2019 Fiscal Year Final Research Report
Methodologies for enhancement of intelligent transport systems through loosely-coupled cooperation of roadside and on-board units
| Project/Area Number |
16KT0106
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 特設分野 |
|---|
| Research Field |
Intensification of Artifact Systems
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2016-07-19 – 2020-03-31
|
| Keywords | 分散協調システム / 機械学習 / 高度交通システム |
|---|
| Outline of Final Research Achievements |
This research supports the enhancement of the intelligent transport system through the loosely-coupled cooperation of roadside units and on-board units. For this purpose, a methodology of distributed deep-neural network-based learning for decision-making and status prediction of the transport system is developed. Specifically, a method that allows multiple devices to share the functions of a deep neural network and cooperate with each other, as well as a distributed event processing platform that has a mechanism to perform load balancing and cooperative processing in a loosely coupled manner, have been investigated. Besides, a vehicle mobility reproduction platform to evaluate these mechanisms are developed. Through proof-of-concept implementations and numerous simulation experiments, the feasibility of the proposed methodologies is shown.
|
| Free Research Field |
モバイルコンピューティング
|
| Academic Significance and Societal Importance of the Research Achievements |
分散協調学習技術はその独創性が注目され，国際WSで2件の基調講演および国内外で2件の招待講演を実施した．国内では情報処理学会の本分野の最大規模のシンポジウムで最優秀論文賞を受賞した．複合イベント処理を完全分散で実現するシステムに関しては分散システムの歴史あるIEEEの国際会議DCOSSや国際論文誌IEEE Access等で発表した．電子情報通信学会論文誌の招待論文でもコンセプトを発信している．車両モビリティ関連技術はIEEE の国際シンポジウムでBest Paper Awardを受賞し，本分野のIEEEの最難関フラグシップ国際会議PerCom2019での採択・発表を実現している．
|
