Development of Algorithm for Ship Handling Decision using Deep Reinforcement Learning
| Project/Area Number |
18H01642
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 24020:Marine engineering-related
|
|---|
| Research Institution | Kyushu University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
石橋 篤 東京海洋大学, 学術研究院, 講師 (00242321)
茨木 洋 九州大学, 工学研究院, 助教 (20274508)
木村 元 九州大学, 工学研究院, 教授 (40302963)
|
|---|
| Project Period (FY) |
2018-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥17,550,000 (Direct Cost: ¥13,500,000、Indirect Cost: ¥4,050,000)
Fiscal Year 2020: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2019: ¥6,370,000 (Direct Cost: ¥4,900,000、Indirect Cost: ¥1,470,000)
Fiscal Year 2018: ¥8,450,000 (Direct Cost: ¥6,500,000、Indirect Cost: ¥1,950,000)
|
|---|
| Keywords | 自律運航船舶 / 海上安全 / 深層強化学習 / 操船判断 / 衝突回避 / 自動運航船 |
|---|
| Outline of Final Research Achievements |
In order to realize autonomous ships, it is necessary to develop an algorithm to properly evaluate circumstance around an own ship such as weather conditions, states of relative ships and so on and to make a decision to navigate the own ship safely changing her course and speed. In this research, an algorithm which can make a ship possible to navigate autonomously considering various complicated conditions around a ship by introducing deep reinforcement learning were developed. Furthermore, a model ship control system which can be used to evaluate the performance of the developed navigation algorithm was also developed. The manoeuvring motion of a model ship can be controlled based on information such as model ship’s position, heading angle, speed, yaw rate and so on.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究で開発した操船判断アルゴリズムの研究をさらに進めて自律航行船舶を実現することができれば，海難事故の発生原因のかなりの割合を占めている操船者の誤判断や不適切な操船等の人的要因による海難事故の防止に寄与することが期待される。また，自船の周囲の複雑な環境条件を適切に評価して航路を設定し，さらに自船の周囲を航行する複数の船舶と協調して航行することが可能となれば，安全かつ効率的な海上貨物輸送システムの構築に繋がる。
|
Report
(4 results)
Research Products
(5 results)
