CN117520670A - Automatic driving taxi parking site selection method and system - Google Patents
Automatic driving taxi parking site selection method and system Download PDFInfo
- Publication number
- CN117520670A CN117520670A CN202311556336.1A CN202311556336A CN117520670A CN 117520670 A CN117520670 A CN 117520670A CN 202311556336 A CN202311556336 A CN 202311556336A CN 117520670 A CN117520670 A CN 117520670A
- Authority
- CN
- China
- Prior art keywords
- parking
- points
- automatic driving
- point
- demand
- 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
- 238000010187 selection method Methods 0.000 title description 4
- 238000011160 research Methods 0.000 claims abstract description 55
- 230000029305 taxis Effects 0.000 claims abstract description 47
- 238000005457 optimization Methods 0.000 claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000011156 evaluation Methods 0.000 claims abstract description 33
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000010276 construction Methods 0.000 claims description 27
- 230000002776 aggregation Effects 0.000 claims description 7
- 238000004220 aggregation Methods 0.000 claims description 7
- 238000011835 investigation Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000006467 substitution reaction Methods 0.000 claims description 3
- SAZUGELZHZOXHB-UHFFFAOYSA-N acecarbromal Chemical compound CCC(Br)(CC)C(=O)NC(=O)NC(C)=O SAZUGELZHZOXHB-UHFFFAOYSA-N 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 230000002194 synthesizing effect Effects 0.000 claims description 2
- 238000011161 development Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Accounting & Taxation (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the application provides a method and a system for selecting parking sites of automatic taxis, wherein the method comprises the steps of predicting the demand of the automatic taxis in a research area based on questionnaire data and travel population data; preliminary site selection of automatic driving taxi parking sites is carried out based on POI data, and candidate parking sites in a research area are obtained; constructing a multi-target site selection optimization model, and carrying out model solving based on an NSGA-II algorithm to obtain a plurality of groups of non-unique Pareto solution sets; for each group of Pareto solution sets, respectively carrying out scoring calculation on evaluation index data of a plurality of groups of Pareto solution sets according to scoring standards; and (5) based on the obtained scoring result, optimizing the candidate parking points to obtain the final parking point. The implementation of the method can formulate a site selection strategy which is more suitable for the automatic driving of the taxis, and accelerate the large-scale application of propelling the automatic driving of the taxis.
Description
Technical Field
The application relates to the technical field of urban automatic driving taxi website site selection, in particular to an automatic driving taxi parking website selection method and system.
Background
In recent years, intelligent internet-connected automobiles have become a strategic direction of global automobile industry development in the context of a new technological revolution and industry revolution. With the strong construction of traffic and the development strategy of intelligent automobile innovation, the automatic driving industry in China is rapidly developed, and the large-scale application of the automatic driving automobile is more and more mature. At present, the automatic driving taxis are developed for normal business operation in cities such as Beijing, shanghai, wuhan and the like, and along with the continuous perfection of the technology, the operation scale is further expanded, and the automatic driving taxis are hopeful to become a main mode of future public transportation. Therefore, in order to improve the efficiency of the service system of the autopilot taxi and increase the standard degree of operation, it is necessary to study the supporting facilities required for development, namely, the autopilot taxi parking sites, so as to accelerate the development of the autopilot automobile industry.
At present, research in the field of automatic driving taxis mainly focuses on aspects of scheduling, reliability, public acceptance and the like, but the research on site selection of parking sites of the automatic driving taxis is relatively few. Although there are plentiful methods for site selection of shared automobile sites, the operation modes of shared automobiles and automatic driving taxis are different, the operation mode of shared automobiles is "people find" and the operation mode of automatic driving taxis is "people find" which can actively drive to passenger demand points, thus expanding service range. Therefore, for the special operation mode of "finding people" of automatically driving taxis, the service range and the number of parking places in the conventional site selection are required to be optimized. In addition, reasonable selection of parking sites can bring more convenient service experience. Placing the parking spots in high demand areas, such as business centers, residential areas, etc., can reduce user waiting time and travel distance, and can provide a more efficient ride experience.
Disclosure of Invention
The embodiment of the application aims at providing a method and a system for selecting parking sites of an automatic driving taxi, which can formulate an address selection strategy more suitable for the automatic driving taxi and accelerate the large-scale application of the propelling automatic driving taxi.
The embodiment of the application also provides a method for selecting the parking net points of the automatic driving taxis, which comprises the following steps:
s1, predicting the demand of automatically driving taxis in a research area based on questionnaire data and travel population data;
s2, preliminary site selection of automatic driving taxi parking sites is carried out based on POI data, and candidate parking sites in a research area are obtained;
s3, constructing a multi-target site selection optimization model, and carrying out model solving based on an NSGA-II algorithm to obtain a plurality of groups of non-unique Pareto solution sets;
s4, aiming at each group of Pareto solution sets, respectively carrying out scoring calculation on evaluation index data of a plurality of groups of Pareto solution sets according to scoring standards;
and S5, optimizing candidate parking points based on the obtained grading result to obtain the final parking point.
In a second aspect, the embodiment of the application further provides an automatic driving taxi parking site selection system, which comprises a demand prediction module, a preliminary site selection module, a site selection optimization model construction and solving module and a parking site optimization module, wherein:
the demand prediction module is used for predicting the demand of the automatic driving taxis in the research area based on the questionnaire data and the travel population data;
the preliminary site selection module is used for determining one type of site and a target type of site in the research area according to the POI data, and performing preliminary site selection of automatic driving taxi parking sites based on various sites to obtain candidate parking sites in the research area;
the site selection optimization model construction and solving module is used for constructing a multi-target site selection optimization model, and carrying out model solving based on an NSGA-II algorithm to obtain a plurality of groups of non-unique Pareto solution sets;
the model output analysis module is used for carrying out scoring calculation on the evaluation index data of a plurality of groups of Pareto solution sets according to scoring standards respectively for each group of Pareto solution sets;
and the parking spot optimization module is also used for optimizing the candidate parking spots based on the obtained scoring result.
In a third aspect, an embodiment of the present application further provides a storage medium, where the storage medium includes an autopilot taxi parking spot selection method program, where the autopilot taxi parking spot selection method program, when executed by a processor, implements the steps of an autopilot taxi parking spot selection method as described in any one of the foregoing embodiments.
As can be seen from the above, according to the method, the system and the storage medium for selecting the parking sites of the taxis for automatic driving provided by the embodiment of the application, on one hand, the demand of the taxis for automatic driving in the research area is predicted based on the questionnaire data and the travel population data, and the demand of the taxis for automatic driving in the research area can be estimated more accurately by acquiring the direct feedback of the travel demand and predicting based on the actual data, so that more reasonable decision making and planning are facilitated; on the other hand, according to POI data, one type of lattice point and a target type of lattice point in a research area are determined, and preliminary site selection of automatic driving taxi parking lattice points is carried out based on various lattice points to obtain candidate parking lattice points in the research area, so that repeated construction of lattice points arranged in unnecessary places is avoided, construction cost is saved, and resource utilization efficiency is improved; on the other hand, a multi-target site selection optimization model can be constructed, and model solving is carried out based on an NSGA-II algorithm to obtain a plurality of groups of non-unique Pareto solution sets; and (3) respectively carrying out scoring calculation on the evaluation index data of the plurality of groups of Pareto solution sets according to scoring standards aiming at each group of Pareto solution sets. Through scoring calculation, objective evaluation can be carried out on each group of Pareto solution sets, so that a decision maker can be helped to better know the quality degree of each solution set; finally, the candidate parking net points can be optimized based on the obtained grading result, so that the automatic driving taxi net points are more convenient and reasonable in position. The implementation of the method can formulate a site selection strategy which is more suitable for the automatic driving of the taxis, and accelerate the large-scale application of propelling the automatic driving of the taxis.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for selecting a parking spot of an autopilot according to an embodiment of the present application;
fig. 2 is a flowchart of an overall implementation of a method for selecting a parking spot of an autopilot according to an embodiment of the present application;
FIG. 3 (a) is a schematic diagram of a buffer method for dividing the service range of a network point;
FIG. 3 (b) is a schematic diagram of the isochronal method for dividing the service range of the network points;
fig. 4 is a schematic structural diagram of an automatic driving taxi parking spot selection system according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, fig. 1 is a flowchart of a method for selecting an autopilot parking spot according to some embodiments of the present application. The method comprises the following steps:
and S1, predicting the demand of the automatic driving taxis in the research area based on the questionnaire data and the travel population data.
And S2, performing preliminary site selection of the automatic driving taxi parking sites based on the POI data to obtain candidate parking sites in the research area.
And S3, constructing a multi-target site selection optimization model, and carrying out model solving based on an NSGA-II algorithm to obtain a plurality of groups of non-unique Pareto solution sets.
And S4, respectively carrying out scoring calculation on the evaluation index data of the plurality of groups of Pareto solution sets according to scoring standards aiming at each group of Pareto solution sets.
And step S5, optimizing the candidate parking points based on the obtained grading result to obtain the final parking point.
As can be seen from the above, according to the method for selecting the parking sites of the automatic driving taxis disclosed by the application, on one hand, the demand of the automatic driving taxis in a research area is predicted based on questionnaire data and travel population data, and the demand of the automatic driving taxis in the research area can be estimated more accurately by acquiring direct feedback on travel demands and predicting based on actual data, so that more reasonable decision making and planning are facilitated; on the other hand, according to POI data, one type of lattice point and a target type of lattice point in a research area are determined, and preliminary site selection of automatic driving taxi parking lattice points is carried out based on various lattice points to obtain candidate parking lattice points in the research area, so that repeated construction of lattice points arranged in unnecessary places is avoided, construction cost is saved, and resource utilization efficiency is improved; on the other hand, a multi-target site selection optimization model can be constructed, and model solving is carried out based on an NSGA-II algorithm to obtain a plurality of groups of non-unique Pareto solution sets; and (3) respectively carrying out scoring calculation on the evaluation index data of the plurality of groups of Pareto solution sets according to scoring standards aiming at each group of Pareto solution sets. Through scoring calculation, objective evaluation can be carried out on each group of Pareto solution sets, so that a decision maker can be helped to better know the quality degree of each solution set; finally, the candidate parking net points can be optimized based on the obtained grading result, so that the automatic driving taxi net points are more convenient and reasonable in position. The implementation of the method can formulate a site selection strategy which is more suitable for the automatic driving of the taxis, and accelerate the large-scale application of propelling the automatic driving of the taxis.
In one embodiment, in step S1, the predicting the demand of the automatic taxi in the research area based on the questionnaire data and the travel population data includes:
and S11, determining the proportion A of the automatic driving taxis to replace other existing travel modes and the peak travel number C in the research area based on the questionnaire data.
Specifically, the ratio A of the automatic taxi to replace other existing travel modes in the research area is the ratio of the number of people with the willingness to travel of the automatic taxi to the total travel times of various traffic modes.
Specifically, under the condition that the maximum number of people traveling in a certain time period is determined based on the questionnaire data, calculating the percentage B of the number of people traveling in the time period in the total number of people to be visited; and then determining the peak travel number C in the research range according to the product of the percentage B and the daily average travel quantity in the research range.
Step S12, based on the product of the proportion A and the peak trip number C, determining that the taxi is driven automatically to replace the trip number D in the peak period.
Specifically, the ratio A and the peak travel number C are multiplied to determine the ratio A and the peak travel number D by using the automatic driving taxi instead of the travel number D in the peak period.
And step S13, determining the demand quantity of converting the number of the taxi replaced travel persons into the common car based on the ratio of the number of the taxi replaced travel persons D and the average passenger capacity of the common car in the peak time.
And S14, based on the demand of the common car, predicting the demand of the automatic driving taxis in the research area according to the quantity substitution relation between the automatic driving taxis and the common car.
Specifically, according to the number substitution relation that 1 automatic driving taxi can substitute 11-14 common cars, in the current embodiment, the demand of automatic driving taxis in the research area is predicted based on the demand of common cars.
In the above embodiment, by collecting and analyzing the questionnaire data and travel population data, it is possible to obtain direct feedback on travel demands and make predictions based on actual data. The data-driven prediction method can more accurately estimate the demand of the automatic taxi in the research area, and is beneficial to making more reasonable decisions and planning.
In one embodiment, in step S2, the performing preliminary address selection of the parking site of the automatic driving taxi based on the POI data to obtain candidate parking sites in the research area includes:
step S21, determining a class of network points and an initial class of network points in a research area, wherein the class of network points comprise public parking lots and roadside parking lots, and the initial class of network points comprise hospitals, office places and commercial shopping places.
Specifically, a class of network points is generally referred to as primary network points or core network points, which are usually located in a city center or a primary business area, and have a larger scale and higher service capacity, including network points such as public parking lots, roadside parking lots and the like existing in the current infrastructure. The second-class net points are generally branch net points or branch net points, are generally distributed in various areas or surrounding areas of a city, have smaller scale and relatively weaker service capability, but have forward feedback on meeting the travel demands of residents.
Step S22, POI data of the initial class II network points are obtained, DBSCAN cluster analysis is conducted based on the POI data, and a cluster analysis result is obtained.
Specifically, referring to fig. 2, in the present embodiment, feature engineering is performed on the collected POI data, and the data is converted into features that can be used in a clustering algorithm. Common features include location longitude and latitude, category, coverage, etc. of the mesh point. The similarity between features may then be calculated using a distance metric method in a clustering algorithm. For the selection of the clustering algorithm, a proper clustering algorithm can be selected to perform the clustering analysis of the POIs according to specific application requirements.
Step S23, screening out the mesh points with the condition of setting parking positions in a preset range from the initial class II mesh points based on the clustering analysis result, and obtaining the target class II mesh points.
And step S24, synthesizing the first class network points and the second class network points to obtain candidate parking network points for automatically driving taxis in a research range.
It should be noted that the second type of dots have complementary and optimized effects on the first type of dots. After clustering is performed by adopting a clustering method, the current embodiment further screens out points with the condition of setting parking positions within a range of 500 meters around the POI, and takes the points as the second class of network points.
In the embodiment, the optimal positions of the first-class net point and the second-class net point are determined through POI data analysis, repeated construction of arranging the net points in unnecessary places is avoided, construction cost is saved, and resource utilization efficiency is improved.
In one embodiment, in step S3, the multi-objective site selection optimization model is constructed by:
step S31, dividing the research area into a plurality of plots.
Step S32, for each plot, determining a location influence coefficient Y according to the position of the plot in the whole research area and the comprehensive aggregation scale of the plot itself m 。
Specifically, in the present embodiment, firstly, the study area is considered to be divided into a plurality of plots, and then the zone potential is calculated according to the position of the plots in the whole study area and the comprehensive aggregation scale of the plots, and the corresponding zone potential influence coefficient Y is obtained m 。
Step S33, based on the location influence coefficient Y m And correcting the vehicle parking quantity of each network point to obtain the number of parking points of the candidate parking network point.
Specifically, the average number of parking positions at a given area(empirically, 3) will be based on the formula:and correcting the number of berths to obtain the berths of the target parking network.
And step S34, acquiring an equal time circle of the candidate parking network points, and determining the demand points contained in the network point service range based on the equal time circle.
It should be noted that, the obtaining of the isochrone is the basis for establishing the multi-objective function, which can help to determine which demand points are included in the network point service range, so as to ensure that each model assumption and constraint conditions are satisfied.
Step S35, based on the requirement points, cost, coverage population and requirement of the distance from the requirement points to the candidate points, an objective function covered by the multi-objective site selection optimization model and a corresponding constraint condition are established.
Specifically, the model assumptions considered in the current embodiment include: 1) The number of vehicles parked at each website is equal to the berth capacity of the website; 2) The distance from the demand point to the candidate point and the distance between the candidate points are all shortest distances based on path planning; 3) Public parking lots in the area and roadside parking lots can be used as network points; 4) Each network point is provided with the same number of charging piles as the capacity value; 5) Costs include land renting costs and charging pile construction costs, and other costs are not calculated. The specific form of the objective function and the constraint condition may refer to the following embodiments, and is not described in detail.
In the embodiment, the construction of the multi-target site selection optimization model can provide comprehensive, scientific and systematic site selection decision support, so that the site selection decision is more comprehensive and reasonable, the optimal allocation of resources is realized, the risk is reduced, and the sustainable development is promoted.
In one embodiment, in step S32, the location influence coefficient Y is determined according to the location of the plot in the whole investigation region and the comprehensive aggregation scale of the plot itself m Comprising:
step S321, according to the position of the plot in the whole research area and the comprehensive aggregation scale of the plot, performing a first zone potential LP of the plot m by the following formula m Second zone potential LP of standard plot o o Is calculated by (1):
wherein k represents a preset scaling factor, a m Representing the location of plot m throughout the investigation region, a o Representing the location of a standard plot o within the entire investigation region; alpha represents the elastic coefficient contributing to the increase in the zone potential; q i Representing the aggregate scale quality factor, i e { m, o }; s is(s) i Representing the aggregate rule modulus factor, i ε { m, o }; beta represents the elastic coefficient of the composite aggregate scale factor contribution to the increase in zone potential, reflecting the aggregate and neighbor effects.
Step S322, based on the first zone potential LP m And the second zone potential LP o The ratio between the two is used for determining the location of the m land blockInfluence coefficient Y m 。
In the embodiment, the location influence coefficient is determined by comprehensively considering the factors such as the position, the surrounding environment and the resource condition of the land, so that the land utilization of different types can be reasonably arranged, and the utilization efficiency and the economic benefit of the land are improved.
In one embodiment, in step S34, the obtaining the candidate parking spot isochrone includes: the introduction of an isochrone drawn based on the actual road network and path planning represents the service range of each candidate parking spot.
The specific acquisition method of the equal time period is acquired by using an API interface provided by a Mapbox.
In the above embodiment, the isochrone circle based on the actual road network and the path planning is introduced to represent the service range of each candidate parking site. Based on fig. 3 (a) and fig. 3 (b), compared with the traditional buffer method, the isochronous circle method adopted in the application is specifically based on actual road network and path planning, and can improve the accurate description of the service range of the candidate parking network point while ensuring the accuracy and the practicability of the service range. Therefore, the technical scheme of the application has the advantage of defining the service range more accurately in the site selection of the candidate parking sites.
In one embodiment, in step S34, the objective function includes: the first optimization target with the largest coverage requirement points is met:the second optimization objective with the minimum construction cost is satisfied: />Meets a third optimization target with the largest population demand: />The fourth optimization target with the minimum distance from the demand point to the candidate point is met: />
The constraint conditions include: first constraint for constraining the range of dot count:a second constraint that allows each demand point to be served by at least one mesh point: />A third constraint that makes it impossible to get a distance between two dots smaller than a certain distance: />Wherein y is j1 Indicating whether the candidate point 1 is selected as a net point, if so, taking 1, otherwise taking 0; y is j2 Indicating whether the candidate point 2 is selected as a net point, if so, taking 1, otherwise taking 0; fourth constraint for constraining the total cost of site construction: y is j .h j The weight is less than or equal to L; fifth constraint for constraining total spot count range of a spot: />
Wherein,j is a candidate parking net point, J is a set of candidate parking net points, I is a demand point, and I is a set of demand points; h is a j For the construction cost of candidate parking net points, p i For the population of the block where the demand point i is located, v j The number of parked vehicles for the candidate point d ij For the distance d between the demand point i and the candidate point j min For the minimum distance between two different dots, +.>Is the distance between two different dots; n (N) min N is the minimum value of the number of the dots max For the maximum number of net points, L is the maximum construction cost, V min Is the total number of parking spaces of the net pointMinimum value, V max The maximum value of the total parking space number of the net points.
In one embodiment, in step S4, for each Pareto solution set, scoring calculation is performed on the evaluation index data of the multiple Pareto solution sets according to the scoring criteria, including:
and S41, selecting a plurality of evaluation index data for evaluating the Pareto optimal solution set, wherein the evaluation index data comprises cost, number of dots, number of road side network points, overlapping area of candidate point service ranges and total berth supply number.
Specifically, in the current embodiment, multiple target site selection is adopted, NSGA-II algorithm is used for solving to obtain a Pareto solution set, and the required steps include:
step1: the initial population with the size of set_num is randomly generated, and after non-dominant sorting, selection, crossover and mutation, the offspring population is generated.
Step2: the two populations are combined together to form a population of size S.
Step3: and (3) carrying out rapid non-dominant sorting based on the population constructed by Step2, carrying out crowding degree calculation on individuals in each non-dominant layer, and selecting proper individuals to form a new parent population according to the non-dominant relationship and the crowding degree of the individuals.
Step4: generating a new offspring population through basic operation of a genetic algorithm, combining the offspring population with the offspring population to form a new population, and repeating the operation until the condition of ending the program is met.
It should be further noted that, in the present embodiment, the evaluation index data may be referred to the following table 1:
table 1 evaluation index data
Wherein, the groups 1 to 10 correspond to the 1 st group to the 10 th group Pareto solution sets. Each Pareto solution set may calculate a corresponding index value according to 5 evaluation indexes illustrated in table 1.
It should be noted that, the above 5 evaluation indexes are all established at the level of operators, and are specifically used for reflecting the merits of the network points. The road side network points are used as positive evaluation indexes, and the cost, the number of network points, the overlapping area of candidate point service ranges and the total berth supply number are used as negative evaluation indexes. The current practice is to use positive and negative evaluation indicators to achieve a comprehensive assessment of the problem or solution. Positive indicators may measure positive contributions to the target, while negative indicators may measure negative effects on the target. Therefore, the evaluation result is more accurate and comprehensive, and the decision maker is facilitated to make decisions more in accordance with actual situations and target requirements.
Step S42, according to the index types, the scoring standard of each index type is represented by a corresponding numerical range.
In particular, the scoring criteria may be referred to in table 2 below:
table 2 scoring criteria
It should be noted that, for each evaluation index, after statistics to obtain the corresponding index value, the numerical range in which the index value is located is determined according to the above-mentioned evaluation criterion; and then, according to the mapping relation between the numerical range and the corresponding scoring interval, performing index scoring based on the mapped scoring interval.
For example, for group 1, after statistically determining the cost index value 229, since the value 229 is in the range of "(225, 240)", further, index scoring may be performed in the scoring interval of (80, 100) according to the scoring criteria shown in table 2, with the positive index value being higher and the negative index being the opposite, the scoring calculation is 100- [ (240-225)/(100-80) ×229-225 ].
And step S43, scoring each evaluation index according to the scoring standard for each group of Pareto solution sets to obtain a corresponding scoring result.
Specifically, for each Pareto solution set, in the current embodiment, the index score of each index is determined first; and then, carrying out average value calculation based on the obtained index scores, and finally, taking the obtained average value scores as scoring results.
In one embodiment, in step S5, the selecting candidate parking points based on the obtained scoring result to obtain the final parking point includes:
step S51, for each Pareto solution set, determining a score mean value based on the corresponding plurality of score results.
And S52, comparing the obtained score average values, and taking the website address scheme corresponding to the group of Pareto solutions with the highest score value as a final address scheme to finish the optimization of the candidate parking websites.
Based on the steps S51 to S53, it should be noted that, for each group of Pareto solutions, the score is calculated according to the scoring criteria illustrated in table 2 in the present embodiment, and the average value obtained based on the scores of the 5 indexes is used as the final selection criterion. Then, only the group with the highest score is selected as the addressing scheme of the final parking site (the addressing scheme is shown in table 3, and the group with the highest score is selected in the present embodiment, namely, the first group of schemes is used as the addressing scheme of the final parking site).
Table 3 alternative sets of addressing schemes
In yet another embodiment, in the current embodiment, automatic taxi parking site model verification is further performed, and specifically includes the following steps:
(1) And clearly establishing a dispatching line before and after the automatic driving taxi parking site.
(2) And calculating the total travel time of the vehicle before and after the establishment of the parking network points.
Wherein, because the network point position and the demand point position have been determined, the distance between the two points is calculated based on the road network, and the travel time of the vehicle is calculated with the vehicle speed set to a fixed value. And finally, adding the travel time of each vehicle dispatch to obtain the total travel time of the vehicle.
(3) And comparing the total running time of the vehicle in the mode of dispatching after the automatic driving taxi parking site model is established with the total running time of the vehicle in the mode of dispatching before the automatic driving taxi parking site model is established, and calculating the percentage capable of improving the total running time.
Wherein the percentage of increase in operating time = (total travel time of vehicles before the website established-total travel time of vehicles after the website established)/total travel time of vehicles before the website established.
In the embodiment, the candidate parking net points are optimized, so that the automatic driving taxi net points are more convenient and reasonable in position. This will reduce passenger walking distance and latency, improve passenger's travel experience, provide more convenient and efficient travel service.
Referring to fig. 4, the system disclosed in the application for selecting a parking site of an automatic driving taxi includes a demand prediction module, a preliminary site selection module, a site selection optimization model construction and solving module, and a parking site optimization module, wherein:
the demand prediction module is used for predicting the demand of the automatic driving taxis in the research area based on the questionnaire data and the travel population data.
And the preliminary site selection module is used for carrying out preliminary site selection of the automatic driving taxi parking sites based on the POI data to obtain candidate parking sites in the research area.
The site selection optimization model construction and solving module is used for constructing a multi-target site selection optimization model, and carrying out model solving based on an NSGA-II algorithm to obtain a plurality of groups of non-unique Pareto solution sets.
And the parking site optimization module is used for carrying out scoring calculation on each group of Pareto solution sets according to the determination of the evaluation index data of the plurality of groups of Pareto solution sets.
And the parking spot optimization module is also used for optimizing the candidate parking spots based on the obtained scoring result.
In one embodiment, the modules in the system are further configured to perform the method of any of the alternative implementations of the above embodiments.
As can be seen from the above, according to the system for selecting the parking sites of the automatic driving taxis disclosed by the application, on one hand, the demand of the automatic driving taxis in a research area is predicted based on questionnaire data and travel population data, and the demand of the automatic driving taxis in the research area can be estimated more accurately by acquiring direct feedback on travel demands and predicting based on actual data, so that more reasonable decision making and planning are facilitated; on the other hand, according to POI data, one type of lattice point and a target type of lattice point in a research area are determined, and preliminary site selection of automatic driving taxi parking lattice points is carried out based on various lattice points to obtain candidate parking lattice points in the research area, so that repeated construction of lattice points arranged in unnecessary places is avoided, construction cost is saved, and resource utilization efficiency is improved; on the other hand, a multi-target site selection optimization model can be constructed, and model solving is carried out based on an NSGA-II algorithm to obtain a plurality of groups of non-unique Pareto solution sets; and (3) respectively carrying out scoring calculation on the evaluation index data of the plurality of groups of Pareto solution sets according to scoring standards aiming at each group of Pareto solution sets. Through scoring calculation, objective evaluation can be carried out on each group of Pareto solution sets, so that a decision maker can be helped to better know the quality degree of each solution set; finally, the candidate parking net points can be optimized based on the obtained grading result, so that the automatic driving taxi net points are more convenient and reasonable in position. The implementation of the method can formulate a site selection strategy which is more suitable for the automatic driving of the taxis, and accelerate the large-scale application of propelling the automatic driving of the taxis.
The present application provides a storage medium that, when executed by a processor, performs the method of any of the alternative implementations of the above embodiments. The storage medium may be implemented by any type of volatile or nonvolatile Memory device or combination thereof, such as static random access Memory (Static Random Access Memory, SRAM), electrically erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
According to the storage medium, on one hand, the demand of the automatic driving taxis in the research area is predicted based on the questionnaire data and the travel population data, and the demand of the automatic driving taxis in the research area can be estimated more accurately by acquiring the direct feedback of the travel demand and predicting based on the actual data, so that more reasonable decision making and planning are facilitated; on the other hand, according to POI data, one type of lattice point and a target type of lattice point in a research area are determined, and preliminary site selection of automatic driving taxi parking lattice points is carried out based on various lattice points to obtain candidate parking lattice points in the research area, so that repeated construction of lattice points arranged in unnecessary places is avoided, construction cost is saved, and resource utilization efficiency is improved; on the other hand, a multi-target site selection optimization model can be constructed, and model solving is carried out based on an NSGA-II algorithm to obtain a plurality of groups of non-unique Pareto solution sets; and (3) respectively carrying out scoring calculation on the evaluation index data of the plurality of groups of Pareto solution sets according to scoring standards aiming at each group of Pareto solution sets. Through scoring calculation, objective evaluation can be carried out on each group of Pareto solution sets, so that a decision maker can be helped to better know the quality degree of each solution set; finally, the candidate parking net points can be optimized based on the obtained grading result, so that the automatic driving taxi net points are more convenient and reasonable in position. The implementation of the method can formulate a site selection strategy which is more suitable for the automatic driving of the taxis, and accelerate the large-scale application of propelling the automatic driving of the taxis.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
Further, the units described as separate units may or may not be physically separate, and units displayed as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
Furthermore, functional modules in various embodiments of the present application may be integrated together to form a single portion, or each module may exist alone, or two or more modules may be integrated to form a single portion.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application, and various modifications and variations may be suggested to one skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (10)
1. The method for selecting the automatic driving taxi parking network point is characterized by comprising the following steps of:
s1, predicting the demand of automatically driving taxis in a research area based on questionnaire data and travel population data;
s2, preliminary site selection of automatic driving taxi parking sites is carried out based on POI data, and candidate parking sites in a research area are obtained;
s3, constructing a multi-target site selection optimization model, and carrying out model solving based on an NSGA-II algorithm to obtain a plurality of groups of non-unique Pareto solution sets;
s4, aiming at each group of Pareto solution sets, respectively carrying out scoring calculation on evaluation index data of a plurality of groups of Pareto solution sets according to scoring standards;
and S5, optimizing candidate parking points based on the obtained grading result to obtain the final parking point.
2. The method according to claim 1, wherein in step S1, the predicting the demand for automatically driving taxis in the research area based on the questionnaire data and the travel population data includes:
s11, determining the proportion A of the automatic driving taxis to replace other existing travel modes and the peak travel number C in a research area based on the questionnaire data;
s12, determining that the taxi is driven automatically to replace the travel number D in the peak period based on the product of the proportion A and the peak travel number C;
s13, determining the demand quantity of the automatic driving taxi for converting the number of the substituted travel persons into the common car based on the ratio of the number of the substituted travel persons D of the automatic driving taxi to the average passenger capacity of the common car in the peak time;
s14, based on the demand of the common car, predicting the demand of the automatic driving taxis in the research area according to the quantity substitution relation between the automatic driving taxis and the common car.
3. The method according to claim 1, wherein in step S2, the preliminary site selection of the autopilot parking site based on the POI data is performed to obtain candidate parking sites in the research area, including:
s21, determining a first class of network points and an initial second class of network points in a research area, wherein the first class of network points comprise public parking lots and road side parking lots, and the initial second class of network points comprise hospitals, office places and commercial shopping places;
s22, acquiring POI data of the initial class II network points, and performing DBSCAN cluster analysis based on the POI data to obtain a cluster analysis result;
s23, screening out the mesh points with the condition of setting parking positions in a preset range from the initial class II mesh points based on the clustering analysis result to obtain target class II mesh points;
s24, synthesizing the first class network points and the second class network points to obtain candidate parking network points for automatically driving taxis in the research range.
4. The method according to claim 1, wherein in step S3, the multi-objective site-selection optimization model is constructed by:
s31, dividing a research area into a plurality of plots;
s32, determining a location influence coefficient Y according to the position of each land block in the whole research area and the comprehensive aggregation scale of the land block per se m ；
S33, based on the location influence coefficient Y m Correcting the number of vehicles parked at each website to obtain the number of parking spots of the candidate parking website;
s34, acquiring an equal time circle of a candidate parking network point, and determining a demand point contained in a network point service range based on the equal time circle;
s35, based on the requirement points, cost, coverage population and the requirement of the distance from the requirement points to the candidate points of the target coverage, establishing an objective function covered by the multi-target site selection optimization model and corresponding constraint conditions.
5. The method according to claim 4, wherein in step S32, the location influence coefficient Y is determined based on the location of the plots in the entire study area and the integrated aggregate size of the plots themselves m Comprising:
s321, according to the land blockThe location within the whole investigation region, and the integrated aggregate size of the plot itself, the first plot potential LP of plot m is performed by the following formula m Second zone potential LP of standard plot o o Is calculated by (1):
wherein k represents a preset scaling factor, a m Representing the location of plot m throughout the investigation region, a o Representing the location of a standard plot o within the entire investigation region; alpha represents the elastic coefficient contributing to the increase in the zone potential; q i Representing the aggregate scale quality factor, i e { m, o }; s is(s) i Representing the aggregate rule modulus factor, i ε { m, o }; beta represents the elastic coefficient of the comprehensive aggregation scale factor contributing to the zone potential growth and is used for reflecting the aggregation and the neighbor effect;
s322, based on the first zone potential LP m And the second zone potential LP o The ratio between the two is used for determining the zone bit influence coefficient Y of the m land block m 。
6. The method of claim 4, wherein in step S34, the obtaining the candidate parking spot isochrones includes:
the introduction of an isochrone drawn based on the actual road network and path planning represents the service range of each candidate parking spot.
7. The method according to claim 4, wherein in step S34, the objective function includes: the first optimization target with the largest coverage requirement points is met:the second optimization objective with the minimum construction cost is satisfied:meets a third optimization target with the largest population demand: />The fourth optimization target with the minimum distance from the demand point to the candidate point is met: />
The constraint conditions include: first constraint for constraining the range of dot count:a second constraint that allows each demand point to be served by at least one mesh point: />A third constraint that makes it impossible to get a distance between two dots smaller than a certain distance: y is j1 .y j2 .d min ≤d j1j2 Wherein y is j1 Indicating whether the candidate point 1 is selected as a net point, if so, taking 1, otherwise taking 0; y is j2 Indicating whether the candidate point 2 is selected as a net point, if so, taking 1, otherwise taking 0; fourth constraint for constraining the total cost of site construction: y is j .h j The weight is less than or equal to L; fifth constraint for constraining total spot count range of a spot: />
Wherein,j is a candidate parking net point, J is a set of candidate parking net points, I is a demand point, and I is a set of demand points; h is a j For the construction cost of candidate parking net points, p i For the population of the block where the demand point i is located, v j The number of parked vehicles for the candidate point d ij For the distance between the demand point i and the candidate point jSeparation, d min For the minimum distance between two different dots, +.>Is the distance between two different dots; n (N) min N is the minimum value of the number of the dots max For the maximum number of net points, L is the maximum construction cost, V min Is the minimum value of the total parking space number of the net points, V max The maximum value of the total parking space number of the net points.
8. The method according to claim 1, wherein in step S4, the scoring the evaluation index data of the Pareto solution sets for each group according to the scoring criteria, includes:
s41, selecting a plurality of evaluation index data for evaluating a Pareto optimal solution set, wherein the evaluation index data comprises cost, number of dots, number of road side network points, overlapping area of candidate point service ranges and total berth supply number;
s42, representing the scoring standard of each index type by a corresponding numerical range according to the index type;
s43, scoring each evaluation index according to the scoring standard for each group of Pareto solution sets to obtain a corresponding scoring result.
9. The method according to claim 1, wherein in step S5, the selecting candidate parking points based on the obtained scoring result to obtain a final parking point includes:
s51, determining a scoring mean value based on a plurality of scoring results for each group of Pareto solution sets;
s52, comparing the obtained score average values, and taking the net point address scheme corresponding to the group of Pareto solutions with the highest score value as a final address scheme to finish the optimization of the candidate parking net points.
10. The utility model provides an automatic driving taxi parks site selection system which characterized in that, the system includes demand prediction module, preliminary addressing module, addressing optimization model construction and solving module, parks site preference module, wherein:
the demand prediction module is used for predicting the demand of the automatic driving taxis in the research area based on the questionnaire data and the travel population data;
the preliminary site selection module is used for carrying out preliminary site selection of automatic driving taxi parking sites based on POI data to obtain candidate parking sites in a research area;
the site selection optimization model construction and solving module is used for constructing a multi-target site selection optimization model, and carrying out model solving based on an NSGA-II algorithm to obtain a plurality of groups of non-unique Pareto solution sets;
the parking site optimization module is used for carrying out scoring calculation on evaluation index data of a plurality of groups of Pareto solution sets according to scoring standards respectively for each group of Pareto solution sets;
and the parking spot optimization module is also used for optimizing the candidate parking spots based on the obtained scoring result to obtain the final parking spot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311556336.1A CN117520670A (en) | 2023-11-17 | 2023-11-17 | Automatic driving taxi parking site selection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311556336.1A CN117520670A (en) | 2023-11-17 | 2023-11-17 | Automatic driving taxi parking site selection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117520670A true CN117520670A (en) | 2024-02-06 |
Family
ID=89760454
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311556336.1A Pending CN117520670A (en) | 2023-11-17 | 2023-11-17 | Automatic driving taxi parking site selection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117520670A (en) |
-
2023
- 2023-11-17 CN CN202311556336.1A patent/CN117520670A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107316098B (en) | Automobile leasing point addressing method based on user behavior analysis | |
| CN104318758B (en) | Based on multi-level multimodal Public transport network planning method | |
| CN110288212B (en) | Improved MOPSO-based electric taxi newly-built charging station site selection method | |
| CN110134865B (en) | Commuting passenger social contact recommendation method and platform based on urban public transport trip big data | |
| CN104809112A (en) | Method for comprehensively evaluating urban public transportation development level based on multiple data | |
| CN109840272B (en) | Method for predicting user demand of shared electric automobile station | |
| Zhu et al. | Solar photovoltaic generation for charging shared electric scooters | |
| CN116720997A (en) | Bus route evaluation system and optimization method based on big data analysis | |
| Rowe et al. | Evaluating the impact of transit service on parking demand and requirements | |
| CN114092176A (en) | Urban commuting regular bus planning method based on bus | |
| CN114358386A (en) | Double-trip-mode ride-sharing site generation method based on reserved trip demand | |
| CN113947245B (en) | Multi-passenger multi-driver ride sharing matching method and system based on order accumulation | |
| CN116797126A (en) | Rural terminal logistics site selection-path planning method based on double-layer planning | |
| CN117520670A (en) | Automatic driving taxi parking site selection method and system | |
| CN110533215A (en) | A kind of taxi of cruising based on GPS data seeks objective behavior prediction method | |
| CN113191601B (en) | Road traffic technology monitoring equipment layout scheme evaluation method | |
| CN115186969A (en) | Multi-guide particle swarm multi-target carpooling problem solving optimization method with variable neighborhood search | |
| CN115330043A (en) | Site selection planning method and system for urban charging station | |
| Li et al. | Evaluation of joint development of park and ride and transit-oriented development near metro stations in Chengdu, China | |
| Wang et al. | A dynamic grid-based algorithm for taxi ridesharing in multiple road condition | |
| Mamdoohi et al. | An Analysis of Public Transit Connectivity Index in Tehran. The Case Study: Tehran Multi-Modal Transit Network | |
| Ma et al. | A hierarchical public bicycle dispatching policy for dynamic demand | |
| CN117196693B (en) | Logistics demand prediction method for urban underground traffic | |
| CN114566037B (en) | Flexible bus multi-vehicle type fleet configuration method based on multi-source data | |
| CN117252404B (en) | Method and system for measuring and calculating population and post scale of city updating unit |
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 |