2021 Fiscal Year Final Research Report
Influence of autonomous vehicles learning system optimum movement with AI on traffic flows and driving behavior
| Project/Area Number |
19K04660
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 22050:Civil engineering plan and transportation engineering-related
|
|---|
| Research Institution | Meijo University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2019-04-01 – 2022-03-31
|
| Keywords | 自動運転 / 深層学習 / AI / マルチエージェント / シミュレーション / ドライビングシミュレータ / 信号制御 / 走行挙動 |
|---|
| Outline of Final Research Achievements |
This study found that autonomous vehicles trained to pass smoothly through signalized intersections can contribute to smoother traffic flow as their mixing ratio increases. It was also found that such effect is increased by coordinating the autonomous vehicles with the traffic signal control. The mixture of autonomous vehicles also has an effect on the surrounding human driven drivers. In particular, it was suggested that the driving behavior of a human driven vehicle may be smoothed in the case of a mixture of autonomous vehicles that emphasize safety. The results of this study show that the mixture of autonomous vehicles with human driven vehicles can lead to an improvement of the traffic conditions in the entire area.
|
| Free Research Field |
交通工学
|
| Academic Significance and Societal Importance of the Research Achievements |
情報通信技術や観測技術の進展に伴い，リアルタイムで交通ビッグデータが入手可能になりつつあり，これらの情報を活用した交通運用策が期待されている．本研究で得られた成果からは，交通観測データによって個々の自動走行車両の円滑化や最短経路の予測が可能であることが示された．近い将来に予想される自動走行車両が走行する環境において，本研究の成果に基づいた走行制御を行うことによって，交通混雑の緩和につなげられる．エネルギー消費を減少させ二酸化炭素排出量も削減可能になる．また，自動走行車両が一般車両に混在する状態においても，交通状況の改善につなげられる可能性も示された．
|
