operation of chromosomal variation is controlled by two parameters, i.e. P m And ρ m In which P is m Is a user-specified constant, commonly referred to as the mutation probability; rho m Is in [0,1 ]]Random values within the range. Selecting each chromosome in turn and generating rho m When P is m >ρ m Then, a mutation operation is performed on the chromosome, and a random number i within a chromosome length range is generated to indicate the position of the scenic road segment mutation. The ith scenic road segment in the chromosome is replaced by a new scenic road segment. Fig. 5 shows an example of variation of chromosomes.
And 3, step 3: the chromosomes are crossed.
The chromosomes are crossed. Chromosome crossing operations are controlled by two parameters, i.e. P c And ρ c In which P is c Is a user-specified constant, commonly referred to as the crossover probability; rho c Is in [0,1 ]]Random values within the range. In the population, k chromosomes are set, and from the 1 st chromosome, the jth chromosome and the j +1 th chromosome are sequentially selected, wherein j is more than or equal to 1 and less than or equal to k, and rho is generated c A value; when P is present c >ρ c When the two chromosomes satisfy the crossing condition, the chromosome crossing operation is performed next, and a random number i in a chromosome length range is generated to represent the position of the scenic road section exchange. FIG. 6 shows a schematic chromosome crossover diagram.
Then, the overall flow of the scenic driving route planning algorithm based on the modular factor algorithm is shown in fig. 1, and the main steps are as follows:
step 1, obtaining an initial population of a landscape road section by determining a search range and a landscape road section code; step 2, decoding the initial population to obtain a plurality of specific driving routes, and performing adaptability evaluation on each driving route;
step 3, improving each chromosome through chromosome selection and variation and cross operation based on local improvement to obtain a new scenic road section population;
and 4, circulating the step 2 and the step 3 until the iteration times specified by the user are reached, and outputting the landscape driving route at the moment as the optimal landscape driving route.
Claims (5)
1. A scenic driving route planning method using a modular factorial algorithm is characterized in that: obtaining an optimal scenic driving route meeting the requirements of a user by using a modular factor algorithm; the system comprises a scenic road section initial population generation module, a fitness evaluation module and a scenic road section new population generation module; the scenic road section initial population generation module screens out the range of effective scenic sections within a time budget range given by a user, and codes scenic road sections from a starting point to an end point into a chromosome through a chromosome coding process to obtain an initial scenic road section population; the fitness evaluation module is used for evaluating the fitness of chromosomes in the population and eliminating chromosomes which do not meet the requirements; the landscape road section new population generation module is used for improving each chromosome through chromosome selection and variation and cross operation based on local improvement to generate a landscape road section new population;
the scenic road section initial population generation module comprises the following steps: the method comprises the following steps: determining a search range; step two: landscape road section coding;
the determined search range is characterized in that a circle is drawn by taking a starting point as a circle center and taking the average speed from the starting point to the end point multiplied by the time budget as a radius, and the circle is the search range of the landscape road section;
the scenic section code comprises the following steps: the method comprises the following steps: drawing a circle by taking the starting point as the circle center and taking the average speed from the starting point to the end point multiplied by the time budget as a radius, and similarly drawing a circle by taking the end point as the circle center and the same radius, wherein the intersection area of the two circles is the effective scenic road section selection area; step two: sequencing the road sections of the effective scenic road section selection area according to the geographic distance from the starting point to obtain an effective scenic road section sequencing set; randomly selecting a scenery road section from the effective scenery road section sequencing set, and updating the starting point to the node in the scenery road section and the time budget; repeating the step one of the landscape road section codes; step three: if the effective scenic road section sequencing set is empty, outputting the scenic route at the moment as a coding scenic route, and ending coding; otherwise, circulating the step two of landscape section coding; finally outputting the encoded initial population of the scenic road section;
the fitness evaluation module is used for calculating the fitness of each chromosome according to the landscape value depending on the driving time and the time after decoding the initial population of the landscape road section into a specific driving route; the greater the route fitness value, the more excellent the chromosome, and the greater the probability of being retained in the subsequent chromosome selection process;
the scenic road section new population generation module comprises the following steps of: the method comprises the following steps: selecting a chromosome; step two: (ii) variation based on local improvement; step three: the chromosomes are crossed.
2. A scenic driving route planning method using a modulo-factor algorithm according to claim 1, characterized in that: the chromosome selection is selected by adopting a roulette wheel algorithm, firstly, the sum of the adaptive values of all chromosomes in the population is calculated, then the ratio of the adaptive value of each chromosome to the total adaptive value is calculated, finally, one chromosome is selected from the population by adopting the roulette wheel algorithm and is added into a new population, a new population with the same size as the population is obtained through multiple iterative selections, and the new population contains repeated chromosomes with higher adaptive values.
3. A scenic driving route planning method using a modulo-factor algorithm according to claim 1, characterized in that: the mutation operation based on local improvement is to replace one scenic road section randomly selected by another scenic road section within the selection range of the effective scenic road sections on the premise of not violating the time budget; mutation operation mutation probability P specified by user m And in [0,1 ]]Two parameter control of random value ρ m in range，P m When rho m, mutation is performed.
4. A scenic driving route planning method using a modulo-factor algorithm according to claim 1, characterized in that: the chromosome crossing operation is to select two chromosomes by using a gambling mechanism, divide the two chromosomes into two parts at the same position, and generate two new chromosomes by exchanging the second parts of the two chromosomes; crossover operation crossover probability P specified by user c And in [0,1 ]]Two parameter controls of random value ρ c in the range, P c ρ c, interleaving is performed.
5. A scenic driving route planning method using a modulo-factor algorithm according to claim 1, characterized in that: the modular factor algorithm comprises the following steps:
the method comprises the following steps: obtaining an initial population of the scenic road section by determining a search range and a scenic road section code;
step two: decoding the initial population to obtain a plurality of specific driving routes, and performing adaptability evaluation on each driving route;
step three: improving each chromosome through chromosome selection and variation and cross operation based on local improvement to obtain a new scenic road section population;
step four: and step two and step three of the cyclic modular factor algorithm, until the iteration times specified by the user are reached, outputting the landscape driving route at the moment as the optimal landscape driving route.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811454385.3A CN109631923B (en) | 2018-11-30 | 2018-11-30 | Scenic driving route planning method based on modular factorial algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811454385.3A CN109631923B (en) | 2018-11-30 | 2018-11-30 | Scenic driving route planning method based on modular factorial algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109631923A CN109631923A (en) | 2019-04-16 |
| CN109631923B true CN109631923B (en) | 2022-10-21 |
Family
ID=66070266
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811454385.3A Active CN109631923B (en) | 2018-11-30 | 2018-11-30 | Scenic driving route planning method based on modular factorial algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109631923B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113551685B (en) * | 2021-07-30 | 2022-08-26 | 重庆大学 | Multi-preference route planning method for double-time-varying road network |
| CN113819916B (en) * | 2021-08-27 | 2024-01-09 | 西安理工大学 | Travel route planning method based on cultural genetic algorithm |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593747B (en) * | 2013-11-07 | 2016-11-23 | 银江股份有限公司 | A kind of large scale customer point classification allocator based on meanshift classification |
| CN107122843A (en) * | 2017-03-13 | 2017-09-01 | 华南理工大学 | A kind of traveling salesman problem method for solving based on improved adaptive GA-IAGA |
| CN107909228B (en) * | 2017-12-23 | 2021-10-29 | 深圳大学 | Dynamic vehicle goods receiving and dispatching path planning method and device based on modular factor calculation |
-
2018
- 2018-11-30 CN CN201811454385.3A patent/CN109631923B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109631923A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shanmugasundaram et al. | Genetic algorithm-based road network design for optimising the vehicle travel distance | |
| CN106600147B (en) | Towards the multiple no-manned plane method for allocating tasks and device of decomposable asymmetric choice net task | |
| CN111178582B (en) | Logistics distribution optimization method based on improved genetic algorithm | |
| Singh et al. | New crossover operators for real coded genetic algorithm (RCGA) | |
| CN109631923B (en) | Scenic driving route planning method based on modular factorial algorithm | |
| Alves et al. | Using genetic algorithms to minimize the distance and balance the routes for the multiple traveling salesman problem | |
| CN109377048A (en) | A kind of comprehensive traffic network hub node selection method | |
| CN112381284B (en) | Improved genetic algorithm for multi-station path optimization of unmanned connection vehicle | |
| CN111695225A (en) | Bus composite complex network model and bus scheduling optimization method thereof | |
| JP2007240281A (en) | Area division round route search system, route search server, and area division round route search method | |
| US6052678A (en) | Problem solving operation apparatus using a state transition | |
| KR20230057558A (en) | Short-term traffic flow prediction method and device using deep learning | |
| CN102903038A (en) | Method and system for small object logistics distribution based on user track | |
| Yuan et al. | Improvement of multi-purpose travel route recommendation system based on genetic algorithm | |
| JP3792938B2 (en) | Navigation device | |
| Maervoet et al. | Tour suggestion for outdoor activities | |
| CN117041992A (en) | Method for realizing urban base station construction based on 5G technology and electronic equipment | |
| Fronita et al. | Comparison of genetic algorithm and hill climbing for shortest path optimization mapping | |
| Rodionov et al. | Framework for biologically inspired graph optimization | |
| Luo et al. | A new memetic algorithm to solve the stochastic tsp | |
| Chira et al. | Multi-objective evolutionary traffic assignment | |
| Vacic et al. | Vehicle routing problem with time windows | |
| Arunadevi et al. | Intelligent transport route planning using parallel genetic algorithms and MPI in high performance computing cluster | |
| Cahyani et al. | Traveling Salesman Problem Multi-destination Route Recommendation System Using Genetic Algorithm and Google Maps API | |
| CN117236534B (en) | Path generation method based on quantum ant colony algorithm |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |