A study on a new analytical method for intelligent transport systems
| Project/Area Number |
17H03323
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Civil engineering project/Traffic engineering
|
|---|
| Research Institution | Gifu University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
倉内 文孝 岐阜大学, 工学部, 教授 (10263104)
應 江黔 岐阜大学, 地域科学部, 教授 (30242738)
高木 朗義 岐阜大学, 工学部, 教授 (30322134)
杉浦 聡志 北海道大学, 工学研究院, 准教授 (30648051)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥13,650,000 (Direct Cost: ¥10,500,000、Indirect Cost: ¥3,150,000)
Fiscal Year 2019: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2018: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Fiscal Year 2017: ¥8,580,000 (Direct Cost: ¥6,600,000、Indirect Cost: ¥1,980,000)
|
|---|
| Keywords | 経路選択行動 / ゲーム理論 / 動的交通量配分 / 交通流特性 / 強化学習 / 深層学習 / 自動走行支援システム / 便益計測 / 交通流シミュレーション / 交通計画 / 交通工学 |
|---|
| Outline of Final Research Achievements |
The purpose of this research is to propose a new method for analyzing road traffic networks based on the premise of a society in which Level 3 automated driving support systems are realized. In particular, in an uncertain and dynamically changing environment, each vehicle is regarded as an agent that uses traffic information to learn the external environment and act efficiently in there. Their behavior can be described using congestion game theory, reinforcement learning, and stochastic approximation theory. The traffic network simulation method proposed in this research is based on these theories, and is a multi-agent model with applicability to practical-scale networks. We propose the use of deep learning to address practical issues such as estimates of the traffic conditions and estimation of structural model parameters.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究のアプローチは、従来の長期的、静学的視点での交通計画の立案のためではなく、短期的、動的に変化する環境での需要マネージメントを前提にした交通管理計画を想定している。こうした状況下では、ベストな状態を達成する最善行動ではなく、前よりもよい状態を移行する最良行動を決定する分析枠組みが必要になる。本研究は、この目標を達成するための理論的枠組みと分析手法を提案している。
|
Report
(4 results)
Research Products
(18 results)
