2021 Fiscal Year Final Research Report
Development of traffic state estimation technology of real world network by fusion of sensing data and traffic flow theory
Project/Area Number |
19K15107
|
Research Category |
Grant-in-Aid for Early-Career Scientists
|
Allocation Type | Multi-year Fund |
Review Section |
Basic Section 22050:Civil engineering plan and transportation engineering-related
|
Research Institution | Nihon University (2021) Tohoku University (2019-2020) |
Principal Investigator |
|
Project Period (FY) |
2019-04-01 – 2022-03-31
|
Keywords | 交通状態推定 / 交通流理論 / 経路選択 / データ同化 / プローブデータ / 車両感知器 |
Outline of Final Research Achievements |
This research proposes to develop a method for estimating traffic state in real-world networks by fusing sensing data and traffic flow theory. In traffic control, it is important to collect information on thenetwork and provide traffic control and information based on the results of monitoring traffic conditions.Previous studies have estimated the traffic condition in a single road section (one-dimensional), but have not estimated the traffic condition in an areal network. Therefore, we developed a model that represents network traffic flow by combining a traffic flow model that takes into account drivers' route selection behavior and sensing data. The model was validated on a real-world network, and the results showed that the model accurately estimated the state of the network.
|
Free Research Field |
交通工学
|
Academic Significance and Societal Importance of the Research Achievements |
本研究は,従来の単路区間(一次元)の交通状態推定手法を二次元ネットワークに拡張し,経路選択率と整合的な交通状態とモデルパラメータを同時に推定するものであり,学術的新規性が高く,今後のネットワークワイドな交通状態推定の学術的な発展に貢献している. また,日常的な渋滞の把握に加えて,事故・災害やオリンピック等の事前にパラメータ学習が困難な非日常時の交通状態推定にも応用可能であり,多様な場面での交通マネジメントに貢献できるので,社会的な有用性も高いと考える.
|