WO2023281756A1 - Traffic simulation device, traffic simulation method, and traffic simulation program - Google Patents

Traffic simulation device, traffic simulation method, and traffic simulation program Download PDF

Info

Publication number
WO2023281756A1
WO2023281756A1 PCT/JP2021/026041 JP2021026041W WO2023281756A1 WO 2023281756 A1 WO2023281756 A1 WO 2023281756A1 JP 2021026041 W JP2021026041 W JP 2021026041W WO 2023281756 A1 WO2023281756 A1 WO 2023281756A1
Authority
WO
WIPO (PCT)
Prior art keywords
traffic simulation
parameters
evaluation function
traffic
parameter space
Prior art date
Application number
PCT/JP2021/026041
Other languages
French (fr)
Japanese (ja)
Inventor
宗之 川谷
賢士 小宮
淳 磯村
雅 高木
Original Assignee
日本電信電話株式会社
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 日本電信電話株式会社 filed Critical 日本電信電話株式会社
Priority to PCT/JP2021/026041 priority Critical patent/WO2023281756A1/en
Publication of WO2023281756A1 publication Critical patent/WO2023281756A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles

Definitions

  • the present invention relates to a traffic simulation device, a traffic simulation method, and a traffic simulation program.
  • Non-Patent Document 1 there is known a technique for simulating traffic using a prediction model (see Non-Patent Document 1).
  • the present invention has been made in view of the above, and it is an object of the present invention to efficiently determine optimum parameters and perform highly accurate simulations in simulations using prediction models related to traffic.
  • the traffic simulation apparatus determines parameters of roads having a priority level equal to or higher than a predetermined threshold among roads connected to a road including a section to be simulated.
  • a selection unit that selects as a parameter space of the evaluation function, a selection unit that selects starting point candidates in the parameter space of the selected evaluation function, and moves a point in the parameter space from each selected starting point candidate to correspond and a search unit that searches for a combination of parameters that gives the highest evaluation function value.
  • FIG. 1 is a diagram for explaining an outline of a traffic simulation device according to this embodiment.
  • FIG. 2 is a diagram for explaining the outline of the traffic simulation device according to this embodiment.
  • FIG. 3 is a schematic diagram illustrating a schematic configuration of the traffic simulation device according to this embodiment.
  • FIG. 4 is a diagram for explaining the processing of the selection unit;
  • FIG. 5 is a diagram for explaining the processing of the selection unit and the search unit;
  • FIG. 6 is a flow chart showing a traffic simulation processing procedure.
  • FIG. 7 is a diagram showing an example of a computer that executes a traffic simulation program.
  • FIG.1 and FIG.2 is a figure for demonstrating the outline
  • a method of successively searching for optimal parameters has been proposed in simulations using predictive models such as traffic congestion prediction.
  • the traffic simulation apparatus of this embodiment reduces the amount of calculation and determines (tunes) the optimum parameters by estimating parameters that greatly affect the accuracy of the prediction model.
  • the traffic simulation apparatus first gives priority to road parameters that have a large effect on the target section to be reproduced in the simulation, which is enclosed by the dashed line, and performs subsequent tuning. set to target.
  • tuning targets are limited to the parameters of the roads connected to the road including the target section.
  • a traffic simulation is generally called a chaotic system, and as shown in Fig. 2, the entire parameter space has points with local continuity and points with discontinuity as indicated by the dashed lines. are mixed. For example, a discontinuity occurs when a singular point is exceeded such that the road becomes more congested as the green light time becomes shorter, and the detour takes less time.
  • the traffic simulation device searches for the point where the evaluation function value of the prediction model is the highest in each range of local continuity of the parameter space, and estimates that the target section has a large impact in the entire parameter space. Tune to the required parameters.
  • the traffic simulation device can efficiently determine the optimal parameters for traffic simulation using the predictive model by reducing the amount of calculation, and perform highly accurate traffic simulation.
  • FIG. 3 is a schematic diagram illustrating a schematic configuration of the traffic simulation device according to this embodiment.
  • the traffic simulation device 10 of the present embodiment is implemented by a general-purpose computer such as a personal computer, and includes an input unit 11, an output unit 12, a communication control unit 13, a storage unit 14, and a control unit 15. .
  • the input unit 11 is implemented using input devices such as a keyboard and a mouse, and inputs various instruction information such as processing start to the control unit 15 in response to input operations by the operator.
  • the output unit 12 is implemented by a display device such as a liquid crystal display, a printer, or the like. For example, the output unit 12 displays the results of traffic simulation processing, which will be described later.
  • the communication control unit 13 is realized by a NIC (Network Interface Card) or the like, and controls communication between an external device and the control unit 15 via an electrical communication line such as a LAN (Local Area Network) or the Internet.
  • the communication control unit 13 controls communication between the control unit 15 and a management device that manages various information such as map data, traffic signals, intersections, traffic volume, vehicle speed, and vehicle length of each road to be processed. do.
  • the storage unit 14 is implemented by semiconductor memory devices such as RAM (Random Access Memory) and flash memory, or storage devices such as hard disks and optical disks.
  • a processing program for operating the traffic simulation device 10 data used during execution of the processing program, and the like are stored in advance, or are temporarily stored each time processing is performed.
  • the storage unit 14 may be configured to communicate with the control unit 15 via the communication control unit 13 .
  • the storage unit 14 acquires and stores in advance various information such as map data, traffic lights, intersections, traffic volume, vehicle speed, and vehicle length of each road to be processed, which are necessary for the traffic simulation process described later. good too.
  • the storage unit 14 also stores a prediction model whose parameters are determined in a traffic simulation process, which will be described later.
  • the control unit 15 is implemented using a CPU (Central Processing Unit) or the like, and executes a processing program stored in memory. Thereby, the control unit 15 functions as an acquisition unit 15a, a selection unit 15b, a selection unit 15c, a search unit 15d, and a calculation unit 15e, as illustrated in FIG.
  • a CPU Central Processing Unit
  • the control unit 15 functions as an acquisition unit 15a, a selection unit 15b, a selection unit 15c, a search unit 15d, and a calculation unit 15e, as illustrated in FIG.
  • these functional units may be implemented in different hardware, respectively or partially.
  • the calculator 15e may be implemented in a device different from the other functional units.
  • the control unit 15 may include other functional units.
  • the acquisition unit 15a acquires information such as intersections and traffic lights on each road on the map, cross-sectional traffic volume, vehicle speed, and length of congested areas.
  • the acquisition unit 15a acquires these pieces of information via the input unit 11 or via the communication control unit 13 from a management device or the like.
  • the acquisition unit 15a may cause the storage unit 14 to store the acquired information.
  • the selection unit 15b selects parameters of roads having a priority level equal to or higher than a predetermined threshold among the roads connected to the road including the target section of the simulation as the parameter space of the evaluation function. Specifically, the selection unit 15b selects the parameters of the road with higher priority for a road closer to the target section.
  • FIG. 4 is a diagram for explaining the processing of the selection unit.
  • the selection unit 15b adds a priority index to each road in order of proximity to the road including the target section, and assigns a priority index that is equal to or less than a predetermined threshold as a priority that increases in descending order of the priority index. road. Then, the selection unit 15b selects the parameters of the selected road as the parameter space of the evaluation function. For example, the selection unit 15b determines the evaluation function of the prediction result of the prediction model using each selected parameter by RMSE (Root Mean Squared Error) or the like.
  • RMSE Root Mean Squared Error
  • the road that includes the target section has a priority index of 1.0, and the road that intersects with this road has a priority index of 1.5.
  • a road that intersects with a road with a priority index of 1.5 that is, a road that is one hop ahead from a road with a priority index of 1.0 that includes the target section is assigned a priority index of 2.0.
  • roads whose priority index is equal to or less than a predetermined threshold that is, roads closer to the road containing the target section are selected with higher priority. , train length, etc. are selected as parameters.
  • the selection unit 15c selects a starting point candidate in the parameter space of the selected evaluation function. For example, the selection unit 15c selects a starting point candidate using a random number. Alternatively, the selection unit 15c selects a starting point candidate that can cross a traffic-related singularity using an orthogonal array.
  • FIG. 5 is a diagram for explaining the processing of the selection unit and search unit.
  • the selection unit 15c selects a plurality of starting point candidates in the parameter space, as circled in FIG.
  • the selection unit 15c may select a starting point candidate using a random number, or may use an orthogonal table.
  • an orthogonal table for example, a list of points that can cross singularities such as red to green ratios of traffic lights of 7.5 to 2.5, 5 to 5, and 2.5 to 7.5 is created in advance, and the selection unit 15c selects a point that can cross the singular point from the orthogonal array as the starting point candidate.
  • the searching unit 15d searches for a combination of parameters with the highest corresponding evaluation function value by moving points in the parameter space from each of the selected starting point candidates. For example, the search unit 15d uses simulated annealing, GA (Genetic Algorithm), etc. to locally Identify the point where the evaluation function value is the highest in the range with good continuity.
  • GA Genetic Algorithm
  • the search unit 15d assumes that the evaluation function follows a Gaussian process in a continuous range, and successively specifies a combination of parameters that maximizes the evaluation function by Bayesian optimization.
  • the combination of parameters at the point with the highest evaluation function value is determined as the parameter to be applied to the prediction model.
  • the calculation unit 15e performs a traffic simulation for the target section using a prediction model to which the determined combination of parameters is applied. For example, the calculation unit 15e predicts the congestion situation in the target section. The calculation unit 15 e outputs the predicted traffic congestion situation in the target section via the output unit 12 or the communication control unit 13 .
  • FIG. 6 is a flow chart showing a traffic simulation processing procedure. The flowchart of FIG. 6 is started, for example, at the timing when the user performs an operation input instructing the start.
  • the selection unit 15b selects parameters of roads having a priority level equal to or higher than a predetermined threshold among the roads connected to the road including the target section of the simulation as the parameter space of the evaluation function (step S1). Specifically, the selection unit 15b selects the parameters of the road with higher priority for a road closer to the target section. For example, the selection unit 15b adds a priority index to each road in order of proximity to the road including the target section, and selects roads with a priority index that is equal to or less than a predetermined threshold, assuming that priority increases in ascending order of priority index. . Then, the selection unit 15b selects the parameters of the selected road as the parameter space of the evaluation function.
  • the selection unit 15c selects a starting point candidate in the parameter space of the selected evaluation function (step S2). For example, the selection unit 15c selects a starting point candidate using a random number. Alternatively, the selection unit 15c selects a starting point candidate that can cross a traffic-related singularity using an orthogonal array.
  • the search unit 15d searches for a combination of parameters that maximizes the corresponding evaluation function value by moving the points in the parameter space from each of the selected starting point candidates (step S3).
  • the calculation unit 15e uses a prediction model to which the determined combination of parameters is applied to execute a traffic simulation such as traffic jam conditions for the target section (step S4). This completes a series of traffic simulation processes.
  • the selection unit 15b evaluates parameters of roads having a priority equal to or higher than a predetermined threshold among the roads connected to the road including the target section of the simulation. Select as the parameter space of the function. Further, the selection unit 15c selects a plurality of starting point candidates in the parameter space of the selected evaluation function. Further, the searching unit 15d searches for a combination of parameters with the highest evaluation function value by moving the parameter space from each selected starting point candidate.
  • the selection unit 15b selects the parameters of the road with higher priority for a road closer to the target section. Also, the selection unit 15c selects a starting point candidate using a random number. Alternatively, the selection unit 15c selects a starting point candidate that can cross a traffic-related singularity using an orthogonal array.
  • the traffic simulation device targets tuning by limiting the parameters of the road connected to the road including the target section of the simulation. Also, in the entire limited parameter space to be tuned, tuning is performed to parameters that are estimated to have a large effect on the target section.
  • the traffic simulation device 10 it is possible to reduce the amount of calculation, efficiently determine the optimum parameters, and perform the traffic simulation with high accuracy.
  • each vehicle searches for the optimum route for its own vehicle.
  • the traffic simulation device 10 of the present embodiment predicts traffic jam conditions and the like due to a plurality of vehicles existing in the target area in the near future.
  • the traffic simulation device 10 can efficiently determine the optimum parameters for the prediction model from among a huge number of parameters of the prediction model used in the simulation, such as traffic volume, vehicle speed, and traffic volume on roads, such as traffic lights, intersections, and roads. becomes possible. As a result, it becomes possible to perform highly accurate traffic simulations such as traffic jam conditions.
  • the traffic simulation device 10 can be implemented by installing a traffic simulation program for executing the traffic simulation processing as package software or online software in a desired computer.
  • the information processing device can function as the traffic simulation device 10 by causing the information processing device to execute the above traffic simulation program.
  • the information processing apparatus referred to here includes a desktop or notebook personal computer.
  • information processing devices include smart phones, mobile communication terminals such as mobile phones and PHSs (Personal Handyphone Systems), and slate terminals such as PDAs (Personal Digital Assistants).
  • FIG. 7 is a diagram showing an example of a computer that executes a traffic simulation program.
  • Computer 1000 includes, for example, memory 1010 , CPU 1020 , hard disk drive interface 1030 , disk drive interface 1040 , serial port interface 1050 , video adapter 1060 and network interface 1070 . These units are connected by a bus 1080 .
  • the memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012 .
  • the ROM 1011 stores a boot program such as BIOS (Basic Input Output System).
  • BIOS Basic Input Output System
  • Hard disk drive interface 1030 is connected to hard disk drive 1031 .
  • Disk drive interface 1040 is connected to disk drive 1041 .
  • a removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1041, for example.
  • a mouse 1051 and a keyboard 1052 are connected to the serial port interface 1050, for example.
  • a display 1061 is connected to the video adapter 1060 .
  • the hard disk drive 1031 stores an OS 1091, application programs 1092, program modules 1093 and program data 1094, for example. Each piece of information described in the above embodiment is stored in the hard disk drive 1031 or the memory 1010, for example.
  • the traffic simulation program is stored in the hard disk drive 1031 as a program module 1093 in which commands to be executed by the computer 1000 are described, for example.
  • the hard disk drive 1031 stores a program module 1093 that describes each process executed by the traffic simulation apparatus 10 described in the above embodiment.
  • data used for information processing by the traffic simulation program is stored as program data 1094 in the hard disk drive 1031, for example. Then, the CPU 1020 reads out the program module 1093 and the program data 1094 stored in the hard disk drive 1031 to the RAM 1012 as necessary, and executes each procedure described above.
  • program modules 1093 and program data 1094 related to the traffic simulation program are not limited to being stored in the hard disk drive 1031.
  • they may be stored in a removable storage medium and read by the CPU 1020 via the disk drive 1041 or the like. may be issued.
  • program modules 1093 and program data 1094 related to the traffic simulation program are stored in another computer connected via a network such as LAN or WAN (Wide Area Network), and are read by CPU 1020 via network interface 1070. may be

Abstract

In the present invention, the parameters of a road having a priority level greater than or equal to a prescribed threshold value among roads connected to a road that includes a section to be simulated are selected by a selection unit (15b) as the parameter space of an evaluation function. A selection unit (15c) selects a plurality of starting point candidates in the selected evaluation function parameter space. A search unit (15d) searches for a combination of parameters that maximizes the evaluation function value by moving the parameter space from the selected starting point candidates.

Description

交通シミュレーション装置、交通シミュレーション方法および交通シミュレーションプログラムTraffic simulation device, traffic simulation method and traffic simulation program
　本発明は、交通シミュレーション装置、交通シミュレーション方法および交通シミュレーションプログラムに関する。 The present invention relates to a traffic simulation device, a traffic simulation method, and a traffic simulation program.
　従来、交通に関して、予測モデルを用いてシミュレーションを行う技術が知られている（非特許文献１参照）。 Conventionally, there is known a technique for simulating traffic using a prediction model (see Non-Patent Document 1).
　しかしながら、従来技術によれば、交通に関して、予測モデルを用いて精度の高いシミュレーションを行うことが困難であった。例えば、シミュレーションに用いる予測モデルの信号機、交差点、道路における交通量、車速、車列長等のパラメータは膨大にあり、最適なパラメータを決定するための探索処理には膨大な時間がかかっていた。 However, with conventional technology, it was difficult to perform highly accurate simulations of traffic using predictive models. For example, there are a huge number of parameters such as traffic lights, intersections, road traffic volume, vehicle speed, and vehicle length in the predictive model used in the simulation, and the search process for determining the optimum parameters takes an enormous amount of time.
　本発明は、上記に鑑みてなされたものであって、交通に関する予測モデルを用いたシミュレーションにおいて、最適なパラメータを効率よく決定して精度の高いシミュレーションを行うことを目的とする。 The present invention has been made in view of the above, and it is an object of the present invention to efficiently determine optimum parameters and perform highly accurate simulations in simulations using prediction models related to traffic.
　上述した課題を解決し、目的を達成するために、本発明に係る交通シミュレーション装置は、シミュレーションの対象区間を含む道路に接続される道路のうち、所定の閾値以上の優先度の道路のパラメータを評価関数のパラメータ空間として選定する選定部と、選定された評価関数のパラメータ空間において、起点候補を選択する選択部と、選択された各起点候補からパラメータ空間の点を移動させることにより、対応する評価関数値が最高となるパラメータの組み合わせを探索する探索部と、を有することを特徴とする。 In order to solve the above-described problems and achieve the object, the traffic simulation apparatus according to the present invention determines parameters of roads having a priority level equal to or higher than a predetermined threshold among roads connected to a road including a section to be simulated. A selection unit that selects as a parameter space of the evaluation function, a selection unit that selects starting point candidates in the parameter space of the selected evaluation function, and moves a point in the parameter space from each selected starting point candidate to correspond and a search unit that searches for a combination of parameters that gives the highest evaluation function value.
　本発明によれば、交通に関する予測モデルを用いたシミュレーションにおいて、最適なパラメータを効率よく決定して精度の高いシミュレーションを行うことが可能となる。 According to the present invention, in a simulation using a predictive model for traffic, it is possible to efficiently determine optimal parameters and perform highly accurate simulations.
図１は、本実施形態に係る交通シミュレーション装置の概要を説明するための図である。FIG. 1 is a diagram for explaining an outline of a traffic simulation device according to this embodiment. 図２は、本実施形態に係る交通シミュレーション装置の概要を説明するための図である。FIG. 2 is a diagram for explaining the outline of the traffic simulation device according to this embodiment. 図３は、本実施形態に係る交通シミュレーション装置の概略構成を例示する模式図である。FIG. 3 is a schematic diagram illustrating a schematic configuration of the traffic simulation device according to this embodiment. 図４は、選定部の処理を説明するための図である。FIG. 4 is a diagram for explaining the processing of the selection unit; 図５は、選択部および探索部の処理を説明するための図である。FIG. 5 is a diagram for explaining the processing of the selection unit and the search unit; 図６は、交通シミュレーション処理手順を示すフローチャートである。FIG. 6 is a flow chart showing a traffic simulation processing procedure. 図７は、交通シミュレーションプログラムを実行するコンピュータの一例を示す図である。FIG. 7 is a diagram showing an example of a computer that executes a traffic simulation program.
　以下、図面を参照して、本発明の一実施形態を詳細に説明する。なお、この実施形態により本発明が限定されるものではない。また、図面の記載において、同一部分には同一の符号を付して示している。 An embodiment of the present invention will be described in detail below with reference to the drawings. It should be noted that the present invention is not limited by this embodiment. Moreover, in the description of the drawings, the same parts are denoted by the same reference numerals.
［交通シミュレーション装置の概要］
　図１および図２は、本実施形態に係る交通シミュレーション装置の概要を説明するための図である。従来、交通に関する渋滞予測等の予測モデルを用いたシミュレーションにおいて、最適なパラメータを逐次的に探索する方法が提案されている。一方、交通に関するシミュレーションでは、信号機、交差点、道路における交通量、車速、車列長等のパラメータが膨大にあり、シミュレーション空間が広大で計算量が膨大になっていた。そこで、本実施形態の交通シミュレーション装置は、予測モデルの精度に大きく影響を与えるパラメータを推定することにより、計算量を削減して最適なパラメータを決定（チューニング）する。 [Overview of Traffic Simulation Device]
FIG.1 and FIG.2 is a figure for demonstrating the outline|summary of the traffic simulation apparatus which concerns on this embodiment. Conventionally, a method of successively searching for optimal parameters has been proposed in simulations using predictive models such as traffic congestion prediction. On the other hand, in traffic simulations, there are a huge number of parameters such as traffic lights, intersections, traffic volume on roads, vehicle speeds, and vehicle line lengths, and the simulation space is vast and the amount of calculation is enormous. Therefore, the traffic simulation apparatus of this embodiment reduces the amount of calculation and determines (tunes) the optimum parameters by estimating parameters that greatly affect the accuracy of the prediction model.
　具体的には、交通シミュレーション装置は、まず、図１に示すように、破線で囲んで示したシミュレーションで再現する対象区間に対して、大きく影響を与える道路のパラメータを優先してその後のチューニングの対象とする。例えば、渋滞等の交通シミュレーションにおいて、対象区間に影響を与えない渋滞箇所の情報を考慮する必要はない。そこで、対象区間を含む道路に接続される道路のパラメータに限定して、チューニングの対象とする。 Specifically, as shown in FIG. 1, the traffic simulation apparatus first gives priority to road parameters that have a large effect on the target section to be reproduced in the simulation, which is enclosed by the dashed line, and performs subsequent tuning. set to target. For example, in a traffic simulation such as congestion, there is no need to consider information on congestion locations that do not affect the target section. Therefore, tuning targets are limited to the parameters of the roads connected to the road including the target section.
　また、交通に関するシミュレーションは、一般にカオス系と呼ばれ、図２に示すように、パラメータ空間全体において、局所的な連続性を持つ箇所と、破線で囲んで示すように不連続性を持つ箇所とが混在する。例えば、青信号の時間が短くなるにつれその道路が渋滞しやすくなり、う回路の方がかかる時間が短くなる等というように特異点を超える場合に、非連続性が発生する。 A traffic simulation is generally called a chaotic system, and as shown in Fig. 2, the entire parameter space has points with local continuity and points with discontinuity as indicated by the dashed lines. are mixed. For example, a discontinuity occurs when a singular point is exceeded such that the road becomes more congested as the green light time becomes shorter, and the detour takes less time.
　そこで、交通シミュレーション装置は、パラメータ空間の局所的な連続性の範囲のそれぞれで予測モデルの評価関数値が最高となる点を探索することにより、パラメータ空間全体で、対象区間に影響が大きいと推定されるパラメータにチューニングする。 Therefore, the traffic simulation device searches for the point where the evaluation function value of the prediction model is the highest in each range of local continuity of the parameter space, and estimates that the target section has a large impact in the entire parameter space. Tune to the required parameters.
　このようにして、交通シミュレーション装置は、予測モデルを用いた交通シミュレーションに用いる最適なパラメータを、計算量を削減して効率よく決定し、精度の高い交通シミュレーションを行うことが可能となる。 In this way, the traffic simulation device can efficiently determine the optimal parameters for traffic simulation using the predictive model by reducing the amount of calculation, and perform highly accurate traffic simulation.
［交通シミュレーション装置の構成］
　図３は、本実施形態に係る交通シミュレーション装置の概略構成を例示する模式図である。図３に例示するように、本実施形態の交通シミュレーション装置１０は、パソコン等の汎用コンピュータで実現され、入力部１１、出力部１２、通信制御部１３、記憶部１４、および制御部１５を備える。 [Configuration of traffic simulation device]
FIG. 3 is a schematic diagram illustrating a schematic configuration of the traffic simulation device according to this embodiment. As illustrated in FIG. 3, the traffic simulation device 10 of the present embodiment is implemented by a general-purpose computer such as a personal computer, and includes an input unit 11, an output unit 12, a communication control unit 13, a storage unit 14, and a control unit 15. .
　入力部１１は、キーボードやマウス等の入力デバイスを用いて実現され、操作者による入力操作に対応して、制御部１５に対する処理開始などの各種指示情報を入力する。出力部１２は、液晶ディスプレイなどの表示装置、プリンター等によって実現される。例えば、出力部１２には、後述する交通シミュレーション処理の結果が表示される。 The input unit 11 is implemented using input devices such as a keyboard and a mouse, and inputs various instruction information such as processing start to the control unit 15 in response to input operations by the operator. The output unit 12 is implemented by a display device such as a liquid crystal display, a printer, or the like. For example, the output unit 12 displays the results of traffic simulation processing, which will be described later.
　通信制御部１３は、ＮＩＣ（Network　Interface　Card）等で実現され、ＬＡＮ（Local　Area　Network）やインターネットなどの電気通信回線を介した外部の装置と制御部１５との通信を制御する。例えば、通信制御部１３は、地図データや、処理対象の各道路の信号機、交差点、交通量、車速、車列長等の各種情報を管理する管理装置等と、制御部１５との通信を制御する。 The communication control unit 13 is realized by a NIC (Network Interface Card) or the like, and controls communication between an external device and the control unit 15 via an electrical communication line such as a LAN (Local Area Network) or the Internet. For example, the communication control unit 13 controls communication between the control unit 15 and a management device that manages various information such as map data, traffic signals, intersections, traffic volume, vehicle speed, and vehicle length of each road to be processed. do.
　記憶部１４は、ＲＡＭ（Random　Access　Memory）、フラッシュメモリ（Flash　Memory）等の半導体メモリ素子、または、ハードディスク、光ディスク等の記憶装置によって実現される。記憶部１４には、交通シミュレーション装置１０を動作させる処理プログラムや、処理プログラムの実行中に使用されるデータなどが予め記憶され、あるいは処理の都度一時的に記憶される。なお、記憶部１４は、通信制御部１３を介して制御部１５と通信する構成でもよい。 The storage unit 14 is implemented by semiconductor memory devices such as RAM (Random Access Memory) and flash memory, or storage devices such as hard disks and optical disks. In the storage unit 14, a processing program for operating the traffic simulation device 10, data used during execution of the processing program, and the like are stored in advance, or are temporarily stored each time processing is performed. Note that the storage unit 14 may be configured to communicate with the control unit 15 via the communication control unit 13 .
　また、記憶部１４は、地図データや、処理対象の各道路の信号機、交差点、交通量、車速、車列長等、後述する交通シミュレーション処理に必要な各種情報等を予め取得して記憶してもよい。また、記憶部１４は、後述する交通シミュレーション処理でパラメータが決定した予測モデルを記憶する。 In addition, the storage unit 14 acquires and stores in advance various information such as map data, traffic lights, intersections, traffic volume, vehicle speed, and vehicle length of each road to be processed, which are necessary for the traffic simulation process described later. good too. The storage unit 14 also stores a prediction model whose parameters are determined in a traffic simulation process, which will be described later.
　制御部１５は、ＣＰＵ（Central　Processing　Unit）等を用いて実現され、メモリに記憶された処理プログラムを実行する。これにより、制御部１５は、図３に例示するように、取得部１５ａ、選定部１５ｂ、選択部１５ｃ、探索部１５ｄおよび計算部１５ｅとして機能する。 The control unit 15 is implemented using a CPU (Central Processing Unit) or the like, and executes a processing program stored in memory. Thereby, the control unit 15 functions as an acquisition unit 15a, a selection unit 15b, a selection unit 15c, a search unit 15d, and a calculation unit 15e, as illustrated in FIG.
　なお、これらの機能部は、それぞれ、あるいは一部が異なるハードウェアに実装されてもよい。例えば、計算部１５ｅは、他の機能部とは異なる装置に実装されてもよい。また、制御部１５は、その他の機能部を備えてもよい。 It should be noted that these functional units may be implemented in different hardware, respectively or partially. For example, the calculator 15e may be implemented in a device different from the other functional units. Also, the control unit 15 may include other functional units.
　取得部１５ａは、地図上の各道路の交差点や信号機、渋滞が発生している箇所の断面交通量、車速、車列長等の情報を取得する。取得部１５ａは、これらの情報を、入力部１１を介して、または管理装置等から通信制御部１３を介して取得する。取得部１５ａは、取得した情報を記憶部１４に記憶させてもよい。 The acquisition unit 15a acquires information such as intersections and traffic lights on each road on the map, cross-sectional traffic volume, vehicle speed, and length of congested areas. The acquisition unit 15a acquires these pieces of information via the input unit 11 or via the communication control unit 13 from a management device or the like. The acquisition unit 15a may cause the storage unit 14 to store the acquired information.
　選定部１５ｂは、シミュレーションの対象区間を含む道路に接続される道路のうち、所定の閾値以上の優先度の道路のパラメータを評価関数のパラメータ空間として選定する。具体的には、選定部１５ｂは、対象区間から近い道路ほど高い優先度で該道路のパラメータを選定する。 The selection unit 15b selects parameters of roads having a priority level equal to or higher than a predetermined threshold among the roads connected to the road including the target section of the simulation as the parameter space of the evaluation function. Specifically, the selection unit 15b selects the parameters of the road with higher priority for a road closer to the target section.
　ここで、図４は、選定部の処理を説明するための図である。図４に示すように、選定部１５ｂは、対象区間を含む道路に近い順に、各道路に優先指標を付加し、優先指標が小さい順に優先度が高くなるものとして、所定の閾値以下の優先指標の道路を選定する。そして、選定部１５ｂは、選定した道路のパラメータを評価関数のパラメータ空間として選定する。例えば、選定部１５ｂは、ＲＭＳＥ（Root　Mean　Squared　Error、二乗平均平方根誤差）等により、選定した各パラメータを用いて予測モデルによる予測結果の評価関数を決定する。 Here, FIG. 4 is a diagram for explaining the processing of the selection unit. As shown in FIG. 4, the selection unit 15b adds a priority index to each road in order of proximity to the road including the target section, and assigns a priority index that is equal to or less than a predetermined threshold as a priority that increases in descending order of the priority index. road. Then, the selection unit 15b selects the parameters of the selected road as the parameter space of the evaluation function. For example, the selection unit 15b determines the evaluation function of the prediction result of the prediction model using each selected parameter by RMSE (Root Mean Squared Error) or the like.
　図４に示す例では、対象区間を含む道路を優先指標１．０、この道路と交差する道路の優先指標１．５としている。また、優先指標１．５の道路と交差する道路、すなわち、対象区間を含む優先指標１．０の道路から１ホップ先の道路を優先指標２．０としている。そして、優先指標が所定の閾値以下の道路、すなわち対象区間を含む道路から近いほど高い優先度で道路を選定し、それらの道路の交差点や信号機、渋滞が発生している箇所の交通量、車速、車列長等の情報をパラメータとして選定する。 In the example shown in FIG. 4, the road that includes the target section has a priority index of 1.0, and the road that intersects with this road has a priority index of 1.5. A road that intersects with a road with a priority index of 1.5, that is, a road that is one hop ahead from a road with a priority index of 1.0 that includes the target section is assigned a priority index of 2.0. Then, roads whose priority index is equal to or less than a predetermined threshold, that is, roads closer to the road containing the target section are selected with higher priority. , train length, etc. are selected as parameters.
　図３の説明に戻る。選択部１５ｃは、選定された評価関数のパラメータ空間において、起点候補を選択する。例えば、選択部１５ｃは、乱数により起点候補を選択する。あるいは、選択部１５ｃは、直交表を用いて交通に関する特異点をまたぎうる起点候補を選択する。 Return to the description of Fig. 3. The selection unit 15c selects a starting point candidate in the parameter space of the selected evaluation function. For example, the selection unit 15c selects a starting point candidate using a random number. Alternatively, the selection unit 15c selects a starting point candidate that can cross a traffic-related singularity using an orthogonal array.
　ここで、図５は、選択部および探索部の処理を説明するための図である。選択部１５ｃは、図５に丸で囲んで示したように、パラメータ空間の複数の起点候補を選択する。例えば、選択部１５ｃは、起点候補を乱数で選択してもよいし、直交表を用いてもよい。直交表として、例えば、信号機の赤対青が７．５対２．５となる点、５対５となる点、２．５対７．５となる点等の特異点をまたぎうる点のリストを予め作成しておき、選択部１５ｃが、直交表から特異点をまたぎうる点を起点候補として選択してもよい。 Here, FIG. 5 is a diagram for explaining the processing of the selection unit and search unit. The selection unit 15c selects a plurality of starting point candidates in the parameter space, as circled in FIG. For example, the selection unit 15c may select a starting point candidate using a random number, or may use an orthogonal table. As an orthogonal table, for example, a list of points that can cross singularities such as red to green ratios of traffic lights of 7.5 to 2.5, 5 to 5, and 2.5 to 7.5 is created in advance, and the selection unit 15c selects a point that can cross the singular point from the orthogonal array as the starting point candidate.
　図３の説明に戻る。探索部１５ｄは、選択された各起点候補からパラメータ空間の点を移動させることにより、対応する評価関数値が最高となるパラメータの組み合わせを探索する。例えば、探索部１５ｄは、図５に破線で示すように、選択された各起点候補からパラメータ空間の値を前後に変化させながら、焼きなまし法やＧＡ（Genetic　Algorithm）等を用いて、局地的な連続性を持つ範囲で、評価関数値が最高となる点を特定する。探索部１５ｄは、例えば、連続性を持つ範囲で評価関数がガウス過程に従うと仮定して、ベイズ最適化により逐次的に評価関数が最大値となるパラメータの組み合わせを特定する。 Return to the description of Fig. 3. The searching unit 15d searches for a combination of parameters with the highest corresponding evaluation function value by moving points in the parameter space from each of the selected starting point candidates. For example, the search unit 15d uses simulated annealing, GA (Genetic Algorithm), etc. to locally Identify the point where the evaluation function value is the highest in the range with good continuity. The search unit 15d, for example, assumes that the evaluation function follows a Gaussian process in a continuous range, and successively specifies a combination of parameters that maximizes the evaluation function by Bayesian optimization.
　そして、各起点候補から特定した点のうち、評価関数値が最高となる点のパラメータの組み合わせを、予測モデルに適用するパラメータとして決定する。 Then, among the points identified from each starting point candidate, the combination of parameters at the point with the highest evaluation function value is determined as the parameter to be applied to the prediction model.
　図３の説明に戻る。計算部１５ｅは、決定されたパラメータの組み合わせを適用した予測モデルを用いて、対象区間について交通シミュレーションを行う。例えば、計算部１５ｅは、対象区間の渋滞状況の予測を行う。計算部１５ｅは、予測した対象区間の渋滞状況を、出力部１２あるいは通信制御部１３を介して出力する。 Return to the description of Fig. 3. The calculation unit 15e performs a traffic simulation for the target section using a prediction model to which the determined combination of parameters is applied. For example, the calculation unit 15e predicts the congestion situation in the target section. The calculation unit 15 e outputs the predicted traffic congestion situation in the target section via the output unit 12 or the communication control unit 13 .
［交通シミュレーション処理］
　次に、図６を参照して、本実施形態に係る交通シミュレーション装置１０による交通シミュレーション処理について説明する。図６は、交通シミュレーション処理手順を示すフローチャートである。図６のフローチャートは、例えば、ユーザが開始を指示する操作入力を行ったタイミングで開始される。 [Traffic simulation processing]
Next, with reference to Drawing 6, traffic simulation processing by traffic simulation device 10 concerning this embodiment is explained. FIG. 6 is a flow chart showing a traffic simulation processing procedure. The flowchart of FIG. 6 is started, for example, at the timing when the user performs an operation input instructing the start.
　まず、選定部１５ｂが、シミュレーションの対象区間を含む道路に接続される道路のうち、所定の閾値以上の優先度の道路のパラメータを評価関数のパラメータ空間として選定する（ステップＳ１）。具体的には、選定部１５ｂは、対象区間から近い道路ほど高い優先度で該道路のパラメータを選定する。例えば、選定部１５ｂは、対象区間を含む道路に近い順に、各道路に優先指標を付加し、優先指標が小さい順に優先度が高くなるものとして、所定の閾値以下の優先指標の道路を選定する。そして、選定部１５ｂは、選定した道路のパラメータを評価関数のパラメータ空間として選定する。 First, the selection unit 15b selects parameters of roads having a priority level equal to or higher than a predetermined threshold among the roads connected to the road including the target section of the simulation as the parameter space of the evaluation function (step S1). Specifically, the selection unit 15b selects the parameters of the road with higher priority for a road closer to the target section. For example, the selection unit 15b adds a priority index to each road in order of proximity to the road including the target section, and selects roads with a priority index that is equal to or less than a predetermined threshold, assuming that priority increases in ascending order of priority index. . Then, the selection unit 15b selects the parameters of the selected road as the parameter space of the evaluation function.
　次に、選択部１５ｃが、選定された評価関数のパラメータ空間において、起点候補を選択する（ステップＳ２）。例えば、選択部１５ｃは、乱数により起点候補を選択する。あるいは、選択部１５ｃは、直交表を用いて交通に関する特異点をまたぎうる起点候補を選択する。 Next, the selection unit 15c selects a starting point candidate in the parameter space of the selected evaluation function (step S2). For example, the selection unit 15c selects a starting point candidate using a random number. Alternatively, the selection unit 15c selects a starting point candidate that can cross a traffic-related singularity using an orthogonal array.
　また、探索部１５ｄが、選択された各起点候補からパラメータ空間の点を移動させることにより、対応する評価関数値が最高となるパラメータの組み合わせを探索する（ステップＳ３）。 Also, the search unit 15d searches for a combination of parameters that maximizes the corresponding evaluation function value by moving the points in the parameter space from each of the selected starting point candidates (step S3).
　そして、計算部１５ｅが、決定されたパラメータの組み合わせを適用した予測モデルを用いて、対象区間について渋滞状況等の交通シミュレーションを実行する（ステップＳ４）。これにより、一連の交通シミュレーション処理が終了する。 Then, the calculation unit 15e uses a prediction model to which the determined combination of parameters is applied to execute a traffic simulation such as traffic jam conditions for the target section (step S4). This completes a series of traffic simulation processes.
［効果］
　以上、説明したように、本実施形態の交通シミュレーション装置１０において、選定部１５ｂが、シミュレーションの対象区間を含む道路に接続される道路のうち、所定の閾値以上の優先度の道路のパラメータを評価関数のパラメータ空間として選定する。また、選択部１５ｃが、選定された評価関数のパラメータ空間において、複数の起点候補を選択する。また、探索部１５ｄが、選択された各起点候補からパラメータ空間を移動させることにより、評価関数値が最高となるパラメータの組み合わせを探索する。 [effect]
As described above, in the traffic simulation device 10 of the present embodiment, the selection unit 15b evaluates parameters of roads having a priority equal to or higher than a predetermined threshold among the roads connected to the road including the target section of the simulation. Select as the parameter space of the function. Further, the selection unit 15c selects a plurality of starting point candidates in the parameter space of the selected evaluation function. Further, the searching unit 15d searches for a combination of parameters with the highest evaluation function value by moving the parameter space from each selected starting point candidate.
　具体的には、選定部１５ｂは、対象区間から近い道路ほど高い優先度で当該道路のパラメータを選定する。また、選択部１５ｃは、乱数により起点候補を選択する。あるいは、選択部１５ｃは、直交表を用いて交通に関する特異点をまたぎうる起点候補を選択する。 Specifically, the selection unit 15b selects the parameters of the road with higher priority for a road closer to the target section. Also, the selection unit 15c selects a starting point candidate using a random number. Alternatively, the selection unit 15c selects a starting point candidate that can cross a traffic-related singularity using an orthogonal array.
　これにより、交通シミュレーション装置は、予測モデルを用いた交通に関するシミュレーションにおいて、シミュレーションの対象区間を含む道路に接続される道路のパラメータに限定して、チューニングの対象とする。また、限定したチューニング対象のパラメータ空間全体の中で、対象区間に影響が大きいと推定されるパラメータにチューニングする。このように、交通シミュレーション装置１０によれば、計算量を削減して効率よく最適なパラメータを決定し、精度高く交通シミュレーションを行うことが可能となる。 As a result, in the traffic simulation using the predictive model, the traffic simulation device targets tuning by limiting the parameters of the road connected to the road including the target section of the simulation. Also, in the entire limited parameter space to be tuned, tuning is performed to parameters that are estimated to have a large effect on the target section. Thus, according to the traffic simulation device 10, it is possible to reduce the amount of calculation, efficiently determine the optimum parameters, and perform the traffic simulation with high accuracy.
　ここで、従来のカーナビ等の経路探索アルゴリズムでは、各車両において、自車両に最適なルートの探索を行う。これに対し、本実施形態の交通シミュレーション装置１０は、近未来の対象エリア内に存在する複数の車両による渋滞状況等の予測を行う。その際に、交通シミュレーション装置１０は、シミュレーションに用いる予測モデルの信号機、交差点、道路における交通量、車速、車列長等の膨大なパラメータのうち、予測モデルに最適なパラメータを効率よく決定するこが可能となる。その結果、精度高く渋滞状況等の交通シミュレーションを精度高く行うことが可能となる。 Here, in conventional route search algorithms such as car navigation systems, each vehicle searches for the optimum route for its own vehicle. On the other hand, the traffic simulation device 10 of the present embodiment predicts traffic jam conditions and the like due to a plurality of vehicles existing in the target area in the near future. At that time, the traffic simulation device 10 can efficiently determine the optimum parameters for the prediction model from among a huge number of parameters of the prediction model used in the simulation, such as traffic volume, vehicle speed, and traffic volume on roads, such as traffic lights, intersections, and roads. becomes possible. As a result, it becomes possible to perform highly accurate traffic simulations such as traffic jam conditions.
［プログラム］
　上記実施形態に係る交通シミュレーション装置１０が実行する処理をコンピュータが実行可能な言語で記述したプログラムを作成することもできる。一実施形態として、交通シミュレーション装置１０は、パッケージソフトウェアやオンラインソフトウェアとして上記の交通シミュレーション処理を実行する交通シミュレーションプログラムを所望のコンピュータにインストールさせることによって実装できる。例えば、上記の交通シミュレーションプログラムを情報処理装置に実行させることにより、情報処理装置を交通シミュレーション装置１０として機能させることができる。ここで言う情報処理装置には、デスクトップ型またはノート型のパーソナルコンピュータが含まれる。また、その他にも、情報処理装置にはスマートフォン、携帯電話機やＰＨＳ（Personal　Handyphone　System）などの移動体通信端末、さらには、ＰＤＡ（Personal　Digital　Assistant）などのスレート端末などがその範疇に含まれる。また、交通シミュレーション装置１０の機能を、クラウドサーバに実装してもよい。 [program]
It is also possible to create a program in which the processing executed by the traffic simulation device 10 according to the above embodiment is described in a computer-executable language. As one embodiment, the traffic simulation device 10 can be implemented by installing a traffic simulation program for executing the traffic simulation processing as package software or online software in a desired computer. For example, the information processing device can function as the traffic simulation device 10 by causing the information processing device to execute the above traffic simulation program. The information processing apparatus referred to here includes a desktop or notebook personal computer. In addition, information processing devices include smart phones, mobile communication terminals such as mobile phones and PHSs (Personal Handyphone Systems), and slate terminals such as PDAs (Personal Digital Assistants). Moreover, you may implement the function of the traffic simulation apparatus 10 in a cloud server.
　図７は、交通シミュレーションプログラムを実行するコンピュータの一例を示す図である。コンピュータ１０００は、例えば、メモリ１０１０と、ＣＰＵ１０２０と、ハードディスクドライブインタフェース１０３０と、ディスクドライブインタフェース１０４０と、シリアルポートインタフェース１０５０と、ビデオアダプタ１０６０と、ネットワークインタフェース１０７０とを有する。これらの各部は、バス１０８０によって接続される。 FIG. 7 is a diagram showing an example of a computer that executes a traffic simulation program. Computer 1000 includes, for example, memory 1010 , CPU 1020 , hard disk drive interface 1030 , disk drive interface 1040 , serial port interface 1050 , video adapter 1060 and network interface 1070 . These units are connected by a bus 1080 .
　メモリ１０１０は、ＲＯＭ（Read　Only　Memory）１０１１およびＲＡＭ１０１２を含む。ＲＯＭ１０１１は、例えば、ＢＩＯＳ（Basic　Input　Output　System）等のブートプログラムを記憶する。ハードディスクドライブインタフェース１０３０は、ハードディスクドライブ１０３１に接続される。ディスクドライブインタフェース１０４０は、ディスクドライブ１０４１に接続される。ディスクドライブ１０４１には、例えば、磁気ディスクや光ディスク等の着脱可能な記憶媒体が挿入される。シリアルポートインタフェース１０５０には、例えば、マウス１０５１およびキーボード１０５２が接続される。ビデオアダプタ１０６０には、例えば、ディスプレイ１０６１が接続される。 The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012 . The ROM 1011 stores a boot program such as BIOS (Basic Input Output System). Hard disk drive interface 1030 is connected to hard disk drive 1031 . Disk drive interface 1040 is connected to disk drive 1041 . A removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1041, for example. A mouse 1051 and a keyboard 1052 are connected to the serial port interface 1050, for example. For example, a display 1061 is connected to the video adapter 1060 .
　ここで、ハードディスクドライブ１０３１は、例えば、ＯＳ１０９１、アプリケーションプログラム１０９２、プログラムモジュール１０９３およびプログラムデータ１０９４を記憶する。上記実施形態で説明した各情報は、例えばハードディスクドライブ１０３１やメモリ１０１０に記憶される。 Here, the hard disk drive 1031 stores an OS 1091, application programs 1092, program modules 1093 and program data 1094, for example. Each piece of information described in the above embodiment is stored in the hard disk drive 1031 or the memory 1010, for example.
　また、交通シミュレーションプログラムは、例えば、コンピュータ１０００によって実行される指令が記述されたプログラムモジュール１０９３として、ハードディスクドライブ１０３１に記憶される。具体的には、上記実施形態で説明した交通シミュレーション装置１０が実行する各処理が記述されたプログラムモジュール１０９３が、ハードディスクドライブ１０３１に記憶される。 Also, the traffic simulation program is stored in the hard disk drive 1031 as a program module 1093 in which commands to be executed by the computer 1000 are described, for example. Specifically, the hard disk drive 1031 stores a program module 1093 that describes each process executed by the traffic simulation apparatus 10 described in the above embodiment.
　また、交通シミュレーションプログラムによる情報処理に用いられるデータは、プログラムデータ１０９４として、例えば、ハードディスクドライブ１０３１に記憶される。そして、ＣＰＵ１０２０が、ハードディスクドライブ１０３１に記憶されたプログラムモジュール１０９３やプログラムデータ１０９４を必要に応じてＲＡＭ１０１２に読み出して、上述した各手順を実行する。 In addition, data used for information processing by the traffic simulation program is stored as program data 1094 in the hard disk drive 1031, for example. Then, the CPU 1020 reads out the program module 1093 and the program data 1094 stored in the hard disk drive 1031 to the RAM 1012 as necessary, and executes each procedure described above.
　なお、交通シミュレーションプログラムに係るプログラムモジュール１０９３やプログラムデータ１０９４は、ハードディスクドライブ１０３１に記憶される場合に限られず、例えば、着脱可能な記憶媒体に記憶されて、ディスクドライブ１０４１等を介してＣＰＵ１０２０によって読み出されてもよい。あるいは、交通シミュレーションプログラムに係るプログラムモジュール１０９３やプログラムデータ１０９４は、ＬＡＮやＷＡＮ（Wide　Area　Network）等のネットワークを介して接続された他のコンピュータに記憶され、ネットワークインタフェース１０７０を介してＣＰＵ１０２０によって読み出されてもよい。 Note that the program modules 1093 and program data 1094 related to the traffic simulation program are not limited to being stored in the hard disk drive 1031. For example, they may be stored in a removable storage medium and read by the CPU 1020 via the disk drive 1041 or the like. may be issued. Alternatively, program modules 1093 and program data 1094 related to the traffic simulation program are stored in another computer connected via a network such as LAN or WAN (Wide Area Network), and are read by CPU 1020 via network interface 1070. may be
　以上、本発明者によってなされた発明を適用した実施形態について説明したが、本実施形態による本発明の開示の一部をなす記述および図面により本発明は限定されることはない。すなわち、本実施形態に基づいて当業者等によりなされる他の実施形態、実施例および運用技術等は全て本発明の範疇に含まれる。 Although the embodiment to which the invention made by the present inventor is applied has been described above, the present invention is not limited by the descriptions and drawings forming part of the disclosure of the present invention according to the present embodiment. That is, other embodiments, examples, operation techniques, etc. made by those skilled in the art based on this embodiment are all included in the scope of the present invention.
　１０　交通シミュレーション装置
　１１　入力部
　１２　出力部
　１３　通信制御部
　１４　記憶部
　１５　制御部
　１５ａ　取得部
　１５ｂ　選定部
　１５ｃ　選択部
　１５ｄ　探索部
　１５ｅ　計算部 10 traffic simulation device 11 input unit 12 output unit 13 communication control unit 14 storage unit 15 control unit 15a acquisition unit 15b selection unit 15c selection unit 15d search unit 15e calculation unit

Claims (6)

  1. 　シミュレーションの対象区間を含む道路に接続される道路のうち、所定の閾値以上の優先度の道路のパラメータを評価関数のパラメータ空間として選定する選定部と、
    　選定された評価関数のパラメータ空間において、起点候補を選択する選択部と、
    　選択された各起点候補からパラメータ空間の点を移動させることにより、対応する評価関数値が最高となるパラメータの組み合わせを探索する探索部と、
    　を有することを特徴とする交通シミュレーション装置。     a selection unit that selects, from among roads connected to a road including a section to be simulated, parameters of roads having a priority level equal to or higher than a predetermined threshold as a parameter space of an evaluation function;
    a selection unit that selects a starting point candidate in the parameter space of the selected evaluation function;
    a search unit that searches for a combination of parameters that maximizes the corresponding evaluation function value by moving a point in the parameter space from each of the selected starting point candidates;
    A traffic simulation device comprising:
  2. 　前記選定部は、前記対象区間から近い道路ほど高い優先度で該道路のパラメータを選定することを特徴とする請求項１に記載の交通シミュレーション装置。 The traffic simulation device according to claim 1, wherein the selection unit selects the parameters of the road with higher priority for a road closer to the target section.
  3. 　前記選択部は、乱数により前記起点候補を選択することを特徴とする請求項１に記載の交通シミュレーション装置。 The traffic simulation device according to claim 1, wherein the selection unit selects the starting point candidate using a random number.
  4. 　前記選択部は、直交表を用いて交通に関する特異点をまたぎうる前記起点候補を選択することを特徴とする請求項１に記載の交通シミュレーション装置。 The traffic simulation device according to claim 1, wherein the selection unit uses an orthogonal array to select the starting point candidate that can cross a singular point related to traffic.
  5. 　交通シミュレーション装置が実行する交通シミュレーション方法であって、
    　シミュレーションの対象区間を含む道路に接続される道路のうち、所定の閾値以上の優先度の道路のパラメータを評価関数のパラメータ空間として選定する選定工程と、
    　選定された評価関数のパラメータ空間において、起点候補を選択する選択工程と、
    　選択された各起点候補からパラメータ空間の点を移動させることにより、対応する評価関数値が最高となるパラメータの組み合わせを探索する探索工程と、
    　を含んだことを特徴とする交通シミュレーション方法。     A traffic simulation method executed by a traffic simulation device,
    A selection step of selecting, as a parameter space of an evaluation function, parameters of roads having a priority level equal to or higher than a predetermined threshold among roads connected to a road including a section to be simulated;
    a selection step of selecting a starting point candidate in the parameter space of the selected evaluation function;
    a search step of searching for a combination of parameters that maximizes the corresponding evaluation function value by moving points in the parameter space from each of the selected starting point candidates;
    A traffic simulation method comprising:
  6. 　シミュレーションの対象区間を含む道路に接続される道路のうち、所定の閾値以上の優先度の道路のパラメータを評価関数のパラメータ空間として選定する選定ステップと、
    　選定された評価関数のパラメータ空間において、起点候補を選択する選択ステップと、
    　選択された各起点候補からパラメータ空間の点を移動させることにより、対応する評価関数値が最高となるパラメータの組み合わせを探索する探索ステップと、
    　をコンピュータに実行させるための交通シミュレーションプログラム。     a selection step of selecting, from among roads connected to a road including a section to be simulated, parameters of roads having a priority level equal to or higher than a predetermined threshold as a parameter space of an evaluation function;
    a selection step of selecting a starting point candidate in the parameter space of the selected evaluation function;
    a search step of searching for a combination of parameters with the highest corresponding evaluation function value by moving points in the parameter space from each of the selected starting point candidates;
    A traffic simulation program for executing on a computer.
PCT/JP2021/026041 2021-07-09 2021-07-09 Traffic simulation device, traffic simulation method, and traffic simulation program WO2023281756A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/026041 WO2023281756A1 (en) 2021-07-09 2021-07-09 Traffic simulation device, traffic simulation method, and traffic simulation program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/026041 WO2023281756A1 (en) 2021-07-09 2021-07-09 Traffic simulation device, traffic simulation method, and traffic simulation program

Publications (1)

Publication Number Publication Date
WO2023281756A1 true WO2023281756A1 (en) 2023-01-12

Family

ID=84800545

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/026041 WO2023281756A1 (en) 2021-07-09 2021-07-09 Traffic simulation device, traffic simulation method, and traffic simulation program

Country Status (1)

Country Link
WO (1) WO2023281756A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009032043A (en) * 2007-07-27 2009-02-12 Panasonic Corp Traffic signal control parameter design device and traffic signal control parameter generation method
JP2011039786A (en) * 2009-08-11 2011-02-24 Toshiba Corp Software test support device, software test support method and program
JP2011113362A (en) * 2009-11-27 2011-06-09 Sumitomo Electric Ind Ltd Traffic information estimation system, boundary traffic information estimation apparatus, traffic information estimation apparatus for divided regions, computer program, traffic information estimation method, boundary traffic information estimation method, and traffic information estimation method for divided region
JP2018147075A (en) * 2017-03-02 2018-09-20 日本電信電話株式会社 Parameter output device, parameter output method, and program

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009032043A (en) * 2007-07-27 2009-02-12 Panasonic Corp Traffic signal control parameter design device and traffic signal control parameter generation method
JP2011039786A (en) * 2009-08-11 2011-02-24 Toshiba Corp Software test support device, software test support method and program
JP2011113362A (en) * 2009-11-27 2011-06-09 Sumitomo Electric Ind Ltd Traffic information estimation system, boundary traffic information estimation apparatus, traffic information estimation apparatus for divided regions, computer program, traffic information estimation method, boundary traffic information estimation method, and traffic information estimation method for divided region
JP2018147075A (en) * 2017-03-02 2018-09-20 日本電信電話株式会社 Parameter output device, parameter output method, and program

Similar Documents

Publication Publication Date Title
EP4086578A1 (en) Vehicle behavior prediction method and apparatus, electronic device, and storage medium
CN113753077A (en) Method and device for predicting movement locus of obstacle and automatic driving vehicle
CN113682318B (en) Vehicle running control method and device
US20230138650A1 (en) Test method for automatic driving, and electronic device
CN110347873A (en) Video classification methods, device, electronic equipment and storage medium
JP2022104639A (en) Vehicle lane change control method, device, storage medium, and program
JP7215077B2 (en) Prediction program, prediction method and prediction device
US20230415787A1 (en) Method and apparatus for generating a simulation scene, electronic device and storage medium
JP2023022185A (en) Map data processing method and device, electronic equipment, storage medium, and computer program
CN114506343A (en) Trajectory planning method, device, equipment, storage medium and automatic driving vehicle
CN115560771A (en) Sampling-based path planning method and device and automatic driving equipment
CN114998477A (en) Method, device, equipment and product for drawing center line of turning area lane
US9633145B2 (en) Traffic simulation method, program, and system
WO2023281756A1 (en) Traffic simulation device, traffic simulation method, and traffic simulation program
CN110728359A (en) Method, device, equipment and storage medium for searching model structure
Merbah et al. Intelligent management of crossroads with traffic lights using an hybrid method combining genetic algorithm and fuzzy logic
CN115366919A (en) Trajectory prediction method, system, electronic device and storage medium
CN115454082A (en) Vehicle obstacle avoidance method and system, computer readable storage medium and electronic device
CN113570727B (en) Scene file generation method and device, electronic equipment and storage medium
CN112862017B (en) Point cloud data labeling method, device, equipment and medium
WO2023014731A1 (en) System and methods of adaptive relevancy prediction for autonomous driving
JP2022037938A (en) Method, device, electric device, storage medium, and computer program product to process traffic data
WO2023058178A1 (en) Simulation device, simulation method, and simulation program
RU2818050C1 (en) Method of manoeuvre-aware determination of time to end of route and system and electronic device implementing thereof
CN114475632B (en) Automatic driving control data determination method, device, equipment and storage medium

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21949388

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE