Chinese Journal of Ship Research, Volume. 20, Issue 1, 172(2025)
Autonomous decision-making method of unmanned ship based on improved DDPG algorithm
Figures & Tables(13)
![[in Chinese]](/Images/icon/loading.gif){kind=icon}
Table 1. The principle parameters of the unmanned vehicle
View tableView in ArticleTable 1. The principle parameters of the unmanned vehicle
参数 数值 船长/m 52.5 船宽/m 8.6 吃水深度/m 2.29 最大指令舵角/(°) 35 额定速度/kn 14
Table 2. The parameters of improved DDPG algorithm and reward functions
View tableView in ArticleTable 2. The parameters of improved DDPG algorithm and reward functions
参数 数值 参数 数值 折扣率 $\gamma $ 0.99 制导奖励权重 ${\lambda _{\rm{g}}}$ 5 策略网络学习率 0.000 3 航向修正奖励权重 ${\lambda _{\rm{yaw}}}$ −2.5 价值网络学习率 0.000 3 COLREGs奖励权重 $ \lambda_{\mathrm{C}\mathrm{ }} $ 6.5 LSTM 隐藏层数量 256 雷达线长度 $ {r_{\rm{1} }} $ /n mile3.5 软更新系数 0.01 船舶领域半径 $ {r_{\rm{d}}} $ /n mile1.4 批次大小 256 角度权重 $\varepsilon $ 0.23 波风向/(°) 31.4 有效波高/m 0.17 波浪周期/s 6.2 平均风速/(m·s−1) 0.38
Table 3. The initial data of two-ship encounter situation
View tableView in ArticleTable 3. The initial data of two-ship encounter situation
会遇局面 无人船 起始位置/n mile 目标位置/n mile 速度/kn 对遇 OS (−1.0, −1.0) (5.0, 6.0) 14.00 TS (3.0, −3.0) (−2.0, −2.0) 9.18 右交叉 OS (1.0, −4.0) (−1.0, 6.0) 14.00 TS (4.0, 0) (−4.0, 0) 9.60 左交叉 OS (−4.0, 0) (1.0, 8.0) 14.00 TS (−6.0, 4.0) (2.0, 4.0) 9.60 追越 OS (−1.0, −4.5) (−.01, 8.0) 14.00 TS (−1.0, −2.0) (−1.0, 4.0) 6.00 大角度右交叉 OS (−2.2, −3.1) (0.8, 2.7) 14.00 TS (0.5, −3.4) (−0.2, 1.3) 9.90 被追越 OS (4.5, 3.6) (4.5, 5.9) 14.00 TS (4.5, 2.6) (4.5, 6.8) 19.00
Table 4. The initial information of there-ship encounter situation
View tableView in ArticleTable 4. The initial information of there-ship encounter situation
无人船 起始位置/n mile 目标位置/n mile 速度/kn OS (0, −1.20) (−0.40, 1.40) 14.00 TS1 (−1.25, 1.70) (1.35, −0.40) 13.75 TS2 (1.50, 0.60) (−1.00, −0.50) 11.20 TS3 (−1.50, −0.80) (1.40, −0.80) 11.90
Table 5. The trajectories comparison for two algorithms
View tableView in ArticleTable 5. The trajectories comparison for two algorithms
算法 实验 次数 路径长度 /n mile 决策时间/s 最小会遇距离 /n mile 改进DDPG算法 1 3.403 875.0 0.760 2 3.352 862.0 0.900 3 3.348 861.0 0.650 4 3.316 853.0 0.730 5 3.432 882.0 0.840 传统DDPG算法 3.596 924.6 0.620 平均值 3.370 866.6 0.776
Tools
Get Citation
Copy Citation Text
Wei GUAN, Shuhui HAO, Zhewen CUI, Miaomiao WANG. Autonomous decision-making method of unmanned ship based on improved DDPG algorithm[J]. Chinese Journal of Ship Research, 2025, 20(1): 172
Paper Information
Category: Planning and Decision-making
Received: May. 14, 2024
Accepted: --
Published Online: Mar. 13, 2025
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20